Towards generative adversarial networks as a new paradigm for radiology education
This addresses the need for scalable, queryable image datasets for medical students and radiology trainees, though it is incremental as it applies an existing GAN method to a new domain.
The paper tackles the problem of limited access to diverse medical images for radiology education by using a conditional GAN to synthesize high-resolution pelvic radiographs based on fracture status, achieving an AUC of >0.95 when a CNN trained on synthetic images is tested on real images.
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 $1024\times1024$ 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.