Structure Preserving Cycle-GAN for Unsupervised Medical Image Domain Adaptation

TL;DR

This paper introduces the Structure Preserving Cycle-GAN (SP Cycle-GAN), a novel unsupervised domain adaptation method for medical imaging that maintains anatomical structures during image translation, improving segmentation accuracy across different modalities.

Contribution

The work proposes a new Cycle-GAN variant with a segmentation loss to ensure structure preservation, enhancing unsupervised domain adaptation in medical image segmentation tasks.

Findings

Outperforms baseline Cycle-GAN in blood vessel segmentation (4% DSC increase).

Achieves state-of-the-art myocardium segmentation Dice score of 0.7435 in MM-WHS dataset.

Effectively preserves anatomical structures visually and quantitatively.

Abstract

The presence of domain shift in medical imaging is a common issue, which can greatly impact the performance of segmentation models when dealing with unseen image domains. Adversarial-based deep learning models, such as Cycle-GAN, have become a common model for approaching unsupervised domain adaptation of medical images. These models however, have no ability to enforce the preservation of structures of interest when translating medical scans, which can lead to potentially poor results for unsupervised domain adaptation within the context of segmentation. This work introduces the Structure Preserving Cycle-GAN (SP Cycle-GAN), which promotes medical structure preservation during image translation through the enforcement of a segmentation loss term in the overall Cycle-GAN training process. We demonstrate the structure preserving capability of the SP Cycle-GAN both visually and through comparison of Dice score segmentation performance for the unsupervised domain adaptation models. The SP Cycle-GAN is able to outperform baseline approaches and standard Cycle-GAN domain adaptation for binary blood vessel segmentation in the STARE and DRIVE datasets, and multi-class Left Ventricle and Myocardium segmentation in the multi-modal MM-WHS dataset. SP Cycle-GAN achieved a state of the art Myocardium segmentation Dice score (DSC) of 0.7435 for the MR to CT MM-WHS domain adaptation problem, and excelled in nearly all categories for the MM-WHS dataset. SP Cycle-GAN also demonstrated a strong ability to preserve blood vessel structure in the DRIVE to STARE domain adaptation problem, achieving a 4% DSC increase over a default Cycle-GAN implementation.