C-MADA: Unsupervised Cross-Modality Adversarial Domain Adaptation framework for medical Image Segmentation
This work addresses domain shift issues in medical imaging, which is crucial for improving model robustness in clinical applications, but it appears incremental as it builds on existing adversarial and cycle-consistency methods.
The paper tackled the problem of performance degradation in deep learning models for medical image segmentation when applied to unseen domains, by proposing an unsupervised cross-modality adversarial domain adaptation framework that achieved competitive results on brain MRI segmentation.
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.