Evaluating generative stochastic image models using task-based image quality measures

Varun A. Kelkar; Dimitrios S. Gotsis; Rucha Deshpande; Frank J. Brooks; Prabhat K. C.; Kyle J. Myers; Rongping Zeng; Mark A. Anastasio

doi:10.1117/12.2654590

3 April 2023 Evaluating generative stochastic image models using task-based image quality measures

Varun A. Kelkar, Dimitrios S. Gotsis, Rucha Deshpande, Frank J. Brooks, Prabhat K. C., Kyle J. Myers, Rongping Zeng, Mark A. Anastasio

Author Affiliations +

Proceedings Volume 12467, Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment; 1246717 (2023) https://doi.org/10.1117/12.2654590
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Modern generative models, such as generative adversarial networks (GANs), hold tremendous promise for several applications in medical imaging that include unconditional medical image synthesis, image translation, and optimization of imaging systems. However, the extent to which a GAN learns image statistics that are relevant to a diagnostic task is unknown. In this work, canonical stochastic image models (SIMs) that simulate realistic mammographic textures are employed to evaluate GAN-based SIMs with respect to detection, detection-localization, and detection-estimation tasks. It is shown that the specific GAN architecture considered has higher propensity to generate statistics that confound the observers performing the three considered tasks. This work highlights the need for continued development of objective metrics for evaluating GANs.

Citation Download Citation

Varun A. Kelkar, Dimitrios S. Gotsis, Rucha Deshpande, Frank J. Brooks, Prabhat K. C., Kyle J. Myers, Rongping Zeng, and Mark A. Anastasio "Evaluating generative stochastic image models using task-based image quality measures", Proc. SPIE 12467, Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment, 1246717 (3 April 2023); https://doi.org/10.1117/12.2654590

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available