KEYWORDS: Data modeling, Education and training, RGB color model, Echocardiography, Performance modeling, Deep learning, Motion models, Ablation, 3D modeling, Image classification
PurposeThe inherent characteristics of transthoracic echocardiography (TTE) images such as low signal-to-noise ratio and acquisition variations can limit the direct use of TTE images in the development and generalization of deep learning models. As such, we propose an innovative automated framework to address the common challenges in the process of echocardiography deep learning model generalization on the challenging task of constrictive pericarditis (CP) and cardiac amyloidosis (CA) differentiation.ApproachPatients with a confirmed diagnosis of CP or CA and normal cases from Mayo Clinic Rochester and Arizona were identified to extract baseline demographics and the apical 4 chamber view from TTE studies. We proposed an innovative preprocessing and image generalization framework to process the images for training the ResNet50, ResNeXt101, and EfficientNetB2 models. Ablation studies were conducted to justify the effect of each proposed processing step in the final classification performance.ResultsThe models were initially trained and validated on 720 unique TTE studies from Mayo Rochester and further validated on 225 studies from Mayo Arizona. With our proposed generalization framework, EfficientNetB2 generalized the best with an average area under the curve (AUC) of 0.96 (±0.01) and 0.83 (±0.03) on the Rochester and Arizona test sets, respectively.ConclusionsLeveraging the proposed generalization techniques, we successfully developed an echocardiography-based deep learning model that can accurately differentiate CP from CA and normal cases and applied the model to images from two sites. The proposed framework can be further extended for the development of echocardiography-based deep learning models.
The use of artificial intelligence (AI) in healthcare has become a very active research area in the last few years. While significant progress has been made in image classification tasks, only a few AI methods are actually deployed in clinical settings. A major hurdle in actively using clinical AI models is the trustworthiness of these models. Often, these complex models are utilized as black boxes in which promising results are generated. However, when scrutinized, these models reveal implicit biases during decision-making, such as having an unintended bias towards particular ethnic groups and sub-populations. In our study, we develop a two-step adversarial debiasing approach with partial learning that can reduce the disparity while preserving the performance of the targeted diagnosis/classification task. The methodology has been evaluated on two independent medical image case studies - chest X-rays and mammograms and showed promises in bias reduction while preserving the targeted performance on both internal and external datasets.
Purpose: In recent years, the development and exploration of deeper and more complex deep learning models has been on the rise. However, the availability of large heterogeneous datasets to support efficient training of deep learning models is lacking. While linear image transformations for augmentation have been used traditionally, the recent development of generative adversarial networks (GANs) could theoretically allow us to generate an infinite amount of data from the real distribution to support deep learning model training. Recently, the Radiological Society of North America (RSNA) curated a multiclass hemorrhage detection challenge dataset that includes over 800,000 images for hemorrhage detection, but all high-performing models were trained using traditional data augmentation techniques. Given a wide variety of selections, the augmentation for image classification often follows a trial-and-error policy.
Approach: We designed conditional DCGAN (cDCGAN) and in parallel trained multiple popular GAN models to use as online augmentations and compared them to traditional augmentation methods for the hemorrhage case study.
Results: Our experimentations show that the super-minority, epidural hemorrhages with cDCGAN augmentation presented a minimum of 2 × improvement in their performance against the traditionally augmented model using the same classifier configuration.
Conclusion: This shows that for complex and imbalanced datasets, traditional data imbalancing solutions may not be sufficient and require more complex and diverse data augmentation methods such as GANs to solve.
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.