Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imaging

Abstract

Modern generative models, such as generative adversarial networks (GANs), hold tremendous promise for several areas of medical imaging, such as unconditional medical image synthesis, image restoration, reconstruction and translation, and optimization of imaging systems. However, procedures for establishing stochastic image models (SIMs) using GANs remain generic and do not address specific issues relevant to medical imaging. In this work, canonical SIMs that simulate realistic vessels in angiography images are employed to evaluate procedures for establishing SIMs using GANs. The GAN-based SIM is compared to the canonical SIM based on its ability to reproduce those statistics that are meaningful to the particular medically realistic SIM considered. It is shown that evaluating GANs using classical metrics and medically relevant metrics may lead to different conclusions about the fidelity of the trained GANs. This work highlights the need for the development of objective metrics for evaluating GANs.

arXiv commentPublished in SPIE Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment

References in corpus (4)

• Generative Adversarial Network in Medical Imaging: A Review
• MedGAN: Medical Image Translation using GANs
• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
• Objective task-based evaluation of artificial intelligence-based medical imaging methods: Framework, strategies and role of the physician