Dental panoramic radiographs are often obtained at dental clinic visits for diagnosis and recording purposes. Automated filing of dental charts can help dentists in reducing their workload and improving diagnostic efficiency. The purpose of this study is to develop a system that prerecords a dental chart by recognizing teeth with their numbers and restoration history on dental panoramic radiographs. The proposed system uses YOLO which detects 16 types of teeth and restoration conditions simultaneously. Based on the detected tooth types, they were further classified into 32 types and combined with the tooth conditions by post-processing. We tested our method on 870 panoramic images obtained at 10 different facilities by 5-fold cross validation. The proposed method obtained 0.99 recall and precision for recognition of 32 tooth types and 0.90 recall and 0.90 precision on determining the tooth condition. It has the potential to assist prefiling the dental charts for efficient dental care.
Purpose: The purpose of our study was to analyze dental panoramic radiographs and contribute to dentists’ diagnosis by automatically extracting the information necessary for reading them. As the initial step, we detected teeth and classified their tooth types in this study.
Approach: We propose single-shot multibox detector (SSD) networks with a side branch for 1-class detection without distinguishing the tooth type and for 16-class detection (i.e., the central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, and third molar, distinguished by the upper and lower jaws). In addition, post-processing was conducted to integrate the results of the two networks and categorize them into 32 classes, differentiating between the left and right teeth. The proposed method was applied to 950 dental panoramic radiographs obtained at multiple facilities, including a university hospital and dental clinics.
Results: The recognition performance of the SSD with a side branch was better than that of the original SSD. In addition, the detection rate was improved by the integration process. As a result, the detection rate was 99.03%, the number of false detections was 0.29 per image, and the classification rate was 96.79% for 32 tooth types.
Conclusions: We propose a method for tooth recognition using object detection and post-processing. The results show the effectiveness of network branching on the recognition performance and the usefulness of post-processing for neural network output.
The diagnosis using a time-intensity curve (TIC) is considered to be useful in the differentiation of pancreatic tumors. TIC is a graph that shows a contrast intensity of contrast-enhanced endoscopic ultrasonography over time. We propose a method to classify pancreatic tumors, which generates and uses two types of images representing a contrast effect from ultrasound endoscopic images. The first type is a two-dimensional histogram that adds information about a distribution of luminance values per frame to TIC which features a contrast effect over time. The second type is a frame with the highest average luminance value among all frames of each case. The frame featured a contrast enhancement pattern of the tumor. The features of the two images were extracted using deep learning. The two extracted features were combined by a concatenate layer. The combined feature outputs by a fully connected layer as the probability of pancreatic cancer. In this study, 131 cases with pancreatic tumors (pancreatic cancer: 86 cases, non-pancreatic cancer: 45 cases) were used. As a result of receiver operating characteristic analysis of the output probability, the area under the curve was 0.82, the sensitivity was 80.2%, and the specificity was 71.1%.
The purpose of this study is to analyze dental panoramic radiographs for completing dental files to contribute to the diagnosis by dentists. In this study, we recognized 32 tooth types and classified four tooth attributes (tooth, remaining root, pontic, and implant) using 925 dental panoramic radiographs. YOLOv4 and post-processing were used for the recognition of 32 tooth types. As a result, the tooth detection recall was 99.65%, the number of false positives was 0.10 per image, and the 32-type recognition recall was 98.55%. For the classification of the four tooth attributes, two methods were compared. In Method 1, image classification was performed using a clipped image based on the tooth detection result. In Method 2, the labels of tooth attributes were added to the labels of tooth types in object detection. By providing two labels for the same bounding box, we performed multi-label object detection. The accuracy of Method 1 was 0.995 and that of Method 2 was 0.990. Method 2 uses a simple and robust model yet has comparable accuracy as Method 1. In addition, Method 2 did not require additional CNN models. This suggested the usefulness of multi-label detection.
The body cavity region contains organs and is an essential region for skeletal muscle segmentation. This study proposes a method to segment body cavity regions using U-Net with focus on the oblique abdominal muscles. The proposed method comprises two steps. First, the body cavity is segmented using U-Net. Subsequently, the abdominal muscles are identified using recognition techniques. This is achieved by removing the segmented body cavity region from the original computerized tomography (CT) images to obtain a simplified CT image for training. In this image, the visceral organ regions are masked by the body cavity; ensuring that the organs therein are excluded from the segmentation target in advance which has been a primary concern in the conventional method of skeletal muscle segmentation. The segmentation accuracies of the body cavity and oblique abdominal muscle in 16 cases were 98.50% and 84.89%, respectively, in terms of the average dice value. Furthermore, it was observed that body cavity information reduced the number of over-extracted pixels by 36.21% in the segmentation of the oblique abdominal muscles adjacent to the body cavity, improving the segmentation accuracy. In future studies, it could be beneficial to examine whether the proposed simplification of CT images by segmentation of body cavities is also effective for abdominal musculoskeletal muscles adjacent to body cavities divided by tendon ends, such as the rectus abdominis.
Supervised learning for image segmentation requires annotated images. However, image annotation has the problem that it is time-consuming. This problem is particularly significant in the erector spinae muscle segmentation due to the large size of the muscle. Therefore, this study considers the relationship between the number of annotated images used for training and segmentation accuracy of the erector spinae muscle in torso CT images. We use Bayesian U-Net, which has shown high accuracy in thigh muscle segmentation, for the segmentation of the erector spinae muscle. In the network training, we limit the number of slices for each case and the number of cases to 100%, 50%, 25%, and 10%. In the experiment, we use 30 torso CT images, including 6 cases for the test dataset. Experimental results are evaluated by the mean Dice value of the test dataset. Using 100% of the slices per case, the segmentation accuracy with 100%, 50%, 25%, and 10% of the cases was 0.934, 0.927, 0.926, and 0.890, respectively. On the other hand, using 100% of the cases, the segmentation accuracy with 100%, 50%, 25%, and 10% of the slices per case was 0.934, 0.934, 0.933, and 0.931, respectively. Furthermore, the segmentation accuracy with 100% of the cases and 10% of the slices per case was higher than that of the previous method. We showed that it is feasible to achieve high segmentation accuracy with a limited number of annotated images by selecting several slices from a limited number of cases for training.
We propose an approach for the automatic segmentation of mammary gland regions on 3D CT images, aiming to accomplish breast cancer risk assessment through CT scans acquired in clinical medicine for various diagnostic purposes. The proposed approach uses a hybrid method that embeds a deep-learning-based attention mechanism as a module into a conventional framework, which originally uses a probabilistic atlas to accomplish Bayesian inference to estimate the pixelwise probability of mammary gland regions on CT images. In this work, we replace both the construction and application of a probabilistic atlas, which is time-consuming and complicated to realize, by a visual explanation from the attention mechanism of a classifier learned through weak supervision. In the experiments, we applied the proposed approach to the segmentation of mammary gland regions based on 174 torso CT scans and evaluated its performance by comparing the segmentation results to human sketches on 14 CT cases. The experimental results showed that the attention maps of the classifier successfully focused on the mammary gland regions on the CT images and could replace the atlas for supporting mammary gland segmentation. The preliminary results on 14 test CT scans showed that the mammary gland regions were segmented successfully with a mean value of 50.6% on the Dice similarity coefficient against the human sketches. We confirmed that the proposed approach, combining deep learning and conventional methods, shows a higher computing efficiency, much better robustness, and easier implementation than our previous approach based on a probabilistic atlas.
The purpose of this study is to analyze dental panoramic radiographs for completing dental files to contribute to the diagnosis by dentists. As the initial stage, we detected each tooth and classified its tooth type. Since the final goal of this study includes multiple tasks, such as determination of dental conditions and recognition of lesions, we proposed a multitask training based on a Single Shot Multibox Detector (SSD) with a branch to predict the presence or absence of a tooth. The results showed that the proposed model improved the detection rate by 1.0%, the number of false positives per image by 0.03, and the detection rate by tooth type (total number of successfully detected and classified teeth/total number of teeth) by 1.6% compared with the original SSD, suggesting the effectiveness of the multi-task learning in dental panoramic radiographs. In addition, we integrated results of single-class detection without distinguishing the tooth type and 16-class (central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, third molar, distinguished by upper and lower jaws) detection for improving the detection rate and included post-processing for classification of teeth into 32 types and correction of tooth numbering. As a result, the detection rate of 98.8%, 0.33 false positives per image, and classification rate of 92.4% for 32 tooth types were archived.
Early detection of glaucoma is important to slow down progression of the disease and to prevent total vision loss. When the retinal nerve is damaged, the thickness of the nerve fiber layer decreases. It is difficult, however, to detect subtle change in early disease stages on retinal fundus photographs. Although an optical coherence tomography (OCT) is generally more sensitive and can evaluate the thicknesses of retinal layers, it is performed as a diagnostic exam rather than screening exam. Retinal fundus photographs are frequently performed for diagnosis and follow-ups at ophthalmology visits and for general health checkups. It will be useful if suspicious regions can be detected on retinal photographs. The purpose of this study is to estimate the regions of defected nerves on retinal photographs using the deep learning model trained by OCT data. The network is based on the fully convolutional network. The region including an optic disc is extracted from the retinal photographs and is used as the input data. The OCT image of the same patient is registrated to the retinal image based on the blood vessel networks, and the deviation map specifying the regions with decreased nerve layer thickness is used as teacher data. The proposed method achieved 76% accuracy in assessing the defected and non-defected regions. It can be useful as a screening tool and for visual assistance in glaucoma diagnosis.
Dental record plays an important role in dental diagnosis and personal identification. Automatic image preinterpretation can help reducing dentists’ workload and improving diagnostic efficiency. Systematic dental record filing enables effective utilization of accumulated records at dental clinics for forensic identification. We have been investigating a tooth labeling method on dental cone-beam CT images for the purpose of automatic filing of dental charts. In our previous method, two separate networks were employed for detection and classification of teeth. Although detection accuracy was promising, classification performance had a room of improvement. The purpose of this study was to investigate the use of the relation network to utilize information of positional relationship between teeth for the detection and classification. Using the proposed method, both detection and classification performance improved. Especially, the tooth type classification accuracy improved. The proposed method can be useful in automatic filing of the dental chart.
The skeletal muscle exists in the whole body and can be observed in many cross sections in various tomographic images. Skeletal muscle atrophy is due to aging and disease, and the abnormality is difficult to distinguish visually. In addition, although skeletal muscle analysis requires a technique for accurate site-specific measurement of skeletal muscle, it is only realized in a limited region. We realized automatic site-specific recognition of skeletal muscle from whole-body CT images using model-based methods. Three-dimensional texture analysis revealed imaging features with statistically significant differences between amyotrophic lateral sclerosis (ALS) and other muscular diseases accompanied by atrophy. In recent years, deep learning technique is also used in the field of computer-aided diagnosis. Therefore, in this initial study, we performed automatic classification of amyotrophic diseases using deep learning for the upper extremity and lower limb regions. The classification accuracy was highest in the right forearm, which was 0.960 at the maximum (0.903 on average). In the future, methods for differentiating more kinds of muscular atrophy and clinical application of ALS detection by analyzing muscular regions must be considered.
In the dopamine nerves of the nigrostriatal body in the brain, 123I-FP-CIT binds to dopamine transporter (DAT), the distribution of which can be visualized on a single photon-emission computed tomography (SPECT) image. The Tossici-Bolt method is generally used to analyze SPECT images. However, since the Tossici-Bolt method uses a fixed region of interest, it is susceptible to the influence of non-accumulated parts. Magnetic resonance (MR) images are effective for recognizing the shape of the striatal region. Here we used MR images generated by deep learning from low-dose CT images taken with SPECT/CT devices. The purpose of this study was to perform a quantitative analysis with high repeatability using the striatal region extracted from automatically generated MR images. First, an MR image was generated from a CT image by pix2pix. After that, a striatal region was extracted from the generated MR image by PSPNet[3]. A quantitative analysis using specific binding ratio was performed using this region. For the experiments, 60 clinical cases of SPECT/CT and MR images were used. The specific binding ratios calculated by this method and the Tossici-Bolt method were compared. As a result, better results than with the Tossici-Bolt method were calculated in 12 cases. Therefore, generating MR images from low-dose CT images and segmentation by deep learning may contribute to quantitative analysis with high reproducibility of DAT imaging.
This paper proposes a novel method to learn a 3D non-rigid deformation for automatic image registration between Positron Emission Tomography (PET) and Computed Tomography (CT) scans obtained from the same patient. There are two modules in the proposed scheme including (1) low-resolution displacement vector field (LR-DVF) estimator, which uses a 3D deep convolutional network (ConvNet) to directly estimate the voxel-wise displacement (a 3D vector field) between PET/CT images, and (2) 3D spatial transformer and re-sampler, which warps the PET images to match the anatomical structures in the CT images using the estimated 3D vector field. The parameters of the ConvNet are learned from a number of PET/CT image pairs via an unsupervised learning method. The Normalized Cross Correlation (NCC) between PET/CT images is used as the similarity metric to guide an end-to-end learning process with a constraint (regular term) to preserve the smoothness of the 3D deformations. A dataset with 170 PET/CT scans is used in experiments based on 10-fold cross-validation, where a total of 22,338 3D patches are sampled from the dataset. In each fold, 3D patches from 153 patients (90%) are used for training the parameters, while the remaining whole-body voxels from 17 patients (10%) are used for testing the performance of the image registration. The experimental results demonstrate that the image registration accuracy (the mean value of NCCs) is increased from 0.402 (the initial situation) to 0.567 on PET/CT scans using the proposed scheme. We also compare the performance of our scheme with previous work (DIRNet) and the advantage of our scheme is confirmed via the promising results.
We propose an automatic approach to anatomy partitioning on three-dimensional (3D) computed tomography (CT) images that divides the human torso into several volumes of interest (VOIs) according to anatomical definition. In the proposed approach, a deep convolutional neural network (CNN) is trained to automatically detect the bounding boxes of organs on two-dimensional (2D) sections of CT images. The coordinates of those boxes are then grouped so that a vote on a 3D VOI (called localization) for each organ can be obtained separately. We applied this approach to localize the 3D VOIs of 17 types of organs in the human torso and then evaluated the performance of the approach by conducting a four-fold crossvalidation using a dataset consisting of 240 3D CT scans with the human-annotated ground truth for each organ region. The preliminary results showed that 86.7% of the 3D VOIs of the 3177 organs in the 240 test CT images were localized with acceptable accuracy (mean of Jaccard indexes was 72.8%) compared to that of the human annotations. This performance was better than that of the state-of-the-art method reported recently. The experimental results demonstrated that using a deep CNN for anatomy partitioning on 3D CT images was more efficient and useful compared to the method used in our previous work.
The purpose of this study is to evaluate and compare the performance of modern deep learning techniques for automatically recognizing and segmenting multiple organ regions on 3D CT images. CT image segmentation is one of the important task in medical image analysis and is still very challenging. Deep learning approaches have demonstrated the capability of scene recognition and semantic segmentation on nature images and have been used to address segmentation problems of medical images. Although several works showed promising results of CT image segmentation by using deep learning approaches, there is no comprehensive evaluation of segmentation performance of the deep learning on segmenting multiple organs on different portions of CT scans. In this paper, we evaluated and compared the segmentation performance of two different deep learning approaches that used 2D- and 3D deep convolutional neural networks (CNN) without- and with a pre-processing step. A conventional approach that presents the state-of-the-art performance of CT image segmentation without deep learning was also used for comparison. A dataset that includes 240 CT images scanned on different portions of human bodies was used for performance evaluation. The maximum number of 17 types of organ regions in each CT scan were segmented automatically and compared to the human annotations by using ratio of intersection over union (IU) as the criterion. The experimental results demonstrated the IUs of the segmentation results had a mean value of 79% and 67% by averaging 17 types of organs that segmented by a 3D- and 2D deep CNN, respectively. All the results of the deep learning approaches showed a better accuracy and robustness than the conventional segmentation method that used probabilistic atlas and graph-cut methods. The effectiveness and the usefulness of deep learning approaches were demonstrated for solving multiple organs segmentation problem on 3D CT images.
In large disasters, dental record plays an important role in forensic identification. However, filing dental charts for corpses is not an easy task for general dentists. Moreover, it is laborious and time-consuming work in cases of large scale disasters. We have been investigating a tooth labeling method on dental cone-beam CT images for the purpose of automatic filing of dental charts. In our method, individual tooth in CT images are detected and classified into seven tooth types using deep convolutional neural network. We employed the fully convolutional network using AlexNet architecture for detecting each tooth and applied our previous method using regular AlexNet for classifying the detected teeth into 7 tooth types. From 52 CT volumes obtained by two imaging systems, five images each were randomly selected as test data, and the remaining 42 cases were used as training data. The result showed the tooth detection accuracy of 77.4% with the average false detection of 5.8 per image. The result indicates the potential utility of the proposed method for automatic recording of dental information.
Breast cancer screening with mammography and ultrasonography is expected to improve sensitivity compared with mammography alone, especially for women with dense breast. An automated breast volume scanner (ABVS) provides the operator-independent whole breast data which facilitate double reading and comparison with past exams, contralateral breast, and multimodality images. However, large volumetric data in screening practice increase radiologists’ workload. Therefore, our goal is to develop a computer-aided detection scheme of breast masses in ABVS data for assisting radiologists’ diagnosis and comparison with mammographic findings. In this study, false positive (FP) reduction scheme using deep convolutional neural network (DCNN) was investigated. For training DCNN, true positive and FP samples were obtained from the result of our initial mass detection scheme using the vector convergence filter. Regions of interest including the detected regions were extracted from the multiplanar reconstraction slices. We investigated methods to select effective FP samples for training the DCNN. Based on the free response receiver operating characteristic analysis, simple random sampling from the entire candidates was most effective in this study. Using DCNN, the number of FPs could be reduced by 60%, while retaining 90% of true masses. The result indicates the potential usefulness of DCNN for FP reduction in automated mass detection on ABVS images.
Amyotrophic lateral sclerosis (ALS) causes functional disorders such as difficulty in breathing and swallowing through the atrophy of voluntary muscles. ALS in its early stages is difficult to diagnose because of the difficulty in differentiating it from other muscular diseases. In addition, image inspection methods for aggressive diagnosis for ALS have not yet been established. The purpose of this study is to develop an automatic analysis system of the whole skeletal muscle to support the early differential diagnosis of ALS using whole-body CT images. In this study, the muscular atrophy parts including ALS patients are automatically identified by recognizing and segmenting whole skeletal muscle in the preliminary steps. First, the skeleton is identified by its gray value information. Second, the initial area of the body cavity is recognized by the deformation of the thoracic cavity based on the anatomical segmented skeleton. Third, the abdominal cavity boundary is recognized using ABM for precisely recognizing the body cavity. The body cavity is precisely recognized by non-rigid registration method based on the reference points of the abdominal cavity boundary. Fourth, the whole skeletal muscle is recognized by excluding the skeleton, the body cavity, and the subcutaneous fat. Additionally, the areas of muscular atrophy including ALS patients are automatically identified by comparison of the muscle mass. The experiments were carried out for ten cases with abnormality in the skeletal muscle. Global recognition and segmentation of the whole skeletal muscle were well realized in eight cases. Moreover, the areas of muscular atrophy including ALS patients were well identified in the lower limbs. As a result, this study indicated the basic technology to detect the muscle atrophy including ALS. In the future, it will be necessary to consider methods to differentiate other kinds of muscular atrophy as well as the clinical application of this detection method for early ALS detection and examine a large number of cases with stage and disease type.
This paper describes a novel approach for the automatic assessment of breast density in non-contrast three-dimensional computed tomography (3D CT) images. The proposed approach trains and uses a deep convolutional neural network (CNN) from scratch to classify breast tissue density directly from CT images without segmenting the anatomical structures, which creates a bottleneck in conventional approaches. Our scheme determines breast density in a 3D breast region by decomposing the 3D region into several radial 2D-sections from the nipple, and measuring the distribution of breast tissue densities on each 2D section from different orientations. The whole scheme is designed as a compact network without the need for post-processing and provides high robustness and computational efficiency in clinical settings. We applied this scheme to a dataset of 463 non-contrast CT scans obtained from 30- to 45-year-old-women in Japan. The density of breast tissue in each CT scan was assigned to one of four categories (glandular tissue within the breast <25%, 25%–50%, 50%–75%, and >75%) by a radiologist as ground truth. We used 405 CT scans for training a deep CNN and the remaining 58 CT scans for testing the performance. The experimental results demonstrated that the findings of the proposed approach and those of the radiologist were the same in 72% of the CT scans among the training samples and 76% among the testing samples. These results demonstrate the potential use of deep CNN for assessing breast tissue density in non-contrast 3D CT images.
We have proposed an end-to-end learning approach that trained a deep convolutional neural network (CNN) for
automatic CT image segmentation, which accomplished a voxel-wised multiple classification to directly map each voxel
on 3D CT images to an anatomical label automatically. The novelties of our proposed method were (1) transforming the
anatomical structures segmentation on 3D CT images into a majority voting of the results of 2D semantic image
segmentation on a number of 2D-slices from different image orientations, and (2) using “convolution” and “deconvolution”
networks to achieve the conventional “coarse recognition” and “fine extraction” functions which were
integrated into a compact all-in-one deep CNN for CT image segmentation. The advantage comparing to previous works
was its capability to accomplish real-time image segmentations on 2D slices of arbitrary CT-scan-range (e.g. body, chest,
abdomen) and produced correspondingly-sized output. In this paper, we propose an improvement of our proposed
approach by adding an organ localization module to limit CT image range for training and testing deep CNNs. A
database consisting of 240 3D CT scans and a human annotated ground truth was used for training (228 cases) and
testing (the remaining 12 cases). We applied the improved method to segment pancreas and left kidney regions,
respectively. The preliminary results showed that the accuracies of the segmentation results were improved significantly
(pancreas was 34% and kidney was 8% increased in Jaccard index from our previous results). The effectiveness and
usefulness of proposed improvement for CT image segmentations were confirmed.
The word "Locomotive syndrome" has been proposed to describe the state of requiring care by musculoskeletal disorders and its high-risk condition. Reduction of the knee extension strength is cited as one of the risk factors, and the accurate measurement of the strength is needed for the evaluation. The measurement of knee extension strength using a dynamometer is one of the most direct and quantitative methods. This study aims to develop a system for measuring the knee extension strength using the ultrasound images of the rectus femoris muscles obtained with non-invasive ultrasonic diagnostic equipment. First, we extract the muscle area from the ultrasound images and determine the image features, such as the thickness of the muscle. We combine these features and physical features, such as the patient’s height, and build a regression model of the knee extension strength from training data. We have developed a system for estimating the knee extension strength by applying the regression model to the features obtained from test data. Using the test data of 168 cases, correlation coefficient value between the measured values and estimated values was 0.82. This result suggests that this system can estimate knee extension strength with high accuracy.
Important features in Parkinson's disease (PD) are degenerations and losses of dopamine neurons in corpus striatum. 123I-FP-CIT can visualize activities of the dopamine neurons. The activity radio of background to corpus striatum is used for diagnosis of PD and Dementia with Lewy Bodies (DLB). The specific activity can be observed in the corpus striatum on SPECT images, but the location and the shape of the corpus striatum on SPECT images only are often lost because of the low uptake. In contrast, MR images can visualize the locations of the corpus striatum. The purpose of this study was to realize a quantitative image analysis for the SPECT images by using image registration technique with brain MR images that can determine the region of corpus striatum. In this study, the image fusion technique was used to fuse SPECT and MR images by intervening CT image taken by SPECT/CT. The mutual information (MI) for image registration between CT and MR images was used for the registration. Six SPECT/CT and four MR scans of phantom materials are taken by changing the direction. As the results of the image registrations, 16 of 24 combinations were registered within 1.3mm. By applying the approach to 32 clinical SPECT/CT and MR cases, all of the cases were registered within 0.86mm. In conclusions, our registration method has a potential in superimposing MR images on SPECT images.
The iliac muscle is an important skeletal muscle related to ambulatory function. The muscles related to ambulatory function are the psoas major and iliac muscles, collectively defined as the iliopsoas muscle. We have proposed an automated recognition method of the iliac muscle. Muscle fibers of the iliac muscle have a characteristic running pattern. Therefore, we used 20 cases from a training database to model the movement of the muscle fibers of the iliac muscle. In the recognition process, the existing position of the iliac muscle was estimated by applying the muscle fiber model. To generate an approximation mask by using a muscle fiber model, a candidate region of the iliac muscle was obtained. Finally, the muscle region was identified by using values from the gray value and boundary information. The experiments were performed by using the 20 cases without abnormalities in the skeletal muscle for modeling. The recognition result in five cases obtained a 76.9% average concordance rate. In the visual evaluation, overextraction of other organs was not observed in 85% of the cases. Therefore, the proposed method is considered to be effective in the recognition of the initial region of the iliac muscle. In the future, we will integrate the recognition method of the psoas major muscle in developing an analytical technique for the iliopsoas area. Furthermore, development of a sophisticated muscle function analysis method is necessary.
This paper describes a brand new automatic segmentation method for quantifying volume and density of mammary gland regions on non-contrast CT images. The proposed method uses two processing steps: (1) breast region localization, and (2) breast region decomposition to accomplish a robust mammary gland segmentation task on CT images. The first step detects two minimum bounding boxes of left and right breast regions, respectively, based on a machine-learning approach that adapts to a large variance of the breast appearances on different age levels. The second step divides the whole breast region in each side into mammary gland, fat tissue, and other regions by using spectral clustering technique that focuses on intra-region similarities of each patient and aims to overcome the image variance caused by different scan-parameters. The whole approach is designed as a simple structure with very minimum number of parameters to gain a superior robustness and computational efficiency for real clinical setting. We applied this approach to a dataset of 300 CT scans, which are sampled with the equal number from 30 to 50 years-old-women. Comparing to human annotations, the proposed approach can measure volume and quantify distributions of the CT numbers of mammary gland regions successfully. The experimental results demonstrated that the proposed approach achieves results consistent with manual annotations. Through our proposed framework, an efficient and effective low cost clinical screening scheme may be easily implemented to predict breast cancer risk, especially on those already acquired scans.
MIBG (iodine-123-meta-iodobenzylguanidine) is a radioactive medicine that is used to help diagnose not only myocardial diseases but also Parkinson’s diseases (PD) and dementia with Lewy Bodies (DLB). The difficulty of the segmentation around the myocardium often reduces the consistency of measurement results. One of the most common measurement methods is the ratio of the uptake values of the heart to mediastinum (H/M). This ratio will be a stable independent of the operators when the uptake value in the myocardium region is clearly higher than that in background, however, it will be unreliable indices when the myocardium region is unclear because of the low uptake values. This study aims to develop a new measurement method by using the image fusion of three modalities of MIBG scintigrams, 201-Tl scintigrams, and chest radiograms, to increase the reliability of the H/M measurement results. Our automated method consists of the following steps: (1) construct left ventricular (LV) map from 201-Tl myocardium image database, (2) determine heart region in chest radiograms, (3) determine mediastinum region in chest radiograms, (4) perform image fusion of chest radiograms and MIBG scintigrams, and 5) perform H/M measurements on MIBG scintigrams by using the locations of heart and mediastinum determined on the chest radiograms. We collected 165 cases with 201-Tl scintigrams and chest radiograms to construct the LV map. Another 65 cases with MIBG scintigrams and chest radiograms were also collected for the measurements. Four radiological technologists (RTs) manually measured the H/M in the MIBG images. We compared the four RTs’ results with our computer outputs by using Pearson’s correlation, the Bland-Altman method, and the equivalency test method. As a result, the correlations of the H/M between four the RTs and the computer were 0.85 to 0.88. We confirmed systematic errors between the four RTs and the computer as well as among the four RTs. The variation range of the H/M among the four RTs was obtained as 0.22 based on the equivalency test method. The computer outputs were existed within this range. We concluded that our image fusion method could measure equivalent values between the system and the RTs.
This paper describes an automatic approach for anatomy partitioning on three-dimensional (3D) computedtomography (CT) images that divide the human torso into several volume-of-interesting (VOI) images based on anatomical definition. The proposed approach combines several individual detections of organ-location with a groupwise organ-location calibration and correction to achieve an automatic and robust multiple-organ localization task. The essence of the proposed method is to jointly detect the 3D minimum bounding box for each type of organ shown on CT images based on intra-organ-image-textures and inter-organ-spatial-relationship in the anatomy. Machine-learning-based template matching and generalized Hough transform-based point-distribution estimation are used in the detection and calibration processes. We apply this approach to the automatic partitioning of a torso region on CT images, which are divided into 35 VOIs presenting major organ regions and tissues required by routine diagnosis in clinical medicine. A database containing 4,300 patient cases of high-resolution 3D torso CT images is used for training and performance evaluations. We confirmed that the proposed method was successful in target organ localization on more than 95% of CT cases. Only two organs (gallbladder and pancreas) showed a lower success rate: 71 and 78% respectively. In addition, we applied this approach to another database that included 287 patient cases of whole-body CT images scanned for positron emission tomography (PET) studies and used for additional performance evaluation. The experimental results showed that no significant difference between the anatomy partitioning results from those two databases except regarding the spleen. All experimental results showed that the proposed approach was efficient and useful in accomplishing localization tasks for major organs and tissues on CT images scanned using different protocols.
KEYWORDS: Bone, Computer aided diagnosis and therapy, Panoramic photography, Radiography, FDA class I medical device development, Computing systems, Dentistry, Minerals, FDA class II medical device development, Neodymium
Findings on dental panoramic radiographs (DPRs) have shown that mandibular cortical index (MCI) based on the morphology of mandibular inferior cortex was significantly correlated with osteoporosis. MCI on DPRs can be categorized into one of three groups and has the high potential for identifying patients with osteoporosis. However, most DPRs are used only for diagnosing dental conditions by dentists in their routine clinical work. Moreover, MCI is not generally quantified but assessed subjectively. In this study, we investigated a computer-aided diagnosis (CAD) system that automatically classifies mandibular cortical bone for detection of osteoporotic patients at early stage. First, an inferior border of mandibular bone was detected by use of an active contour method. Second, regions of interest including the cortical bone are extracted and analyzed for its thickness and roughness. Finally, support vector machine (SVM) differentiate cases into three MCI categories by features including the thickness and roughness. Ninety eight DPRs were used to evaluate our proposed scheme. The number of cases classified to Class I, II, and III by a dental radiologist are 56, 25 and 17 cases, respectively. Experimental result based on the leave-one-out cross-validation evaluation showed that the sensitivities for the classes I, II, and III were 94.6%, 57.7% and 94.1%, respectively. Distribution of the groups in the feature space indicates a possibility of MCI quantification by the proposed method. Therefore, our scheme has a potential in identifying osteoporotic patients at an early stage.
Periodontal disease is a kind of typical dental diseases, which affects many adults. The presence of alveolar bone resorption, which can be observed from dental panoramic radiographs, is one of the most important signs of the progression of periodontal disease. Automatically evaluating alveolar-bone resorption is of important clinic meaning in dental radiology. The purpose of this study was to propose a novel system for automated alveolar-bone-resorption evaluation from digital dental panoramic radiographs for the first time. The proposed system enables visualization and quantitative evaluation of alveolar bone resorption degree surrounding the teeth. It has the following procedures: (1) pre-processing for a test image; (2) detection of tooth root apices with Gabor filter and curve fitting for the root apex line; (3) detection of features related with alveolar bone by using image phase congruency map and template matching and curving fitting for the alveolar line; (4) detection of occlusion line with selected Gabor filter; (5) finally, evaluation of the quantitative alveolar-bone-resorption degree in the area surrounding teeth by simply computing the average ratio of the height of the alveolar bone and the height of the teeth. The proposed scheme was applied to 30 patient cases of digital panoramic radiographs, with alveolar bone resorption of different stages. Our initial trial on these test cases indicates that the quantitative evaluation results are correlated with the alveolar-boneresorption degree, although the performance still needs further improvement. Therefore it has potential clinical practicability.
Several studies have reported the presence of carotid artery calcifications (CACs) on dental panoramic radiographs (DPRs) as a possible sign of arteriosclerotic diseases. However, CACs are not easily visible at the common window level for dental examinations, and dentists, in general, are not looking for CACs. Computerized detection of CACs may help dentists in referring patients with a risk of arteriosclerotic diseases to have a detailed examination at a medical clinic. Downside of our previous method was a relatively large number of false positives (FPs). In this study, we attempted to reduce FPs by including an additional feature and selecting effective features for the classifier. A hundred DPRs including 34 cases with calcifications were included. Initial candidates were detected by thresholding the output of top-hat operation. For each candidate, 10 features and a new feature characterizing the relative position of a CAC with reference to the lower mandible edge were determined. After the rule-based FP reduction, candidates were classified into CACs and FPs by a support vector machine. Based on the leave-one-out cross-validation evaluations, an average number of FPs was 3.1 per image at 90.4% sensitivity using seven features selected. Compared to our previous method, the number of FPs was reduced by 38% at the same sensitivity level. The proposed method has a potential in identifying patients with a risk of arteriosclerosis early via general dental examinations.
This paper describes a universal approach to automatic segmentation of different internal organ and tissue regions in three-dimensional (3D) computerized tomography (CT) scans. The proposed approach combines object localization, a probabilistic atlas, and 3D GrabCut techniques to achieve automatic and quick segmentation. The proposed method first detects a tight 3D bounding box that contains the target organ region in CT images and then estimates the prior of each pixel inside the bounding box belonging to the organ region or background based on a dynamically generated probabilistic atlas. Finally, the target organ region is separated from the background by using an improved 3D GrabCut algorithm. A machine-learning method is used to train a detector to localize the 3D bounding box of the target organ using template matching on a selected feature space. A content-based image retrieval method is used for online generation of a patient-specific probabilistic atlas for the target organ based on a database. A 3D GrabCut algorithm is used for final organ segmentation by iteratively estimating the CT number distributions of the target organ and backgrounds using a graph-cuts algorithm. We applied this approach to localize and segment twelve major organ and tissue regions independently based on a database that includes 1300 torso CT scans. In our experiments, we randomly selected numerous CT scans and manually input nine principal types of inner organ regions for performance evaluation. Preliminary results showed the feasibility and efficiency of the proposed approach for addressing automatic organ segmentation issues on CT images.
In this paper, we present a texture classification method based on texton learned via sparse representation (SR) with new feature histogram maps in the classification of emphysema. First, an overcomplete dictionary of textons is learned via KSVD learning on every class image patches in the training dataset. In this stage, high-pass filter is introduced to exclude patches in smooth area to speed up the dictionary learning process. Second, 3D joint-SR coefficients and intensity histograms of the test images are used for characterizing regions of interest (ROIs) instead of conventional feature histograms constructed from SR coefficients of the test images over the dictionary. Classification is then performed using a classifier with distance as a histogram dissimilarity measure. Four hundreds and seventy annotated ROIs extracted from 14 test subjects, including 6 paraseptal emphysema (PSE) subjects, 5 centrilobular emphysema (CLE)
subjects and 3 panlobular emphysema (PLE) subjects, are used to evaluate the effectiveness and robustness of the
proposed method. The proposed method is tested on 167 PSE, 240 CLE and 63 PLE ROIs consisting of mild, moderate
and severe pulmonary emphysema. The accuracy of the proposed system is around 74%, 88% and 89% for PSE, CLE
and PLE, respectively.
This paper describes an approach to accomplish the fast and automatic localization of the different inner organ regions on 3D CT scans. The proposed approach combines object detections and the majority voting technique to achieve the robust and quick organ localization. The basic idea of proposed method is to detect a number of 2D partial appearances of a 3D target region on CT images from multiple body directions, on multiple image scales, by using multiple feature spaces, and vote all the 2D detecting results back to the 3D image space to statistically decide one 3D bounding rectangle of the target organ. Ensemble learning was used to train the multiple 2D detectors based on template matching on local binary patterns and Haar-like feature spaces. A collaborative voting was used to decide the corner coordinates of the 3D bounding rectangle of the target organ region based on the coordinate histograms from detection results in three body directions. Since the architecture of the proposed method (multiple independent detections connected to a majority voting) naturally fits the parallel computing paradigm and multi-core CPU hardware, the proposed algorithm was easy to achieve a high computational efficiently for the organ localizations on a whole body CT scan by using general-purpose computers. We applied this approach to localization of 12 kinds of major organ regions independently on 1,300 torso CT scans. In our experiments, we randomly selected 300 CT scans (with human indicated organ and tissue locations) for training, and then, applied the proposed approach with the training results to localize each of the target regions on the other 1,000 CT scans for the performance testing. The experimental results showed the possibility of the proposed approach to automatically locate different kinds of organs on the whole body CT scans.
When a computer-aided diagnosis (CAD) system is used in clinical practice, it is desirable that the system is constantly
and automatically updated with new cases obtained for performance improvement. In this study, the effect of different
case selection methods for the system updates was investigated. For the simulation, the data for classification of benign and malignant masses on mammograms were used. Six image features were used for training three classifiers: linear discriminant analysis (LDA), support vector machine (SVM), and k-nearest neighbors (kNN). Three datasets, including dataset I for initial training of the classifiers, dataset T for intermediate testing and retraining, and dataset E for evaluating the classifiers, were randomly sampled from the database. As a result of intermediate testing, some cases from dataset T were selected to be added to the previous training set in the classifier updates. In each update, cases were selected using 4 methods: selection of (a) correctly classified samples, (b) incorrectly classified samples, (c) marginally classified samples, and (d) random samples. For comparison, system updates using all samples in dataset T were also evaluated. In general, the average areas under the receiver operating characteristic curves (AUCs) were almost unchanged with method (a), whereas AUCs generally degraded with method (b). The AUCs were improved with method (c) and (d), although use of all available cases generally provided the best or nearly best AUCs. In conclusion, CAD systems may be improved by retraining with new cases accumulated during practice.
Inflammation in paranasal sinus sometimes becomes chronic to take long terms for the treatment. The finding is
important for the early treatment, but general dentists may not recognize the findings because they focus on teeth
treatments. The purpose of this study was to develop a computer-aided detection (CAD) system for the inflammation in
paranasal sinus on dental panoramic radiographs (DPRs) by using the mandible contour and to demonstrate the potential usefulness of the CAD system by means of receiver operating characteristic analysis. The detection scheme consists of 3 steps: 1) Contour extraction of mandible, 2) Contralateral subtraction, and 3) Automated detection. The Canny operator and active contour model were applied to extract the edge at the first step. At the subtraction step, the right region of the extracted contour image was flipped to compare with the left region. Mutual information between two selected regions was obtained to estimate the shift parameters of image registration. The subtraction images were generated based on the shift parameter. Rectangle regions of left and right paranasal sinus on the subtraction image were determined based on the size of mandible. The abnormal side of the regions was determined by taking the difference between the averages of each region. Thirteen readers were responded to all cases without and with the automated results. The averaged AUC of all readers was increased from 0.69 to 0.73 with statistical significance (p=0.032) when the automated detection results were provided. In conclusion, the automated detection method based on contralateral subtraction technique improves readers' interpretation performance of inflammation in paranasal sinus on DPRs.
Diagnostic imaging on FDG-PET scans was often used to evaluate chemotherapy results of cancer patients. Radiologists compare the changes of lesions' activities between previous and current examinations for the evaluation. The purpose of this study was to develop a new computer-aided detection (CAD) system with temporal subtraction technique for FDGPET scans and to show the fundamental usefulness based on an observer performance study. Z-score mapping based on statistical image analysis was newly applied to the temporal subtraction technique. The subtraction images can be obtained based on the anatomical standardization results because all of the patients' scans were deformed into standard body shape. An observer study was performed without and with computer outputs to evaluate the usefulness of the scheme by ROC (receiver operating characteristics) analysis. Readers responded as confidence levels on a continuous scale from absolutely no change to definitely change between two examinations. The recognition performance of the computer outputs for the 43 pairs was 96% sensitivity with 31.1 false-positive marks per scan. The average of area-under-the-ROC-curve (AUC) from 4 readers in the observer performance study was increased from 0.85 without computer outputs to 0.90 with computer outputs (p=0.0389, DBM-MRMC). The average of interpretation time was slightly decreased from 42.11 to 40.04 seconds per case (p=0.625, Wilcoxon test). We concluded that the CAD system for torso FDG-PET scans with temporal subtraction technique might improve the diagnostic accuracy of radiologist in cancer therapy evaluation.
ROC studies require complex procedures to select cases from many data samples, and to set confidence levels in
each selected case to generate ROC curves. In some observer performance studies, researchers have to develop software
with specific graphical user interface (GUI) to obtain confidence levels from readers. Because ROC studies could be
designed for various clinical situations, it is difficult task for preparing software corresponding to every ROC studies. In
this work, we have developed software for recording confidence levels during observer studies on tiny personal handheld
devices such as iPhone, iPod touch, and iPad. To confirm the functions of our software, three radiologists performed
observer studies to detect lung nodules by using public database of chest radiograms published by Japan Society of
Radiological Technology. The output in text format conformed to the format for the famous ROC kit from the University
of Chicago. Times required for the reading each case was recorded very precisely.
We aim at using a new texton based texture classification method in the classification of pulmonary emphysema in
computed tomography (CT) images of the lungs. Different from conventional computer-aided diagnosis (CAD)
pulmonary emphysema classification methods, in this paper, firstly, the dictionary of texton is learned via applying
sparse representation(SR) to image patches in the training dataset. Then the SR coefficients of the test images over the
dictionary are used to construct the histograms for texture presentations. Finally, classification is performed by using a
nearest neighbor classifier with a histogram dissimilarity measure as distance. The proposed approach is tested on 3840
annotated regions of interest consisting of normal tissue and mild, moderate and severe pulmonary emphysema of three
subtypes. The performance of the proposed system, with an accuracy of about 88%, is comparably higher than state of
the art method based on the basic rotation invariant local binary pattern histograms and the texture classification method
based on texton learning by k-means, which performs almost the best among other approaches in the literature.
Findings of dental panoramic radiographs (DPRs) have shown that the mandibular cortical thickness (MCT) was
significantly correlated with osteoporosis. Identifying asymptomatic patients with osteoporosis through dental
examinations may bring a supplemental benefit for the patients. However, most of the DPRs are used for only diagnosing
dental conditions by dentists in their routine clinical work. The aim of this study was to develop a computeraided
diagnosis scheme that automatically measures MCT to assist dentists in screening osteoporosis. First, the inferior
border of mandibular bone was detected by use of an active contour method. Second, the locations of mental foramina
were estimated on the basis of the inferior border of mandibular bone. Finally, MCT was measured on the basis of the
grayscale profile analysis. One hundred DPRs were used to evaluate our proposed scheme. Experimental results showed
that the sensitivity and specificity for identifying osteoporotic patients were 92.6 % and 100 %, respectively. We
conducted multiclinic trials, in which 223 cases have been obtained and processed in about a month. Our scheme
succeeded in detecting all cases of suspected osteoporosis. Therefore, our scheme may have a potential to identify
osteoporotic patients at an early stage.
This paper presents a fast and robust segmentation scheme that automatically identifies and extracts a massive-organ
region on torso CT images. In contrast to the conventional algorithms that are designed empirically for segmenting a
specific organ based on traditional image processing techniques, the proposed scheme uses a fully data-driven approach
to accomplish a universal solution for segmenting the different massive-organ regions on CT images. Our scheme
includes three processing steps: machine-learning-based organ localization, content-based image (reference) retrieval,
and atlas-based organ segmentation techniques. We applied this scheme to automatic segmentations of heart, liver,
spleen, left and right kidney regions on non-contrast CT images respectively, which are still difficult tasks for traditional
segmentation algorithms. The segmentation results of these organs are compared with the ground truth that manually
identified by a medical expert. The Jaccard similarity coefficient between the ground truth and automated segmentation
result centered on 67% for heart, 81% for liver, 78% for spleen, 75% for left kidney, and 77% for right kidney. The
usefulness of our proposed scheme was confirmed.
For gaining a better understanding of bone quality, a great deal of attention has been paid to vertebral geometry in
anatomy. The aim of this study was to design a decision support scheme for vertebral geometries. The proposed scheme
consists of four parts: (1) automated extraction of bone, (2) generation of median plane image of spine, (3) detection of
vertebrae, (4) quantification of vertebral body width, depth, cross-sectional area (CSA), and trabecular bone mineral
density (BMD). The proposed scheme was applied to 10 CT cases and compared with manual tracking performed by an
anatomy expert. Mean differences in the width, depth, CSA, and trabecular BMD were 3.1 mm, 1.4 mm, 88.7 mm2, and
7.3 mg/cm3, respectively. We found moderate or high correlations in vertebral geometry between our scheme and
manual tracking (r > 0.72). In contrast, measurements obtained by using our scheme were slightly smaller than those
acquired from manual tracking. However, the outputs of the proposed scheme in most CT cases were regarded to be
appropriate on the basis of the subjective assessment of an anatomy expert. Therefore, if the appropriate outputs from the
proposed scheme are selected in advance by an anatomy expert, the results can potentially be used for an analysis of
vertebral body geometries.
The multidetector row computed tomography (MDCT) method has the potential to be used for quantitative analysis
of osteoporosis with higher accuracy and precision than that provided by conventional two-dimensional methods. It is
desirable to develop a computer-assisted scheme for analyzing vertebral geometry using body CT images. The aim of
this study was to design a computerized scheme for the localization of vertebral bodies on body CT images. Our new
scheme involves the following steps: (i) Re-formation of CT images on the basis of the center line of the spinal canal to
visually remove the spinal curvature, (ii) use of information on the position of the ribs relative to the vertebral bodies,
(iii) the construction of a simple model on the basis of the contour of the vertebral bodies on CT sections, and (iv) the
localization of individual vertebral bodies by using a template matching technique. The proposed scheme was applied to
104 CT cases, and its performance was assessed using the Hausdorff distance. The average Hausdorff distance of T2-L5
was 4.3 mm when learning models with 100 samples were used. On the other hand, the average Hausdorff distance with
10 samples was 5.1 mm. The results of our assessments confirmed that the proposed scheme could provide the location
of individual vertebral bodies. Therefore, the proposed scheme may be useful in designing a computer-based application
that analyzes vertebral geometry on body CT images.
To detect the metastatic liver tumor on CT scans, two liver edge maps on unenhanced and portal venous phase images
are firstly extracted and registered using phase-only correlation (POC) method, by which rotation and shift parameters
are detected on two log-polar transformed power spectrum images. Then the liver gray map is obtained on non-contrast
phase images by calculating the gray value within the region of edge map. The initial tumors are derived from the
subtraction of edge and gray maps as well as referring to the score from the spherical gray-level differentiation searching
(SGDS) filter. Finally the FPs are eliminated by shape and texture features. 12 normal cases and 25 cases with 44
metastatic liver tumors are used to test the performance of our algorithm, 86.7% of TPs are successfully extracted by our
CAD system with 2.5 FPs per case. The result demonstrates that the POC is a robust method for the liver registration,
and our proposed SGDS filter is effective to detect spherical shape tumor on CT images. It is expected that our CAD
system could useful for quantitative assessment of metastatic liver tumor in clinical practice.
Inflammation in the paranasal sinus is often observed in seasonal allergic rhinitis or with colds, but is also an
indication for odontogenic tumors, carcinoma of the maxillary sinus or a maxillary cyst. The detection of those findings
in dental panoramic radiographs is not difficult for radiologists, but general dentists may miss the findings since they
focus on treatments of teeth. The purpose of this work is to develop a contralateral subtraction method for detecting the
odontogenic sinusitis region on dental panoramic radiographs. We developed a contralateral subtraction technique in
paranasal sinus region, consisting of 1) image filtering of the smoothing and sobel operation for noise reduction and edge
extraction, 2) image registration of mirrored image by using mutual information, and 3) image display method of
subtracted pixel data. We employed 56 cases (24 normal and 32 abnormal). The abnormal regions and the normal cases
were verified by a board-certified radiologist using CT scans. Observer studies with and without subtraction images were
performed for 9 readers. The true-positive rate at a 50% confidence level in 7 out of 9 readers was improved, but there
was no statistical significance in the difference of area-under-curve (AUC) in each radiologist. In conclusion, the
contralateral subtraction images of dental panoramic radiographs may improve the detection rate of abnormal regions in
paranasal sinus.
Arteriolosclerosis is one cause of acquired blindness. Retinal fundus image examination is useful for early detection of
arteriolosclerosis. In order to diagnose the presence of arteriolosclerosis, the physicians find the silver-wire arteries, the
copper-wire arteries and arteriovenous crossing phenomenon on retinal fundus images. The focus of this study was to
develop the automated detection method of the arteriovenous crossing phenomenon on the retinal images. The blood
vessel regions were detected by using a double ring filter, and the crossing sections of artery and vein were detected by
using a ring filter. The center of that ring was an interest point, and that point was determined as a crossing section when
there were over four blood vessel segments on that ring. And two blood vessels gone through on the ring were classified
into artery and vein by using the pixel values on red and blue component image. Finally, V2-to-V1 ratio was measured for
recognition of abnormalities. V1 was the venous diameter far from the blood vessel crossing section, and V2 was the
venous diameter near from the blood vessel crossing section. The crossing section with V2-to-V1 ratio over 0.8 was
experimentally determined as abnormality. Twenty four images, including 27 abnormalities and 54 normal crossing
sections, were used for preliminary evaluation of the proposed method. The proposed method was detected 73% of
crossing sections when the 2.8 sections per image were mis-detected. And, 59% of abnormalities were detected by
measurement of V1-to-V2 ratio when the 1.7 sections per image were mis-detected.
X-ray CT images have been widely used in clinical routine in recent years. CT images scanned by a modern CT
scanner can show the details of various organs and tissues. This means various organs and tissues can be simultaneously
interpreted on CT images. However, CT image interpretation requires a lot of time and energy. Therefore, support for
interpreting CT images based on image-processing techniques is expected. The interpretation of the spinal curvature is
important for clinicians because spinal curvature is associated with various spinal disorders. We propose a quantification
scheme of the spinal curvature based on the center line of spinal canal on CT images. The proposed scheme consists of
four steps: (1) Automated extraction of the skeletal region based on CT number thresholding. (2) Automated extraction
of the center line of spinal canal. (3) Generation of the median plane image of spine, which is reformatted based on the
spinal canal. (4) Quantification of the spinal curvature. The proposed scheme was applied to 10 cases, and compared
with the Cobb angle that is commonly used by clinicians. We found that a high-correlation (for the 95% confidence
interval, lumbar lordosis: 0.81-0.99) between values obtained by the proposed (vector) method and Cobb angle. Also, the
proposed method can provide the reproducible result (inter- and intra-observer variability: within 2°). These
experimental results suggested a possibility that the proposed method was efficient for quantifying the spinal curvature
on CT images.
Glaucoma is a leading cause of permanent blindness. Retinal fundus image examination is useful for early detection of
glaucoma. In order to evaluate the presence of glaucoma, the ophthalmologists determine the cup and disc areas and they
diagnose glaucoma using a vertical cup-to-disc ratio. However, determination of the cup area is very difficult, thus we
propose a method to measure the cup-to-disc ratio using a vertical profile on the optic disc. First, the blood vessels were
erased from the image and then the edge of optic disc was then detected by use of a canny edge detection filter. Twenty
profiles were then obtained around the center of the optic disc in the vertical direction on blue channel of the color image,
and the profile was smoothed by averaging these profiles. After that, the edge of the cup area on the vertical profile was
determined by thresholding technique. Lastly, the vertical cup-to-disc ratio was calculated. Using seventy nine images,
including twenty five glaucoma images, the sensitivity of 80% and a specificity of 85% were achieved with this method.
These results indicated that this method can be useful for the analysis of the optic disc in glaucoma examinations.
Abnormalities of retinal vasculatures can indicate health conditions in the body, such as the high blood pressure and
diabetes. Providing automatically determined width ratio of arteries and veins (A/V ratio) on retinal fundus images may
help physicians in the diagnosis of hypertensive retinopathy, which may cause blindness. The purpose of this study was
to detect major retinal vessels and classify them into arteries and veins for the determination of A/V ratio. Images used in
this study were obtained from DRIVE database, which consists of 20 cases each for training and testing vessel detection
algorithms. Starting with the reference standard of vasculature segmentation provided in the database, major arteries and
veins each in the upper and lower temporal regions were manually selected for establishing the gold standard. We
applied the black top-hat transformation and double-ring filter to detect retinal blood vessels. From the extracted vessels,
large vessels extending from the optic disc to temporal regions were selected as target vessels for calculation of A/V
ratio. Image features were extracted from the vessel segments from quarter-disc to one disc diameter from the edge of
optic discs. The target segments in the training cases were classified into arteries and veins by using the linear
discriminant analysis, and the selected parameters were applied to those in the test cases. Out of 40 pairs, 30 pairs (75%)
of arteries and veins in the 20 test cases were correctly classified. The result can be used for the automated calculation of
A/V ratio.
Indocyanine green (ICG) is widely used for its clearance test in the evaluation of liver function. Gadoxetate disodium
(Gd-EOB-DTPA) is a targeted MR contrast agent partially taken up by hepatocytes. The objective of this study was to
evaluate the feasibility of an estimation of the liver function corresponding to plasma disappearance rate of indocyanine
green (ICG-PDR) by use of the signal intensity of the liver alone in Gd-EOB-DTPA enhanced MR imaging (EOB-MRI).
We evaluated fourteen patients who had EOB-MRI and ICG clearance test within 1 month. 2D-GRE T1 weighted
images were obtained at pre contrast, 3 min (equilibrium phase) and 20 min (hepatobiliary phase) after the intravenous
administration of Gd-EOB-DTPA, and the mean signal intensity of the liver was measured. The correlation between
ICG-PDR and many parameters derived from the signal intensity of the liver in EOB-MRI was evaluated. The
correlation coefficient between ICG-PDR and many parameters derived from the signal intensity of the liver in EOBMRI
was low and not significant. The estimation of the liver function corresponding to ICG-PDR by use of the signal
intensity of the liver alone in EOB-MRI would not be reliable.
In aging societies, it is important to analyze age-related hypokinesia. A psoas major muscle has many important
functional capabilities such as capacity of balance and posture control. These functions can be measured by its cross
sectional area (CSA), volume, and thickness. However, these values are calculated manually in the clinical situation. The
purpose of our study is to propose an automated recognition method of psoas major muscles in X-ray torso CT images.
The proposed recognition process involves three steps: 1) determination of anatomical points such as the origin and
insertion of the psoas major muscle, 2) generation of a shape model for the psoas major muscle, and 3) recognition of the
psoas major muscles by use of the shape model. The model was built using quadratic function, and was fit to the
anatomical center line of psoas major muscle. The shape model was generated using 20 CT cases and tested by 20 other
CT cases. The applied database consisted of 12 male and 8 female cases from the ages of 40's to 80's. The average value
of Jaccard similarity coefficient (JSC) values employed in the evaluation was 0.7. Our experimental results indicated that
the proposed method was effective for a volumetric analysis and could be possible to be used for a quantitative
measurement of psoas major muscles in CT images.
Retinal nerve fiber layer defect (NFLD) is a major sign of glaucoma, which is the second leading cause of blindness in the world. Early detection of NFLDs is critical for improved prognosis of this progressive, blinding disease. We have investigated a computerized scheme for detection of NFLDs on retinal fundus images. In this study, 162 images, including 81 images with 99 NFLDs, were used. After major blood vessels were removed, the images were transformed so that the curved paths of retinal nerves become approximately straight on the basis of ellipses, and the Gabor filters were applied for enhancement of NFLDs. Bandlike regions darker than the surrounding pixels were detected as candidates of NFLDs. For each candidate, image features were determined and the likelihood of a true NFLD was determined by using the linear discriminant analysis and an artificial neural network (ANN). The sensitivity for detecting the NFLDs was 91% at 1.0 false positive per image by using the ANN. The proposed computerized system for the detection of NFLDs can be useful to physicians in the diagnosis of glaucoma in a mass screening.
X-ray CT images have been widely used in clinical diagnosis in recent years. A modern CT scanner can generate
about 1000 CT slices to show the details of all the human organs within 30 seconds. However, CT image interpretations
(viewing 500-1000 slices of CT images manually in front of a screen or films for each patient) require a lot of time and
energy. Therefore, computer-aided diagnosis (CAD) systems that can support CT image interpretations are strongly
anticipated. Automated recognition of the anatomical structures in CT images is a basic pre-processing of the CAD
system. The bone structure is a part of anatomical structures and very useful to act as the landmarks for predictions of the
other different organ positions. However, the automated recognition of the bone structure is still a challenging issue. This
research proposes an automated scheme for segmenting the bone regions and recognizing the bone structure in noncontrast
torso CT images. The proposed scheme was applied to 48 torso CT cases and a subjective evaluation for the
experimental results was carried out by an anatomical expert following the anatomical definition. The experimental
results showed that the bone structure in 90% CT cases have been recognized correctly. For quantitative evaluation,
automated recognition results were compared to manual inputs of bones of lower limb created by an anatomical expert
on 10 randomly selected CT cases. The error (maximum distance in 3D) between the recognition results and manual
inputs distributed from 3-8 mm in different parts of the bone regions.
The presence of microaneurysms in the eye is one of the early signs of diabetic retinopathy, which is one of the leading
causes of vision loss. We have been investigating a computerized method for the detection of microaneurysms on retinal
fundus images, which were obtained from the Retinopathy Online Challenge (ROC) database. The ROC provides 50
training cases, in which "gold standard" locations of microaneurysms are provided, and 50 test cases without the gold
standard locations. In this study, the computerized scheme was developed by using the training cases. Although the
results for the test cases are also included, this paper mainly discusses the results for the training cases because the
"gold
standard" for the test cases is not known. After image preprocessing, candidate regions for microaneurysms were
detected using a double-ring filter. Any potential false positives located in the regions corresponding to blood vessels
were removed by automatic extraction of blood vessels from the images. Twelve image features were determined, and
the candidate lesions were classified into microaneurysms or false positives using the rule-based method and an artificial
neural network. The true positive fraction of the proposed method was 0.45 at 27 false positives per image. Forty-two
percent of microaneurysms in the 50 training cases were considered invisible by the consensus of two co-investigators.
When the method was evaluated for visible microaneurysms, the sensitivity for detecting microaneurysms was 65% at
27 false positives per image. Our computerized detection scheme could be improved for helping ophthalmologists in the
early diagnosis of diabetic retinopathy.
The detection of cerebrovascular diseases such as unruptured aneurysm, stenosis, and occlusion is a major application of magnetic resonance angiography (MRA). However, their accurate detection is often difficult for radiologists. Therefore, several computer-aided diagnosis (CAD) schemes have been developed in order to assist radiologists with image interpretation. The purpose of this study was to develop a computerized method for segmenting cerebral arteries, which is an essential component of CAD schemes. For the segmentation of vessel regions, we first used a gray level transformation to calibrate voxel values. To adjust for variations in the positioning of patients, registration was subsequently employed to maximize the overlapping of the vessel regions in the target image and reference image. The vessel regions were then segmented from the background using gray-level thresholding and region growing techniques. Finally, rule-based schemes with features such as size, shape, and anatomical location were employed to distinguish between vessel regions and false positives. Our method was applied to 854 clinical cases obtained from two different hospitals. The segmentation of cerebral arteries in 97.1%(829/854) of the MRA studies was attained as an acceptable result. Therefore, our computerized method would be useful in CAD schemes for the detection of cerebrovascular diseases in MRA images.
A large cup-to-disc (C/D) ratio, which is the ratio of the diameter of the depression (cup) to that of the optical nerve head
(ONH, disc), can be one of the important signs for diagnosis of glaucoma. Eighty eyes, including 25 eyes with the signs
of glaucoma, were imaged by a stereo retinal fundus camera. An ophthalmologist provided the outlines of cup and disc
on a regular monitor and on the stereo display. The depth image of the ONH was created by determining the
corresponding pixels in a pair of images based on the correlation coefficient in localized regions. The areas of the disc
and cup were determined by use of the red component in one of the color images and by use of the depth image,
respectively. The C/D ratio was determined based on the largest vertical lengths in the cup and disc areas, which was
then compared with that by the ophthalmologist. The disc areas determined by the computerized method agreed
relatively well with those determined by the ophthalmologist, whereas the agreement for the cup areas was somewhat
lower. When C/D ratios were employed for distinction between the glaucomatous and non-glaucomatous eyes, the area
under the receiver operating characteristic curve (AUC) was 0.83. The computerized analysis of ONH can be useful for
diagnosis of glaucoma.
Depth analysis of the optic nerve head (ONH) in the retinal fundus is important for the early detection of glaucoma. In this study, we investigate an automatic reconstruction method for the quantitative depth measurement of the ONH from a stereo retinal fundus image pair. We propose a technique to obtain the depth value from the stereo retinal fundus image pair, which mainly consists of five steps: 1. cutout of the ONH region from the stereo retinal fundus image pair, 2. registration of the stereo image pair, 3. disparity measurement, 4. noise reduction, and 5. quantitative depth calculation. Depth measurements of 12 normal eyes are performed using the stereo fundus camera and the Heidelberg Retina Tomograph (HRT), which is a confocal laser-scanning microscope. The depth values of the ONH obtained from the stereo retinal fundus image pair were in good accordance with the value obtained using HRT (r=0.80±0.15). These results indicate that our proposed method could be a useful and easy-to-handle tool for assessing the cup depth of the ONH in routine diagnosis as well as in glaucoma screening.
The purpose of this work was to develop an automated method to calculate the score of SUV for torso region on FDG-PET scans. The three dimensional distributions for the mean and the standard deviation values of SUV were stored in each volume to score the SUV in corresponding pixel position within unknown scans. The modeling methods is based on SPM approach using correction technique of Euler characteristic and Resel (Resolution element). We employed 197 nor-mal cases (male: 143, female: 54) to assemble the normal metabolism distribution of FDG. The physique were registered each other in a rectangular parallelepiped shape using affine transformation and Thin-Plate-Spline technique. The regions of the three organs were determined based on semi-automated procedure. Seventy-three abnormal spots were used to estimate the effectiveness of the scoring methods. As a result, the score images correctly represented that the scores for normal cases were between zeros to plus/minus 2 SD. Most of the scores of abnormal spots associated with cancer were lager than the upper of the SUV interval of normal organs.
Ultrasonography is one of the most important methods for breast cancer screening in Japan. Several mechanical
whole breast ultrasound (US) scanners have been developed for mass screening. We have reported a computer-aided
detection (CAD) scheme for the detection of masses in whole breast US images. In this study, the method
of detecting mass candidates and the method of reducing false positives (FPs) were improved in order to enhance
the performance of this scheme. A 3D difference (3DD) filter was newly developed to extract low-intensity regions.
The 3DD filter is defined as the difference of pixel values between the current pixel value and the mean pixel value
of 17 neighboring pixels. Low-intensity regions were efficiently extracted by use of 3DD filter values, and FPs were
reduced using a FP reduction method employing the rule-based technique and quadratic discriminant analysis
with the filter values. The performance of our previous and improved CAD schemes indicated a sensitivity of
80.0% with 16.8 FPs and 9.5 FPs per breast, respectively. The FPs of the improved scheme were reduced by
44% as compared to the previous scheme. The 3DD filter was useful for the detection of masses in whole breast
US images.
We have been developing several automated methods for detecting abnormalities in fundus images. The purpose of this
study is to improve our automated hemorrhage detection method to help diagnose diabetic retinopathy. We propose a
new method for preprocessing and false positive elimination in the present study. The brightness of the fundus image
was changed by the nonlinear curve with brightness values of the hue saturation value (HSV) space. In order to
emphasize brown regions, gamma correction was performed on each red, green, and blue-bit image. Subsequently, the
histograms of each red, blue, and blue-bit image were extended. After that, the hemorrhage candidates were detected.
The brown regions indicated hemorrhages and blood vessels and their candidates were detected using density analysis.
We removed the large candidates such as blood vessels. Finally, false positives were removed by using a 45-feature
analysis. To evaluate the new method for the detection of hemorrhages, we examined 125 fundus images, including 35
images with hemorrhages and 90 normal images. The sensitivity and specificity for the detection of abnormal cases was
were 80% and 88%, respectively. These results indicate that the new method may effectively improve the performance
of our computer-aided diagnosis system for hemorrhages.
The detection of unruptured aneurysms is a major subject in magnetic resonance angiography (MRA). However, their accurate detection is often difficult because of the overlapping between the aneurysm and the adjacent vessels on maximum intensity projection images. The purpose of this study is to develop a computerized method for the detection of unruptured aneurysms in order to assist radiologists in image interpretation. The vessel regions were first segmented using gray-level thresholding and a region growing technique. The gradient concentration (GC) filter was then employed for the enhancement of the aneurysms. The initial candidates were identified in the GC image using a gray-level threshold. For the elimination of false positives (FPs), we determined shape features and an anatomical location feature. Finally, rule-based schemes and quadratic discriminant analysis were employed along with these features for distinguishing between the aneurysms and the FPs. The sensitivity for the detection of unruptured aneurysms was 90.0% with 1.52 FPs per patient. Our computerized scheme can be useful in assisting the radiologists in the detection of unruptured aneurysms in MRA images.
Cirrhosis of the liver is a chronic disease. It is characterized by the presence of widespread nodules and fibrosis in
the liver which results in characteristic texture patterns. Computerized analysis of hepatic texture patterns is usually
based on regions-of-interest (ROIs). However, not all ROIs are typical representatives of the disease stage of the
liver from which the ROIs originated. This leads to uncertainties in the ROI labels (diseased or non-diseased). On
the other hand, supervised classifiers are commonly used in determining the assignment rule. This presents a
problem as the training of a supervised classifier requires the correct labels of the ROIs. The main purpose of this
paper is to investigate the use of an unsupervised classifier, the k-means clustering, in classifying ROI based data.
In addition, a procedure for generating a receiver operating characteristic (ROC) curve depicting the classification
performance of k-means clustering is also reported. Hepatic MRI images of 44 patients (16 cirrhotic; 28 non-cirrhotic)
are used in this study. The MRI data are derived from gadolinium-enhanced equilibrium phase images.
For each patient, 10 ROIs selected by an experienced radiologist and 7 texture features measured on each ROI are
included in the MRI data. Results of the k-means classifier are depicted using an ROC curve. The area under the
curve (AUC) has a value of 0.704. This is slightly lower than but comparable to that of LDA and ANN classifiers
which have values 0.781 and 0.801, respectively. Methods in constructing ROC curve in relation to k-means
clustering have not been previously reported in the literature.
Cerebrovascular diseases are the third leading cause of death in Japan. Therefore, a screening system for the early detection of asymptomatic brain diseases is widely used. In this screening system, leukoaraiosis is often detected in magnetic resonance (MR) images. The quantitative analysis of leukoaraiosis is important because its presence and extension is associated with an increased risk of severe stroke. However, thus far, the diagnosis of leukoaraiosis has generally been limited to subjective judgments by radiologists. Therefore, the purpose of this study was to develop a computerized method for the segmentation of leukoaraiosis, and provide an objective measurement of the lesion volume. Our database comprised of T1- and T2-weighted images obtained from 73 patients. The locations of leukoaraiosis regions were determined by an experienced neuroradiologist. We first segment cerebral parenchymal regions in T1-weighted images by using a region growing technique. For determining the initial candidate regions for leukoaraiosis, the k-means clustering of pixel values in the T1- and T2-weighted images was applied to the segmented cerebral region. For the elimination of false positives (FPs), we determined features such as the location, size, and circularity from each of the initial candidates. Finally, rule-based schemes and a quadratic discriminant analysis with these features were employed for distinguishing between the leukoaraiosis regions and the FPs. The results indicated that the sensitivity for the detection of leukoaraiosis was 100% with 5.84 FPs per image. Our computerized scheme can be useful in assisting radiologists for the quantitative analysis of leukoaraiosis in T1- and T2-weighted images.
In order to support the diagnosis of hepatic diseases, understanding the anatomical structures of hepatic lobes and
hepatic vessels is necessary. Although viewing and understanding the hepatic vessels in contrast media-enhanced CT
images is easy, the observation of the hepatic vessels in non-contrast X-ray CT images that are widely used for the
screening purpose is difficult. We are developing a computer-aided diagnosis (CAD) system to support the liver
diagnosis based on non-contrast X-ray CT images. This paper proposes a new approach to segment the middle hepatic
vein (MHV), a key structure (landmark) for separating the liver region into left and right lobes. Extraction and
classification of hepatic vessels are difficult in non-contrast X-ray CT images because the contrast between hepatic
vessels and other liver tissues is low. Our approach uses an atlas-driven method by the following three stages. (1)
Construction of liver atlases of left and right hepatic lobes using a learning datasets. (2) Fully-automated enhancement
and extraction of hepatic vessels in liver regions. (3) Extraction of MHV based on the results of (1) and (2). The
proposed approach was applied to 22 normal liver cases of non-contrast X-ray CT images. The preliminary results show
that the proposed approach achieves the success in 14 cases for MHV extraction.
Biometric technique has been implemented instead of conventional identification methods such as password in computer,
automatic teller machine (ATM), and entrance and exit management system. We propose a personal identification (PI)
system using color retinal fundus images which are unique to each individual. The proposed procedure for identification
is based on comparison of an input fundus image with reference fundus images in the database. In the first step,
registration between the input image and the reference image is performed. The step includes translational and rotational
movement. The PI is based on the measure of similarity between blood vessel images generated from the input and
reference images. The similarity measure is defined as the cross-correlation coefficient calculated from the pixel values.
When the similarity is greater than a predetermined threshold, the input image is identified. This means both the input
and the reference images are associated to the same person. Four hundred sixty-two fundus images including forty-one
same-person's image pairs were used for the estimation of the proposed technique. The false rejection rate and the false
acceptance rate were 9.9×10-5% and 4.3×10-5%, respectively. The results indicate that the proposed method has a higher
performance than other biometrics except for DNA. To be used for practical application in the public, the device which
can take retinal fundus images easily is needed. The proposed method is applied to not only the PI but also the system
which warns about misfiling of fundus images in medical facilities.
The comparison of left and right mammograms is a common technique used by radiologists for the detection and
diagnosis of masses. In mammography, computer-aided detection (CAD) schemes using bilateral subtraction
technique have been reported. However, in breast ultrasonography, there are no reports on CAD schemes using
comparison of left and right breasts. In this study, we propose a scheme of false positive reduction based on
bilateral subtraction technique in whole breast ultrasound images. Mass candidate regions are detected by using
the information of edge directions. Bilateral breast images are registered with reference to the nipple positions
and skin lines. A false positive region is detected based on a comparison of the average gray values of a mass
candidate region and a region with the same position and same size as the candidate region in the contralateral
breast. In evaluating the effectiveness of the false positive reduction method, three normal and three abnormal
bilateral pairs of whole breast images were employed. These abnormal breasts included six masses larger than
5 mm in diameter. The sensitivity was 83% (5/6) with 13.8 (165/12) false positives per breast before applying
the proposed reduction method. By applying the method, false positives were reduced to 4.5 (54/12) per breast
without removing a true positive region. This preliminary study indicates that the bilateral subtraction technique
is effective for improving the performance of a CAD scheme in whole breast ultrasound images.
This paper describes a method for detecting hemorrhages and exudates in ocular fundus images. The detection of
hemorrhages and exudates is important in order to diagnose diabetic retinopathy. Diabetic retinopathy is one of the most
significant factors contributing to blindness, and early detection and treatment are important. In this study, hemorrhages
and exudates were automatically detected in fundus images without using fluorescein angiograms. Subsequently, the
blood vessel regions incorrectly detected as hemorrhages were eliminated by first examining the structure of the blood
vessels and then evaluating the length-to-width ratio. Finally, the false positives were eliminated by checking the
following features extracted from candidate images: the number of pixels, contrast, 13 features calculated from the co-occurrence
matrix, two features based on gray-level difference statistics, and two features calculated from the extrema
method. The sensitivity of detecting hemorrhages in the fundus images was 85% and that of detecting exudates was
77%. Our fully automated scheme could accurately detect hemorrhages and exudates.
We have been developing the CAD scheme for head and abdominal injuries for emergency medical care. In this work, we
have developed an automated method to detect typical head injuries, rupture or strokes of brain. Extradural and subdural
hematoma region were detected by comparing technique after the brain areas were registered using warping. We employ
5 normal and 15 stroke cases to estimate the performance after creating the brain model with 50 normal cases. Some of
the hematoma regions were detected correctly in all of the stroke cases with no false positive findings on normal cases.
Cirrhosis of the liver is characterized by the presence of widespread nodules and fibrosis in the liver. The fibrosis
and nodules formation causes distortion of the normal liver architecture, resulting in characteristic texture patterns.
Texture patterns are commonly analyzed with the use of co-occurrence matrix based features measured on regions-of-interest (ROIs). A classifier is subsequently used for the classification of cirrhotic or non-cirrhotic livers.
Problem arises if the classifier employed falls into the category of supervised classifier which is a popular choice.
This is because the 'true disease states' of the ROIs are required for the training of the classifier but is, generally, not
available. A common approach is to adopt the 'true disease state' of the liver as the 'true disease state' of all ROIs in
that liver. This paper investigates the use of a nonsupervised classifier, the k-means clustering method in classifying
livers as cirrhotic or non-cirrhotic using unlabelled ROI data. A preliminary result with a sensitivity and specificity
of 72% and 60%, respectively, demonstrates the feasibility of using the k-means non-supervised clustering method
in generating a characteristic cluster structure that could facilitate the classification of cirrhotic and non-cirrhotic
livers.
Primary malignant liver tumor, including hepatocellular carcinoma (HCC), caused 1.25 million deaths per year
worldwide. Multiphase CT images offer clinicians important information about hepatic cancer. The presence of HCC is
indicated by high-intensity regions in arterial phase images and low-intensity regions in equilibrium phase images
following enhancement with contrast material. We propose an automatic method for detecting HCC based on edge
detection and subtraction processing. Within a liver area segmented according to our scheme, black regions are selected
by subtracting the equilibrium phase images to the corresponding registrated arterial phase images. From these black
regions, the HCC candidates are extracted as the areas without edges by using Sobel and LoG edge detection filters. The
false-positive (FP) candidates are eliminated by using six features extracted from the cancer and liver regions. Other FPs
are further eliminated by opening processing. Finally, an expansion process is applied to acquire the 3D shape of the
HCC. The cases used in this experiment were from the CT images of 44 patients, which included 44 HCCs. We extracted
97.7% (43/44) HCCs successfully by our proposed method, with an average number of 2.1 FPs per case. The result
demonstrates that our edge-detection-based method is effective in locating the cancer region by using the information
obtained from different phase images.
Magnetic resonance angiography (MRA) is routinely employed in the diagnosis of cerebrovascular disease. Unruptured
aneurysms and arterial occlusions can be detected in examinations using MRA. This paper describes a computerized
detection method of arterial occlusion in MRA studies. Our database consists of 100 MRA studies, including 85 normal
cases and 15 abnormal cases with arterial occlusion. Detection of abnormality is based on comparison with a reference
(normal) MRA study with all the vessel known. Vessel regions in a 3D target MRA study is first segmented by using
thresholding and region growing techniques. Image registration is then performed so as to maximize the overlapping of
the vessel regions in the target image and the reference image. The segmented vessel regions are then classified into
eight arteries based on comparison of the target image and the reference image. Relative lengths of the eight arteries are
used as eight features in classifying the normal and arterial occlusion cases. Classifier based on the distance of a case
from the center of distribution of normal cases is employed for distinguishing between normal cases and abnormal cases.
The sensitivity and specificity for the detection of abnormal cases with arterial occlusion is 80.0% (12/15) and 95.3%
(81/85), respectively. The potential of our proposed method in detecting arterial occlusion is demonstrated.
Retinal nerve fiber layer defect (NFLD) is one of the most important findings for the diagnosis of glaucoma reported by
ophthalmologists. However, such changes could be overlooked, especially in mass screenings, because ophthalmologists
have limited time to search for a number of different changes for the diagnosis of various diseases such as diabetes,
hypertension and glaucoma. Therefore, the use of a computer-aided detection (CAD) system can improve the results of
diagnosis. In this work, a technique for the detection of NFLDs in retinal fundus images is proposed. In the
preprocessing step, blood vessels are "erased" from the original retinal fundus image by using morphological filtering.
The preprocessed image is then transformed into a rectangular array. NFLD regions are observed as vertical dark bands
in the transformed image. Gabor filtering is then applied to enhance the vertical dark bands. False positives (FPs) are
reduced by a rule-based method which uses the information of the location and the width of each candidate region. The
detected regions are back-transformed into the original configuration. In this preliminary study, 71% of NFLD regions
are detected with average number of FPs of 3.2 per image. In conclusion, we have developed a technique for the
detection of NFLDs in retinal fundus images. Promising results have been obtained in this initial study.
The analysis of the optic nerve head (ONH) in the retinal fundus is important for the early detection of glaucoma. In this
study, we investigate an automatic reconstruction method for producing the 3-D structure of the ONH from a stereo
retinal image pair; the depth value of the ONH measured by using this method was compared with the measurement
results determined from the Heidelberg Retina Tomograph (HRT). We propose a technique to obtain the depth value
from the stereo image pair, which mainly consists of four steps: (1) cutout of the ONH region from the retinal images,
(2) registration of the stereo pair, (3) disparity detection, and (4) depth calculation. In order to evaluate the accuracy of
this technique, the shape of the depression of an eyeball phantom that had a circular dent as generated from the stereo
image pair and used to model the ONH was compared with a physically measured quantity. The measurement results
obtained when the eyeball phantom was used were approximately consistent. The depth of the ONH obtained using the
stereo retinal images was in accordance with the results obtained using the HRT. These results indicate that the stereo
retinal images could be useful for assessing the depth of the ONH for the diagnosis of glaucoma.
The identification of mammary gland regions is a necessary processing step during the anatomical structure
recognition of human body and can be expected to provide the useful information for breast tumor diagnosis. This paper
proposes a fully-automated scheme for segmenting the mammary gland regions in non-contrast torso CT images. This
scheme calculates the probability for each voxel belonging to the mammary gland or other regions (for example
pectoralis major muscles) in CT images and decides the mammary gland regions automatically. The probability is
estimated from the location of the mammary gland and pectoralis major muscles in CT images. The location (named as a
probabilistic atlas) is investigated from the pre-segmentation results in a number of different CT scans and the CT
number distribution is approximated using a Gaussian function. We applied this scheme to 66 patient cases (female, age:
40-80) and evaluated the accuracy by using the coincidence rate between the segmented result and gold standard that is
generated manually by a radiologist for each CT case. The mean value of the coincidence rate was 0.82 with the standard
deviation of 0.09 for 66 CT cases.
Breast cancer mass screening is widely performed by mammography but in some population with dense
breast, ultrasonography is much effective for cancer detection. For this purpose it is necessary to
develop special ultrasonic equipment and the system for breast mass screening. It is important to
design scanner, image recorder, viewer with CAD (Computer-assisted detection) as a system. Authors
developed automatic scanner which scans unilateral breast within 30 seconds. An electric linear probe
visualizes width of 6cm, the probe moves 3 paths for unilateral breast. Ultrasonic images are recorded
as movie files. These files are treated by microcomputer as volume data. Doctors can diagnose by
digital rapid viewing with 3D function. It is possible to show unilateral or bilateral images on a screen.
The viewer contains reporting function as well. This system is considered enough capability to
perform ultrasonic breast cancer mass screening.
Hepatic vessel trees are the key structures in the liver. Knowledge of the hepatic vessel trees is important for liver surgery
planning and hepatic disease diagnosis such as portal hypertension. However, hepatic vessels cannot be easily distinguished
from other liver tissues in non-contrast CT images. Automated segmentation of hepatic vessels in non-contrast CT images
is a challenging issue. In this paper, an approach for automated segmentation of hepatic vessels trees in non-contrast X-ray
CT images is proposed. Enhancement of hepatic vessels is performed using two techniques: (1) histogram transformation
based on a Gaussian window function; (2) multi-scale line filtering based on eigenvalues of Hessian matrix. After the
enhancement of hepatic vessels, candidate of hepatic vessels are extracted by thresholding. Small connected regions of
size less than 100 voxels are considered as false-positives and are removed from the process. This approach is applied to
20 cases of non-contrast CT images. Hepatic vessel trees segmented from the contrast-enhanced CT images of the same
patient are used as the ground truth in evaluating the performance of the proposed segmentation method. Results show that
the proposed method can enhance and segment the hepatic vessel regions in non-contrast CT images correctly.
Segmentation of an abnormal liver region based on CT or MR images is a crucial step in surgical planning. However,
precisely carrying out this step remains a challenge due to either connectivities of the liver to other organs or the shape,
internal texture, and homogeneity of liver that maybe extensively affected in case of liver diseases. Here, we propose a
non-density based method for extracting the liver region containing tumor tissues by edge detection processing. False
extracted regions are eliminated by a shape analysis method and thresholding processing. If the multi-phased images are
available then the overall outcome of segmentation can be improved by subtracting two phase images, and the
connectivities can be further eliminated by referring to the intensity on another phase image. Within an edge liver map,
tumor candidates are identified by their different gray values relative to the liver. After elimination of the small and nonspherical
over-extracted regions, the final liver region integrates the tumor region with the liver tissue. In our experiment,
40 cases of MDCT images were used and the result showed that our fully automatic method for the segmentation of liver
region is effective and robust despite the presence of hepatic tumors within the liver.
We have investigated Computer-aided detection (CAD) system for breast masses on screening ultrasound (US) images. A lot of methods of Computer-aided detection and diagnosis system on US images have been developed by many researchers in the world. However, some methods require substantial computation time in analysing a US image, and some systems also need a radiologist to indicate the masses in advance. In this paper, we proposed fast automatic detection system which utilizes edge information in detecting masses. Our method consists of the following steps: (1) noise reduction and image normalization, (2) decision of the region of interest (ROI) using vertical edges detected by the canny edge detector, (3) segmentation of ROI using watershed algorithm, and (4) reduction of false positives. This study employs 11 whole breast cases with a total of 924 images. All the cases have been diagnosed by a radiologist prior to the study. This database have 11 malignant masses. These malignant masses have heterogeneous internal echo, a low or equal echo-level, and a deficient or disappearance posterior echo. Using the proposed method, the sensitivity in detecting malignant masses is 90.9% (10/11) and the number of false positives per image is 0.69 (633/924). It is concluded that our method is effective for detecting breast masses on US images.
A co-occurrence matrix is a joint probability distribution of the pixel values of two pixels in an image separated by a distance d in the direction θ. It is one of the texture analysis tools favored by the medical image processing community. The size of a co-occurrence matrix depends on gray levels re-quantization Q. Hence, when dealing with high depth
resolution images, gray levels re-quantization is routinely performed to reduce the size of the co-occurrence matrix. The gray levels re-quantization may play a role in the display of spatial relationships in co-occurrence matrix but is usually dealt with lightly. In this paper, we use an example to study the effect of gray-level re-quantization in high depth resolution medical images. Digitized film-screen mammograms have a typical depth resolution of 4096 gray levels. In a study classifying masses on mammograms as benign or malignant, 260 texture features are measured on 43 regions-of-interest (ROIs) containing malignant masses and 28 ROIs containing benign masses. Of the 260 texture features,
240 are texture features measured on co-occurrence matrices with parameters θ = 0, π/2; d = 11, 15, 21, 25, 31; and Q = 50, 100, 400. A genetic algorithm is used to select a subset of features (out of 260) that has discriminative power. Results show that top performing feature combinations selected by the genetic algorithm are not restricted to a single value of Q. This indicates that instead of searching for a correct Q, it may be more appropriate to explore a range of
Q values.
The purpose of this work is to develop a new pattern recognition method using the higher-order autocorrelation features (HOAFs), and to apply this to our microcalcification detection system on mammographic images. Microcalcification is a typical sign of breast cancer and tends to show up as very subtle shadows. We developed a triple-ring filter for detecting microcalcifications, and the prototype detection system is nearly complete. However, our prototype system does not allow for the detection of three types of microcalcifications, two of which are amorphous and linear microcalcifications and the third is obscured microcalcifications which is often confused with the background or circumference that have almost the same density. We targeted the amorphous type of microcalcification, which has a low contrast and easily goes undetected. The various features of microcalcifications and false-positive (FP) shadows were extracted and trained using the multi-regression analysis, and unknown images were recognized as a result of this training. As a result, amorphous microcalcifications were successfully detected with no increase in the number of FPs compared with our existing detection method.
We have been developing a computer-aided diagnosis (CAD) scheme for automatically recognizing human tissue and organ regions from high-resolution torso CT images. We show some initial results for extracting skin, soft-tissue and skeleton regions. 139 patient cases of torso CT images (male 92, female 47; age: 12-88) were used in this study. Each case was imaged with a common protocol (120kV/320mA) and covered the whole torso with isotopic spatial resolution of about 0.63 mm and density resolution of 12 bits. A gray-level thresholding based procedure was applied to separate the human body from background. The density and distance features to body surface were used to determine the skin, and separate soft-tissue from the others. A 3-D region growing based method was used to extract the skeleton. We applied this system to the 139 cases and found that the skin, soft-tissue and skeleton regions were recognized correctly for 93% of the patient cases. The accuracy of segmentation results was acceptable by evaluating the results slice by slice. This scheme will be included in CAD systems for detecting and diagnosing the abnormal lesions in multi-slice torso CT images.
An automatic extraction of pulmonary emphysema area on 3-D chest CT images was performed using an adaptive thresholding technique. We proposed a method to estimate the ratio of the emphysema area to the whole lung volume. We employed 32 cases (15 normal and 17 abnormal) which had been already diagnosed by radiologists prior to the study. The ratio in all the normal cases was less than 0.02, and in abnormal cases, it ranged from 0.01 to 0.26. The effectiveness of our approach was confirmed through the results of the present study.
We have developed an algorithm that can be used to distinguish the central part of the vertebral body from an
abdominal X-ray CT image and to automatically calculate three measures to diagnose the degree of osteoporosis in a
patient. In addition, we examined whether it is possible to use these CT images as an aid in diagnosing osteoporosis.
Three measures that were automatically extracted from the central part of a vertebral body in the CT images were
compared with the bone mineral density (BMD) values that were obtained from the same vertebral body. We calculated
the mean CT number, coefficient of variation, and the first moment of power spectrum in the recognized vertebral body.
We judged whether a patient had osteoporosis using the diagnostic criteria for primary osteoporosis (Year 2000
revision, published by the Japanese Society for Bone and Mineral Research). We classified three measures for normal
and abnormal groups using the principal component analysis, and the two groups were compared with the results
obtained from the diagnostic criteria. As a result, it was found that the algorithm could be used to distinguish the central
part of the vertebral body in the CT images and to calculate these measures automatically. When distinguishing whether
a patient was osteoporotic or not with the three measures obtained from the CT images, the ratio (sensitivity) usable for
diagnosing a patient as osteoporotic was 0.93 (14/15), and the ratio (specificity) usable for diagnosing a patient as
normal was 0.64 (7/11). Based on these results, we believe that it is possible to utilize the measures obtained from these
CT images to aid in diagnosing osteoporosis.
As well as mass and microcalcification, architectural distortion is a very important finding for the early detection of breast cancer via mammograms, and such distortions can be classified into three typical types: spiculation, retraction, and distortion. The purpose of this work is to develop an automatic method for detecting areas of architectural distortion with spiculation. The suspect areas are detected by concentration indexes of line-structures extracted by using mean curvature. After that, discrimination analysis of nine features is employed for the classifications of true and false positives. The employed features are the size, the mean pixel value, the mean concentration index, the mean isotropic index, the contrast, and four other features based on the power spectrum. As a result of this work, the accuracy of the classification was 76% and the sensitivity was 80% with 0.9 false positives per image in our database in regard to spiculation. It was concluded that our method was effective in detectiong the area of architectural distortion; however, some architectural distortions were not detected accurately because of the size, the density, or the different appearance of the distorted areas.
We have developed a computer-aided diagnosis system to detect the abnormalities on retinal fundus images. In Japan, ophthalmologists usually detect hypertensive changes by identifying narrowing arteriolae with a focus on an irregularity. The purpose of this study is to develop an automated method for detecting narrowing arteriolae with a focus on an irregularity on retinal images. The blood vessel candidates were detected by the density analysis method. In blood vessel tracking, a local detection function was used to go along the centerline of the blood vessel. A direction comparison function using three vectors was designed to provide an optimal estimation of the next possible location of a blood vessel. After the connectivity of vessel segments was adjusted based on the recognized intersections, the true tree-like structure of the retinal blood vessels was established. The abnormal blood vessels were finally detected by measuring their diameters. The comparison between the results obtained using our system and the diagnostic results of physicians showed that our proposed method automatically detected an irregularity in diameter in 75% of all 24 narrowing arteries with a focus on an irregularity on 70 retinal fundus images. Approximately 2.88 normal vessel segments per image were determined to be abnormal, a number which must be reduced at the next stage. The automated detection of narrowing arteriolae with a focus on an irregularity could help ophthalmologists in diagnosing ocular diseases.
We previously developed a scheme to automatically detect pulmonary nodules on CT images, as a part of computer-aided diagnosis (CAD) system. The proposed method consisted of two template-matching approaches based on simple models that simulate real nodules. One was a new template-matching technique based on a genetic algorithm (GA) template matching (GATM) for detecting nodules within the lung area. The other one was a conventional template matching along the lung wall [lung wall template matching (LWTM)] for detecting nodules on the lung wall. After the two template matchings, thirteen feature values were calculated and used for eliminating false positives. Twenty clinical cases involving a total of 557 sectional images were applied; 71 nodules out of 98 were correctly detected with the number of false positives at approximately 30.8/case by applying two template matchings (GATM and LWTM) and elimination process of false positives. In this study, five features were newly added, and threshold-values of our previous features were reconsidered for further eliminating false positives. As the result, the number of false positives was decreased to 5.5/case without elimination of true positives.
Computer-aided diagnosis (CAD) has been expected to help radiologists to improve the accuracy of abnormality detection and reduce the burden during CT image interpretations. In order to realize such functions, automated segmentations of the target organ regions are always required by CAD systems. This paper describes a fully automatic processing procedure, which is designed to identify inter-lobe fissures and divide lung into five lobe regions. The lung fissures are disappeared very fuzzy and indefinite in CT images, so that it is very difficult to extract fissures directly based on its CT values. We propose a method to solve this problem using the anatomy knowledge of human lung. We extract lung region firstly and then recognize the structures of lung vessels and bronchus. Based on anatomy knowledge, we classify the vessels and bronchus on a lobe-by-lobe basis and estimate the boundary of each lobe region as the initial fissure locations. Within those locations, we extract lung fissures precisely based on an edge detection method and divide lung regions into five lung lobes lastly. The performance of the proposed method was evaluated using 9 patient cases of high-resolution multi-slice chest CT images; the improvement has been confirmed with the reliable recognition results.
A method for measuring the characteristic curves generated by the mammography imaging systems has not yet
been well established due to poor quality control over X-ray exposure in the range of kV values, which is lower than the
conventional quality. In this paper, we proposed a bootstrap method using a “stepwedge” designed for characteristic
curve measurement in mammography. A ten-step stepwedge containing calcium phosphate, with each step having a
different density of material, was employed. In our experiment, the tube voltage and mA values were changed in the
range of 25 to 32 kV at increments of 1 kV and in the range of 20 to 100 mAs at increments of 20 mAs, respectively.
The results of the curve measurements indicated that our method might be useful to both screen-film mammography and
computed radiography (CR), although additional experiments to evaluate the accuracy and precision of the acquired
data are required.
We have been developing an automated detection scheme for mammographic microcalcifications as a part of computer-assisted diagnosis (CAD) system. The purpose of this study is to develop an automated classification technique for the detected microcalcifications. Types of distributions of calcifications are known to be significantly relevant to their probability of malignancy, and are described on ACR BI-RADS (Breast Imaging Reporting and Data System) , in which five typical types are illustrated as diffuse/scattered, regional, segmental, linear and clustered. Detected microcalcifications by our CAD system are classified automatically into one of their five types based on shape of grouped microcalcifications and the number of microcalcifications within the grouped area. The type of distribution and other general image feature values are analyzed by artificial neural networks (ANNs) and the probability of malignancy is indicated. Eighty mammograms with biopsy-proven microcalcifications were employed and digitized with a laser scanner at a pixel size of 0.1mm and 12-bit density depth. The sensitivity and specificity were 93% and 93%, respectively. The performance was significantly improved in comparison with the case that the five criteria in BI-RADS were not employed.
The existence of a cluster of microcalcifications in mass area on mammogram is one of important features for distinguishing the breast cancer between benign and malignant. However, missed detections often occur because of its low subject contrast in denser background and small quantity of microcalcifications. To get a higher performance of detecting the cluster in mass area, we combined the shift-invariant artificial neural network (SIANN) with triple-ring filter (TRF) method in our computer-aided diagnosis (CAD) system. 150 region-of- interests around mass containing both of positive and negative microcalcifications were selected for training the network by a modified error-back-propagation algorithm. A variable-ring filter was used for eliminating the false- positive (FP) detections after the outputs of SIANN and TRF. The remained Fps were then reduced by a conventional three layer artificial neural network. Finally, the program identified clustered microcalcifications form individual microcalcifications. In a practical detection of 30 cases with 40 clusters in masses, the sensitivity of detecting clusters was improved form 90% by our previous method to 95% by using both SIANN and TRF, while the number of FP clusters was decreased from 0.85 to 0.40 cluster per image.
We developed a software named LiverANN based on artificial neural network (ANN) technique for distinguishing the pathologies of focal liver lesions in magnetic resonance (MR) imaging, which helps radiologists integrate the imaging findings with different pulse sequences and raise the diagnostic accuracy even with radiologists inexperienced in liver MR imaging. In each patient, regions of focal liver lesion on T1-weighted, T2-weighted, and gadolinium-enhanced dynamic MR images obtained in the hepatic arterial and equilibrium phases were placed by a radiologist (M.K.), then the program automatically calculated the brightness and homogeneity into numerical data within the selected areas as the input signals to the ANN. The outputs from the ANN were the 5 categories of focal hepatic diseases: liver cyst, cavernous hemangioma, dysplasia, hepatocellular carcinoma, and metastasis. Fifty cases were used for training the ANN, while 30 cases for testing the performance. The result showed that the LiverANN classified 5 types of focal liver lesions with sensitivity of 93%, which demonstrated the ability of ANN to fuse the complex relationships among the image findings with different sequences, and the ANN-based software may provide radiologists with referential opinion during the radiologic diagnostic procedure.
We are developing automated-detection schemes for the masses and clustered microcalcifications on laser-digitized mammograms (0.1 mm, 10-bit resolution, 2000 X 2510) by using a conventional workstation. The purpose of this paper is to provide an overview of our recent schemes and to evaluate the current performance of the schemes. The fully automated computer system consists of several parts such as the extraction of breast region, detection of masses, detection of clustered microcalcifications, classification of the candidates, and the display of the detected results. Our schemes tested with more than 200 cases of Japanese women achieved an about 95% (86%) true-positive rate with 0.61 (0.55) false-positive masses (clusters) per image. It was found that the automated method has the potential to aid physicians in screening mammograms for breast tumors. Initial results for the mammograms digitized with the pixel sizes of 25, 50, and 100 micrometers are also discussed, in which a genetic algorithm (GA) technique was applied to the detection filter for the microcalcifications. It was indicated from the experiment with a breast phantom that 100- micrometers pixel size is not enough for the computer detection of microcalcifications, and it seems that at least 50-micrometers pixel size is required.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.