TY - GEN
T1 - Evaluating generative stochastic image models using task-based image quality measures
AU - Kelkar, Varun A.
AU - Gotsis, Dimitrios S.
AU - Deshpande, Rucha
AU - Brooks, Frank J.
AU - Prabhat, K. C.
AU - Myers, Kyle J.
AU - Zeng, Rongping
AU - Anastasio, Mark A.
N1 - Publisher Copyright:
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - Generative adversarial networks
KW - image perception
KW - objective image quality assessment
KW - stochastic image models
UR - http://www.scopus.com/inward/record.url?scp=85160945689&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85160945689&partnerID=8YFLogxK
U2 - 10.1117/12.2654590
DO - 10.1117/12.2654590
M3 - Conference contribution
AN - SCOPUS:85160945689
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2023
A2 - Mello-Thoms, Claudia R.
A2 - Chen, Yan
PB - SPIE
T2 - Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment
Y2 - 21 February 2023 through 23 February 2023
ER -