The Journal of Medical Imaging thanks the individuals who served as reviewers in 2018.

This editorial provides an overview of the articles in the special section.

We present a breast lesion classification methodology, based on four-dimensional (4-D) dynamic contrast-enhanced magnetic resonance images (DCE-MRI), using recurrent neural networks in combination with a pretrained convolutional neural network (CNN). The method enables to capture not only the two-dimensional image features but also the temporal enhancement patterns presented in DCE-MRI. We train a long short-term memory (LSTM) network on temporal sequences of feature vectors extracted from the dynamic MRI sequences. To capture the local changes in lesion enhancement, the feature vectors are obtained from various levels of a pretrained CNN. We compare the LSTM method’s performance to that of a CNN fine-tuned on “RGB” MRIs, formed by precontrast, first, and second postcontrast MRIs. LSTM significantly outperformed the fine-tuned CNN, resulting in AUC_LSTM  =  0.88 and AUC_fine-tuned  =  0.84, p  =  0.00085, in the task of distinguishing benign and malignant lesions. Our method captures clinically useful information carried by the full 4-D dynamic MRI sequence and outperforms the standard fine-tuning method.

Image guidance systems that register scans of the prostate obtained using transrectal ultrasound (TRUS) and magnetic resonance imaging are becoming increasingly popular as a means of enabling tumor-targeted prostate cancer biopsy and treatment. However, intraoperative segmentation of TRUS images to define the three-dimensional (3-D) geometry of the prostate remains a necessary task in existing guidance systems, which often require significant manual interaction and are subject to interoperator variability. Therefore, automating this step would lead to more acceptable clinical workflows and greater standardization between different operators and hospitals. In this work, a convolutional neural network (CNN) for automatically segmenting the prostate in two-dimensional (2-D) TRUS slices of a 3-D TRUS volume was developed and tested. The network was designed to be able to incorporate 3-D spatial information by taking one or more TRUS slices neighboring each slice to be segmented as input, in addition to these slices. The accuracy of the CNN was evaluated on data from a cohort of 109 patients who had undergone TRUS-guided targeted biopsy, (a total of 4034 2-D slices). The segmentation accuracy was measured by calculating 2-D and 3-D Dice similarity coefficients, on the 2-D images and corresponding 3-D volumes, respectively, as well as the 2-D boundary distances, using a 10-fold patient-level cross-validation experiment. However, incorporating neighboring slices did not improve the segmentation performance in five out of six experiment results, which include varying the number of neighboring slices from 1 to 3 at either side. The up-sampling shortcuts reduced the overall training time of the network, 161 min compared with 253 min without the architectural addition.

Spectral computed tomography (CT) using photon counting detectors (PCDs) can provide accurate tissue composition measurements by utilizing the energy dependence of x-ray attenuation in different materials. PCDs are especially suited for K-edge imaging, revealing the spatial distribution of select imaging probes through quantitative material decomposition. We report on a prototype spectral micro-CT system with a CZT-based PCD (DxRay, Inc.) that has 16  ×  16  pixels of 0.5  ×  0.5  mm², a thickness of 3 mm, and four energy thresholds. Due to the PCD’s limited size (8  ×  8  mm²), our system uses a translate-rotate projection acquisition strategy to cover a field of view relevant for preclinical imaging (∼4.5  cm). Projection corrections were implemented to minimize artifacts associated with dead pixels and projection stitching. A sophisticated iterative algorithm was used to reconstruct both phantom and ex vivo mouse data. To achieve preclinically relevant spatial resolution, we trained a convolutional neural network to perform pan-sharpening between low-resolution PCD data (247-μm voxels) and high-resolution energy-integrating detector data (82-μm voxels), recovering a high-resolution estimate of the spectral contrast suitable for material decomposition. Long-term, preclinical spectral CT systems such as ours could serve in the developing field of theranostics (therapy and diagnostics) for cancer research.

The segmentation of organs at risk is a crucial and time-consuming step in radiotherapy planning. Good automatic methods can significantly reduce the time clinicians have to spend on this task. Due to its variability in shape and low contrast to surrounding structures, segmenting the parotid gland is challenging. Motivated by the recent success of deep learning, we study the use of two-dimensional (2-D), 2-D ensemble, and three-dimensional (3-D) U-Nets for segmentation. The mean Dice similarity to ground truth is ∼0.83 for all three models. A patch-based approach for class balancing seems promising for false-positive reduction. The 2-D ensemble and 3-D U-Net are applied to the test data of the 2015 MICCAI challenge on head and neck autosegmentation. Both deep learning methods generalize well onto independent data (Dice 0.865 and 0.88) and are superior to a selection of model- and atlas-based methods with respect to the Dice coefficient. Since appropriate reference annotations are essential for training but often difficult and expensive to obtain, it is important to know how many samples are needed for training. We evaluate the performance after training with different-sized training sets and observe no significant increase in the Dice coefficient for more than 250 training cases.

Spectral computed tomography (SCT) has advantages in multienergy material decomposition for material discrimination and quantitative image reconstruction. However, due to the nonideal physical effects of photon counting detectors, including charge sharing, pulse pileup and K-escape, it is difficult to obtain precise system models in practical SCT systems. Serious spectral distortion is unavoidable, which introduces error into the decomposition model and affects material decomposition accuracy. Recently, neural networks demonstrated great potential in image segmentation, object detection, natural language processing, etc. By adjusting the interconnection relationship among internal nodes, it provides a way to mine information from data. Considering the difficulty in modeling SCT system spectra and the superiority of data-driven characteristics of neural networks, we proposed a spectral information extraction method for virtual monochromatic attenuation maps using a simple fully connected neural network without knowing spectral information. In our method, virtual monochromatic linear attenuation coefficients can be obtained directly through our neural network, which could contribute to further material recognition. Our method also provides outstanding performance on denoising and artifacts suppression. It can be furnished for SCT systems with different settings of energy bins or thresholds. Various substances available can be used for training. The trained neural network has a good generalization ability according to our results. The testing mean square errors are about 1  ×  ^{10  −  05}  cm^−  2.

Multistage processing of automated breast ultrasound lesions recognition is dependent on the performance of prior stages. To improve the current state of the art, we propose the use of end-to-end deep learning approaches using fully convolutional networks (FCNs), namely FCN-AlexNet, FCN-32s, FCN-16s, and FCN-8s for semantic segmentation of breast lesions. We use pretrained models based on ImageNet and transfer learning to overcome the issue of data deficiency. We evaluate our results on two datasets, which consist of a total of 113 malignant and 356 benign lesions. To assess the performance, we conduct fivefold cross validation using the following split: 70% for training data, 10% for validation data, and 20% testing data. The results showed that our proposed method performed better on benign lesions, with a top “mean Dice” score of 0.7626 with FCN-16s, when compared with the malignant lesions with a top mean Dice score of 0.5484 with FCN-8s. When considering the number of images with Dice score >0.5, 89.6% of the benign lesions were successfully segmented and correctly recognised, whereas 60.6% of the malignant lesions were successfully segmented and correctly recognized. We conclude the paper by addressing the future challenges of the work.

Quantitative material decomposition of multiple mixed, or spatially coincident, contrast agent (gadolinium and iodine) and tissue (calcium and water) compositions is demonstrated using photon-counting spectral computed tomography (CT). Material decomposition is performed using constrained maximum likelihood estimation (MLE) in the image domain. MLE is calibrated by multiple linear regression of all pure material compositions, which exhibits a strong correlation (R²  >  0.91) between the measured x-ray attenuation in each photon energy bin and known concentrations in the calibration phantom. Material decomposition of mixed compositions in the sample phantom provides color material concentration maps that clearly identify and differentiate each material. The measured area under the receiver operating characteristic curve is >0.95, indicating highly accurate material identification. Material decomposition also provides accurate quantitative estimates of material concentrations in mixed compositions with a root-mean-squared error <12  %   of the maximum concentration for each material. Thus, photon-counting spectral CT enables quantitative molecular imaging of multiple spatially coincident contrast agent (gadolinium and iodine) and tissue (calcium and water) compositions, which is not possible with current clinical molecular imaging modalities, such as nuclear imaging and magnetic resonance imaging.

The potential of dual-energy mammography for microcalcification classification was investigated with simulation and phantom studies. Classification of type I/II calcifications was performed using the tissue attenuation ratio as a performance metric. The simulation and phantom studies were carried out using breast phantoms of 50% fibroglandular and 50% adipose tissue composition and thicknessess ranging from 3 to 6 cm. The phantoms included models of microcalcifications ranging in size between 200 and 900  μm. The simulation study was carried out with fixed MGD of 1.5 mGy using various low- and high-kVp spectra, aluminum filtration thicknesses, and exposure distribution ratios to predict an optimized imaging protocol for the phantom study. Attenuation ratio values were calculated for microcalcification signals of different types at two different voltage settings. ROC analysis showed that classification performance as indicated by the area under the ROC curve was always greater than 0.95 for 1.5 mGy deposited mean glandular dose. This study provides encouraging first results in classifying malignant and benign microcalcifications based solely on dual-energy mammography images.

Prior information is often included in the basis material decomposition to solve the quantification problem of three-material mixtures in dual-energy computed tomography (DECT). Multienergy computed tomography (MECT) with more than two energy bins can provide a sufficient solution to this problem without invoking additional prior information. However, a question remains as to whether the prior information should still be included in the material decomposition process using MECT to improve the quantification accuracy and control noise amplification. This study aims to evaluate the impact of the prior information on noise and quantification bias in both DECT and MECT. The material decomposition tasks we used in this study are to quantify water/iodine, water/iodine/gadolinium, and water/ iodine/calcium in two- and three-material decompositions, under the assumption that the object to be decomposed consists of the basis materials and their mixtures. We performed phantom simulation and experimental studies using a clinical DECT system and a research photon-counting-detector-based MECT system. Results in the current phantom studies show that the prior information can still improve the noise performance without substantially affecting the basis material quantitative accuracy during the material decomposition process, even when the number of x-ray energy beams/bins is equal or greater than the number of basis materials.

We propose to characterize the bias and variability of quantitative morphology features of lung lesions across a range of computed tomography (CT) imaging conditions. A total of 15 lung lesions were simulated (five in each of three spiculation classes: low, medium, and high). For each lesion, a series of simulated CT images representing different imaging conditions were synthesized by applying three-dimensional blur and adding correlated noise based on the measured noise and resolution properties of five commercial multislice CT systems, representing three dose levels (CTDI_vol of 1.90, 3.75, 7.50 mGy), three slice thicknesses (0.625, 1.25, 2.5 mm), and 33 clinical reconstruction kernels from five clinical scanners. The images were segmented using three segmentation algorithms and each algorithm was evaluated by computing a Sørensen–Dice coefficient between the ground truth and the segmentation. A series of 21 shape-based morphology features were extracted from both “ground truth” (i.e., preblur without noise) and “image rendered” lesions (i.e., postblur and with noise). For each morphology feature, the bias was quantified by comparing the percentage relative error in the morphology metric between the imaged lesions and the ground-truth lesions. The variability was characterized by calculating the average coefficient of variation averaged across repeats and imaging conditions. The active contour segmentation had the highest average Dice coefficient of 0.80 followed by 0.63 for threshold, and 0.39 for fuzzy c-means. The bias of the features was segmentation algorithm and feature-dependent, with sharper kernels being less biased and smoother kernels being more biased in general. The feature variability from simulated images ranged from 0.30% to 10% for repeats of the same condition and from 0.74% to 25.3% for different lesions in the same spiculation class. In conclusion, the bias of morphology features is dependent on the acquisition protocol in combination with the segmentation algorithm used and the variability is primarily dependent on the segmentation algorithm.

Segmentation of organs at risk (OAR) in computed tomography (CT) is of vital importance in radiotherapy treatment. This task is time consuming and for some organs, it is very challenging due to low-intensity contrast in CT. We propose a framework to perform the automatic segmentation of multiple OAR: esophagus, heart, trachea, and aorta. Different from previous works using deep learning techniques, we make use of global localization information, based on an original distance map that yields not only the localization of each organ, but also the spatial relationship between them. Instead of segmenting directly the organs, we first generate the localization map by minimizing a reconstruction error within an adversarial framework. This map that includes localization information of all organs is then used to guide the segmentation task in a fully convolutional setting. Experimental results show encouraging performance on CT scans of 60 patients totaling 11,084 slices in comparison with other state-of-the-art methods.

Ovarian cancer has the lowest survival rate among all gynecologic cancers predominantly due to late diagnosis. Early detection of ovarian cancer can increase 5-year survival rates from 40% up to 92%, yet no reliable early detection techniques exist. Optical coherence tomography (OCT) is an emerging technique that provides depth-resolved, high-resolution images of biological tissue in real-time and demonstrates great potential for imaging of ovarian tissue. Mouse models are crucial to quantitatively assess the diagnostic potential of OCT for ovarian cancer imaging; however, due to small organ size, the ovaries must first be separated from the image background using the process of segmentation. Manual segmentation is time-intensive, as OCT yields three-dimensional data. Furthermore, speckle noise complicates OCT images, frustrating many processing techniques. While much work has investigated noise-reduction and automated segmentation for retinal OCT imaging, little has considered the application to the ovaries, which exhibit higher variance and inhomogeneity than the retina. To address these challenges, we evaluate a set of algorithms to segment OCT images of mouse ovaries. We examine five preprocessing techniques and seven segmentation algorithms. While all preprocessing methods improve segmentation, Gaussian filtering is most effective, showing an improvement of 32  %    ±  1.2  %  . Of the segmentation algorithms, active contours performs best, segmenting with an accuracy of 94.8  %    ±  1.2  %   compared with manual segmentation. Even so, further optimization could lead to maximizing the performance for segmenting OCT images of the ovaries.

The effectiveness of brain magnetic resonance imaging (MRI) as a useful evaluation tool strongly depends on the performed segmentation of associated tissues or anatomical structures. We introduce an enhanced brain segmentation approach of Bayesian label fusion that includes the construction of adaptive target-specific probabilistic priors using atlases ranked by kernel-based similarity metrics to deal with the anatomical variability of collected MRI data. In particular, the developed segmentation approach appraises patch-based voxel representation to enhance the voxel embedding in spaces with increased tissue discrimination, as well as the construction of a neighborhood-dependent model that addresses the label assignment of each region with a different patch complexity. To measure the similarity between the target and training atlases, we propose a tensor-based kernel metric that also includes the training labeling set. We evaluate the proposed approach, adaptive Bayesian label fusion using kernel-based similarity metrics, in the specific case of hippocampus segmentation of five benchmark MRI collections, including ADNI dataset, resulting in an increased performance (assessed through the Dice index) as compared to other recent works.

Magnetic resonance imaging (MRI) has evolved into the gold standard for quantifying excess adiposity, but reliable, efficient use in longitudinal studies requires analysis of large numbers of images. The objective of this study is to develop and evaluate a segmentation method designed to identify cardiac, subcutaneous, and visceral adipose tissue (VAT) in Dixon MRI scans. The proposed method is evaluated using 10 scans from volunteer females 18- to 35-years old, with body mass indexes between 30 and 39.99  kg  /  m². Cross-sectional area (CSA) for cardiac adipose tissue (CAT), subcutaneous adipose tissue (SAT), and VAT, is compared to manually-traced results from three observers. Comparisons of CSA are made in 191 images for CAT, 394 images for SAT, and 50 images for VAT. The segmentation correlated well with respect to average observer CSA with Pearson correlation coefficient (R²) values of 0.80 for CAT, 0.99 for SAT, and 0.99 for VAT. The proposed method provides accurate segmentation of CAT, SAT, and VAT and provides an option to support longitudinal studies of obesity intervention.

Multiple sclerosis (MS) is a white matter (WM) disease characterized by the formation of WM lesions, which can be visualized by magnetic resonance imaging (MRI). The fluid-attenuated inversion recovery (FLAIR) MRI pulse sequence is used clinically and in research for the detection of WM lesions. However, in clinical settings, some MRI pulse sequences could be missed because of various constraints. The use of the three-dimensional fully convolutional neural networks is proposed to predict FLAIR pulse sequences from other MRI pulse sequences. In addition, the contribution of each input pulse sequence is evaluated with a pulse sequence-specific saliency map. This approach is tested on a real MS image dataset and evaluated by comparing this approach with other methods and by assessing the lesion contrast in the synthetic FLAIR pulse sequence. Both the qualitative and quantitative results show that this method is competitive for FLAIR synthesis.

Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep architectures. Second, feature accumulation with recurrent residual convolutional layers ensures better feature representation for segmentation tasks. Third, it allows us to design better U-Net architectures with the same number of network parameters with better performance for medical image segmentation. The proposed models are tested on three benchmark datasets, such as blood vessel segmentation in retinal images, skin cancer segmentation, and lung lesion segmentation. The experimental results show superior performance on segmentation tasks compared to equivalent models, including a variant of a fully connected convolutional neural network called SegNet, U-Net, and residual U-Net.

Zonal segmentation of the prostate gland using magnetic resonance imaging (MRI) is clinically important for prostate cancer (PCa) diagnosis and image-guided treatments. A two-dimensional convolutional neural network (CNN) based on the U-net architecture was evaluated for segmentation of the central gland (CG) and peripheral zone (PZ) using a dataset of 40 patients (34 PCa positive and 6 PCa negative) scanned on two different MRI scanners (1.5T GE and 3T Siemens). Images were cropped around the prostate gland to exclude surrounding tissues, resampled to 0.5  ×  0.5  ×  0.5  mm voxels and z-score normalized before being propagated through the CNN. Performance was evaluated using the Dice similarity coefficient (DSC) and mean absolute distance (MAD) in a fivefold cross-validation setup. Overall performance showed DSC of 0.794 and 0.692, and MADs of 3.349 and 2.993 for CG and PZ, respectively. Dividing the gland into apex, mid, and base showed higher DSC for the midgland compared to apex and base for both CG and PZ. We found no significant difference in DSC between the two scanners. A larger dataset, preferably with multivendor scanners, is necessary for validation of the proposed algorithm; however, our results are promising and have clinical potential.

Barrett’s esophagus (BE) is a premalignant condition that has an increased risk to turn into esophageal adenocarcinoma. Classification and staging of the different changes (BE in particular) in the esophageal mucosa are challenging since they have a very similar appearance. Confocal laser endomicroscopy (CLE) is one of the newest endoscopy tools that is commonly used to identify the pathology type of the suspected area of the esophageal mucosa. However, it requires a well-trained physician to classify the image obtained from CLE. An automatic stage classification of esophageal mucosa is presented. The proposed model enhances the internal features of CLE images using an image filter that combines fractional integration with differentiation. Various features are then extracted on a multiscale level, to classify the mucosal tissue into one of its four types: normal squamous (NS), gastric metaplasia (GM), intestinal metaplasia (IM or BE), and neoplasia. These sets of features are used to train two conventional classifiers: support vector machine (SVM) and random forest. The proposed method was evaluated on a dataset of 96 patients with 557 images of different histopathology types. The SVM classifier achieved the best performance with 96.05% accuracy based on a leave-one-patient-out cross-validation. Additionally, the dataset was divided into 60% training and 40% testing; the model achieved an accuracy of 93.72% for the testing data using the SVM. The presented model showed superior performance when compared with four state-of-the-art methods. Accurate classification is essential for the intestinal metaplasia grade, which most likely develops into esophageal cancer. Not only does our method come to the aid of physicians for more accurate diagnosis by acting as a second opinion, but it also acts as a training method for junior physicians who need practice in using CLE. Consequently, this work contributes to an automatic classification that facilitates early intervention and decreases samples of required biopsy.

Ultrasound (US) has been increasingly used during interventions, such as cardiac catheterization. To accurately identify the catheter inside US images, extra training for physicians and sonographers is needed. As a consequence, automated segmentation of the catheter in US images and optimized presentation viewing to the physician can be beneficial to accelerate the efficiency and safety of interventions and improve their outcome. For cardiac catheterization, a three-dimensional (3-D) US image is potentially attractive because of no radiation modality and richer spatial information. However, due to a limited spatial resolution of 3-D cardiac US and complex anatomical structures inside the heart, image-based catheter segmentation is challenging. We propose a cardiac catheter segmentation method in 3-D US data through image processing techniques. Our method first applies a voxel-based classification through newly designed multiscale and multidefinition features, which provide a robust catheter voxel segmentation in 3-D US. Second, a modified catheter model fitting is applied to segment the curved catheter in 3-D US images. The proposed method is validated with extensive experiments, using different in-vitro, ex-vivo, and in-vivo datasets. The proposed method can segment the catheter within an average tip-point error that is smaller than the catheter diameter (1.9 mm) in the volumetric images. Based on automated catheter segmentation and combined with optimal viewing, physicians do not have to interpret US images and can focus on the procedure itself to improve the quality of cardiac intervention.

We investigated effects of prevalence and case distribution on radiologist diagnostic performance as measured by area under the receiver operating characteristic curve (AUC) and sensitivity-specificity in lab-based reader studies evaluating imaging devices. Our retrospective reader studies compared full-field digital mammography (FFDM) to screen-film mammography (SFM) for women with dense breasts. Mammograms were acquired from the prospective Digital Mammographic Imaging Screening Trial. We performed five reader studies that differed in terms of cancer prevalence and the distribution of noncancers. Twenty radiologists participated in each reader study. Using split-plot study designs, we collected recall decisions and multilevel scores from the radiologists for calculating sensitivity, specificity, and AUC. Differences in reader-averaged AUCs slightly favored SFM over FFDM (biggest AUC difference: 0.047, SE  =  0.023, p  =  0.047), where standard error accounts for reader and case variability. The differences were not significant at a level of 0.01 (0.05/5 reader studies). The differences in sensitivities and specificities were also indeterminate. Prevalence had little effect on AUC (largest difference: 0.02), whereas sensitivity increased and specificity decreased as prevalence increased. We found that AUC is robust to changes in prevalence, while radiologists were more aggressive with recall decisions as prevalence increased.

Previously published work on joint estimation/detection tasks has focused on the area under the estimation receiver operating characteristic (EROC) curve as a figure of merit (FOM) for these tasks in imaging. Another FOM for these joint tasks is the Bayesian risk, where a cost is assigned to all detection outcomes and to the estimation errors, and then averaged over all sources of randomness in the object ensemble and the imaging system. Important elements of the cost function, which are not included in standard EROC analysis, are that the cost for a false positive depends on the estimate produced for the parameter vector, and the cost for a false negative depends on the true value of the parameter vector. The ideal observer in this setting, which minimizes the risk, is derived for two applications. In the first application, a parameter vector is estimated only in the case of a signal present classification. For the second application, parameter vectors are estimated for either classification, and these vectors may have different dimensions. In both applications, a risk-based estimation receiver operating characteristic curve is defined and an expression for the area under this curve is given. It is also shown that, for some observers, this area may be estimated from a two alternative forced choice test. Finally, if the classifier is optimized for a given estimator, then it is shown that the slope of the risk-based estimation receiver operating characteristic curve at each point is the negative of the ratio of the prior probabilities for the two classes.

We compare the reproducibility of the human observers and a channelized Hotelling observer (CHO), when reading digital breast tomosynthesis (DBT) images of a physical phantom containing a breast simulating structured background and calcification clusters at three dose levels. The phantom is scanned 217 times on a Siemens Inspiration DBT system. Volumes of interest, with and without the calcification targets, are extracted and the human observers’ percentage of correct (PC) scores is evaluated using a four-alternative forced choice method. A two-layer CHO is developed using the human observer results. The first layer consists of a localizing CHO that identifies the most conspicuous calcifications using two Laguerre–Gauss channels. Then a CHO with eight Gabor channels estimates the PC score for the calcification cluster. Observer reproducibility is estimated by bootstrapping, and the standard deviation (SD) is used as a figure of merit. The CHO closely approximated the human observer results for all the three dose levels with a correlation of >0.97. For the larger calcification cluster sizes, both observers have similar reproducibility, whereas the CHO is more reproducible for the smaller calcifications, with a maximum of 5.5 SD against 13.1 SD for the human observers. The developed CHO is a good candidate for automated reading of the calcification clusters of the structured phantom, with better reproducibility than the human readers for small calcifications.

In an effort to increase the efficiency and cure rate of nonmelanoma skin cancer (NMSC) excisions, we have developed a point-of-care method of imaging and evaluation of skin cancer margins. We evaluate the skin surgical specimens using a smart, near-infrared probe (6qcNIR) that fluoresces in the presence of cathepsin proteases overexpressed in NMSC. Imaging is done with an inverted, flying-spot fluorescence scanner that reduces scatter, giving a 70% improved step response as compared to a conventional imaging system. We develop a scheme for careful comparison of fluorescent signals to histological annotation, which involves image segmentation, fiducial-based registration, and nonrigid free-form deformation on fluorescence images, corresponding color images, “bread-loafed” tissue images, hematoxylin and eosin (H&E)-stained slides, and pathological annotations. From epidermal landmarks, spatial accuracy in the bulk of the sample is ∼500  μm, which when extrapolated with a linear stretch model, suggests an error at the margin of ∼100  μm, within clinical reporting standards. Cancer annotations on H&E slides are transformed and superimposed on the fluorescence images to generate the final results. Using this methodology, fluorescence cancer signals are generally found to correspond spatially with histological annotations. This method will allow us to accurately analyze molecular probes for imaging skin cancer margins.

Automated detection and segmentation of nuclei from high-resolution histopathological images is a challenging problem owing to the size and complexity of digitized histopathologic images. In the context of breast cancer, the modified Bloom–Richardson Grading system is highly correlated with the morphological and topological nuclear features are highly correlated with Modified Bloom–Richardson grading. Therefore, to develop a computer-aided prognosis system, automated detection and segmentation of nuclei are critical prerequisite steps. We present a method for automated detection and segmentation of breast cancer nuclei named a convolutional neural network initialized active contour model with adaptive ellipse fitting (CoNNACaeF). The CoNNACaeF model is able to detect and segment nuclei simultaneously, which consist of three different modules: convolutional neural network (CNN) for accurate nuclei detection, (2) region-based active contour (RAC) model for subsequent nuclear segmentation based on the initial CNN-based detection of nuclear patches, and (3) adaptive ellipse fitting for overlapping solution of clumped nuclear regions. The performance of the CoNNACaeF model is evaluated on three different breast histological data sets, comprising a total of 257 H&E-stained images. The model is shown to have improved detection accuracy of F-measure 80.18%, 85.71%, and 80.36% and average area under precision-recall curves (AveP) 77%, 82%, and 74% on a total of 3 million nuclei from 204 whole slide images from three different datasets. Additionally, CoNNACaeF yielded an F-measure at 74.01% and 85.36%, respectively, for two different breast cancer datasets. The CoNNACaeF model also outperformed the three other state-of-the-art nuclear detection and segmentation approaches, which are blue ratio initialized local region active contour, iterative radial voting initialized local region active contour, and maximally stable extremal region initialized local region active contour models.

We propose a segmentation method for nuclei in glioblastoma histopathologic images based on a sparse shape prior guided variational level set framework. By spectral clustering and sparse coding, a set of shape priors is exploited to accommodate complicated shape variations. We automate the object contour initialization by a seed detection algorithm and deform contours by minimizing an energy functional that incorporates a shape term in a sparse shape prior representation, an adaptive contour occlusion penalty term, and a boundary term encouraging contours to converge to strong edges. As a result, our approach is able to deal with mutual occlusions and detect contours of multiple intersected nuclei simultaneously. Our method is applied to several whole-slide histopathologic image datasets for nuclei segmentation. The proposed method is compared with other state-of-the-art methods and demonstrates good accuracy for nuclei detection and segmentation, suggesting its promise to support biomedical image-based investigations.

This erratum corrects an error in “Measuring temporal stability of positron emission tomography standardized uptake value bias using long-lived sources in a multicenter network,” by D. Byrd et al.