Skip to main navigation Skip to search Skip to main content

Dual-Domain Equivariant Generative Adversarial Network for Multimodal CT-Pet Synthesis

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

Abstract

We present a Dual-Domain Equivariant Generative Adversarial Network (DDE-GAN) for multimodal CT-PET image synthesis. Traditional GAN-based approaches often operate solely in the spatial domain and ignore geometric consistency, resulting in limited structural fidelity. DDE-GAN addresses these challenges by jointly learning from both spatial and frequency (Fourier) domains, capturing complementary anatomical and spectral information. Furthermore, rotational equivariance embedded in the physics of the CT and PET measurements are integrated into the loss of both the generator and discriminator to ensure consistent responses under rotations, improving anatomical accuracy. A hierarchical dual-domain training strategy enforces intraand inter-domain consistency through multi-stage loss functions. Evaluated on the HECKTOR 2022 CT-PET dataset, DDE-GAN achieves superior synthesis quality over baseline models for CT-PET image synthesis. The results demonstrate that combining dual-domain learning with geometric equivariance substantially enhances multimodal image synthesis accuracy and robustness, enabling practical applications in PET completion and data augmentation.

Original languageEnglish
Title of host publicationISBI 2026 - 23rd IEEE International Symposium on Biomedical Imaging
Place of PublicationLondon
PublisherIEEE Computer Society
ISBN (Electronic)9798331577636
DOIs
Publication statusPublished - 20 May 2026
Event23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026 - London, United Kingdom
Duration: 8 Apr 202611 Apr 2026

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2026-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026
Country/TerritoryUnited Kingdom
CityLondon
Period8/04/2611/04/26

Keywords

  • CT-PET image Synthesis
  • Dual-domain
  • Equivariance
  • Generative Adversarial Network

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Dual-Domain Equivariant Generative Adversarial Network for Multimodal CT-Pet Synthesis'. Together they form a unique fingerprint.

Cite this