Paper
3 November 2020 Unpaired PET/CT image synthesis of liver region using CycleGAN
Author Affiliations +
Proceedings Volume 11583, 16th International Symposium on Medical Information Processing and Analysis; 115830T (2020) https://doi.org/10.1117/12.2576095
Event: The 16th International Symposium on Medical Information Processing and Analysis, 2020, Lima, Peru
Abstract
Cross-modality synthesis represent nowadays a promising application in medical image processing to manage the problem of paired data scarcity. In this work we designed and trained a CycleGAN model to generate PET/CT data from 2D slices collected from the liver body region of twelve patients. The results obtained from the six test patients show how our model can outperform baseline CycleGAN framework and effectively be used for synthesizing artificial images to be used for data augmentation or dataset completion.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gianmarco Santini, Constance Fourcade, Noémie Moreau, Caroline Rousseau, Ludovic Ferrer, Marie Lacombe, Vincent Fleury, Mario Campone, Pascal Jézéquel, and Mathieu Rubeaux "Unpaired PET/CT image synthesis of liver region using CycleGAN", Proc. SPIE 11583, 16th International Symposium on Medical Information Processing and Analysis, 115830T (3 November 2020); https://doi.org/10.1117/12.2576095
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Liver

Data modeling

Image processing

Medical imaging

RELATED CONTENT


Back to Top