Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning

TL;DR

This paper introduces a novel unsupervised domain adaptation framework combining adversarial learning and self-learning techniques to improve cross-modality liver segmentation from CT to MRI, achieving high accuracy without labeled MRI data.

Contribution

It proposes a joint adversarial and self-learning framework with shape and semantic awareness, and introduces pseudo-labeling and augmentation strategies for robust cross-modality segmentation.

Findings

Achieved a Dice score of 0.912 on public datasets.

Outperformed four supervised methods in liver segmentation.

Enhanced robustness with low-signal augmentation.

Abstract

Liver segmentation on images acquired using computed tomography (CT) and magnetic resonance imaging (MRI) plays an important role in clinical management of liver diseases. Compared to MRI, CT images of liver are more abundant and readily available. However, MRI can provide richer quantitative information of the liver compared to CT. Thus, it is desirable to achieve unsupervised domain adaptation for transferring the learned knowledge from the source domain containing labeled CT images to the target domain containing unlabeled MR images. In this work, we report a novel unsupervised domain adaptation framework for cross-modality liver segmentation via joint adversarial learning and self-learning. We propose joint semantic-aware and shape-entropy-aware adversarial learning with post-situ identification manner to implicitly align the distribution of task-related features extracted from the target domain with those from the source domain. In proposed framework, a network is trained with the above two adversarial losses in an unsupervised manner, and then a mean completer of pseudo-label generation is employed to produce pseudo-labels to train the next network (desired model). Additionally, semantic-aware adversarial learning and two self-learning methods, including pixel-adaptive mask refinement and student-to-partner learning, are proposed to train the desired model. To improve the robustness of the desired model, a low-signal augmentation function is proposed to transform MRI images as the input of the desired model to handle hard samples. Using the public data sets, our experiments demonstrated the proposed unsupervised domain adaptation framework reached four supervised learning methods with a Dice score 0.912 plus or minus 0.037 (mean plus or minus standard deviation).