Towards generative adversarial networks as a new paradigm for radiology education

Abstract

Medical students and radiology trainees typically view thousands of images in order to "train their eye" to detect the subtle visual patterns necessary for diagnosis. Nevertheless, infrastructural and legal constraints often make it difficult to access and quickly query an abundance of images with a user-specified feature set. In this paper, we use a conditional generative adversarial network (GAN) to synthesize $1024\times 1024$ pixel pelvic radiographs that can be queried with conditioning on fracture status. We demonstrate that the conditional GAN learns features that distinguish fractures from non-fractures by training a convolutional neural network exclusively on images sampled from the GAN and achieving an AUC of $>0.95$ on a held-out set of real images. We conduct additional analysis of the images sampled from the GAN and describe ongoing work to validate educational efficacy.

arXiv commentMachine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:cs/0101200

References in corpus (7)

• Conditional Generative Adversarial Nets
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Data Augmentation Generative Adversarial Networks
• Synthetic Medical Images from Dual Generative Adversarial Networks
• Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks
• Detecting hip fractures with radiologist-level performance using deep neural networks
• High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks

Cited by in corpus (6)

• Generative Adversarial Network in Medical Imaging: A Review
• On Leveraging Pretrained GANs for Generation with Limited Data
• MammoGANesis: Controlled Generation of High-Resolution Mammograms for Radiology Education
• Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
• Artificial Intelligence for Pediatric Ophthalmology
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation