Saved in:
Bibliographic Details
Main Authors: Xin, Bowen, Young, Tony, Wainwright, Claire E, Blake, Tamara, Lebrat, Leo, Gaass, Thomas, Benkert, Thomas, Stemmer, Alto, Coman, David, Dowling, Jason
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.09432
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911993461473280
author Xin, Bowen
Young, Tony
Wainwright, Claire E
Blake, Tamara
Lebrat, Leo
Gaass, Thomas
Benkert, Thomas
Stemmer, Alto
Coman, David
Dowling, Jason
author_facet Xin, Bowen
Young, Tony
Wainwright, Claire E
Blake, Tamara
Lebrat, Leo
Gaass, Thomas
Benkert, Thomas
Stemmer, Alto
Coman, David
Dowling, Jason
contents Medical image synthesis generates additional imaging modalities that are costly, invasive or harmful to acquire, which helps to facilitate the clinical workflow. When training pairs are substantially misaligned (e.g., lung MRI-CT pairs with respiratory motion), accurate image synthesis remains a critical challenge. Recent works explored the directional registration module to adjust misalignment in generative adversarial networks (GANs); however, substantial misalignment will lead to 1) suboptimal data mapping caused by correspondence ambiguity, and 2) degraded image fidelity caused by morphology influence on discriminators. To address the challenges, we propose a novel Deformation-aware GAN (DA-GAN) to dynamically correct the misalignment during the image synthesis based on multi-objective inverse consistency. Specifically, in the generative process, three levels of inverse consistency cohesively optimise symmetric registration and image generation for improved correspondence. In the adversarial process, to further improve image fidelity under misalignment, we design deformation-aware discriminators to disentangle the mismatched spatial morphology from the judgement of image fidelity. Experimental results show that DA-GAN achieved superior performance on a public dataset with simulated misalignments and a real-world lung MRI-CT dataset with respiratory motion misalignment. The results indicate the potential for a wide range of medical image synthesis tasks such as radiotherapy planning.
format Preprint
id arxiv_https___arxiv_org_abs_2408_09432
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairs
Xin, Bowen
Young, Tony
Wainwright, Claire E
Blake, Tamara
Lebrat, Leo
Gaass, Thomas
Benkert, Thomas
Stemmer, Alto
Coman, David
Dowling, Jason
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Medical image synthesis generates additional imaging modalities that are costly, invasive or harmful to acquire, which helps to facilitate the clinical workflow. When training pairs are substantially misaligned (e.g., lung MRI-CT pairs with respiratory motion), accurate image synthesis remains a critical challenge. Recent works explored the directional registration module to adjust misalignment in generative adversarial networks (GANs); however, substantial misalignment will lead to 1) suboptimal data mapping caused by correspondence ambiguity, and 2) degraded image fidelity caused by morphology influence on discriminators. To address the challenges, we propose a novel Deformation-aware GAN (DA-GAN) to dynamically correct the misalignment during the image synthesis based on multi-objective inverse consistency. Specifically, in the generative process, three levels of inverse consistency cohesively optimise symmetric registration and image generation for improved correspondence. In the adversarial process, to further improve image fidelity under misalignment, we design deformation-aware discriminators to disentangle the mismatched spatial morphology from the judgement of image fidelity. Experimental results show that DA-GAN achieved superior performance on a public dataset with simulated misalignments and a real-world lung MRI-CT dataset with respiratory motion misalignment. The results indicate the potential for a wide range of medical image synthesis tasks such as radiotherapy planning.
title Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairs
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.09432