C-MADA: Unsupervised Cross-Modality Adversarial Domain Adaptation framework for medical Image Segmentation

TL;DR

C-MADA is an unsupervised framework that enhances medical image segmentation across different imaging modalities by combining image translation and adversarial training to learn domain-invariant features.

Contribution

It introduces a sequential image- and feature-level adaptation approach for cross-modality domain adaptation in medical image segmentation.

Findings

Achieved competitive brain MRI segmentation results

Effectively reduces domain gap in medical images

Improves segmentation accuracy with shape and texture information

Abstract

Deep learning models have obtained state-of-the-art results for medical image analysis. However, when these models are tested on an unseen domain there is a significant performance degradation. In this work, we present an unsupervised Cross-Modality Adversarial Domain Adaptation (C-MADA) framework for medical image segmentation. C-MADA implements an image- and feature-level adaptation method in a sequential manner. First, images from the source domain are translated to the target domain through an un-paired image-to-image adversarial translation with cycle-consistency loss. Then, a U-Net network is trained with the mapped source domain images and target domain images in an adversarial manner to learn domain-invariant feature representations. Furthermore, to improve the networks segmentation performance, information about the shape, texture, and con-tour of the predicted segmentation is included during the adversarial train-ing. C-MADA is tested on the task of brain MRI segmentation, obtaining competitive results.