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

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2023
Subtitle of host publicationImage Perception, Observer Performance, and Technology Assessment
EditorsClaudia R. Mello-Thoms, Yan Chen
PublisherSPIE
ISBN (Electronic)9781510660397
DOIs
StatePublished - 2023
Externally publishedYes
EventMedical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment - San Diego, United States
Duration: Feb 21 2023Feb 23 2023

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12467
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment
Country/TerritoryUnited States
CitySan Diego
Period2/21/232/23/23

Keywords

  • Generative adversarial networks
  • image perception
  • objective image quality assessment
  • stochastic image models

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Evaluating generative stochastic image models using task-based image quality measures'. Together they form a unique fingerprint.

Cite this