A bidirectional multilayer contrastive adaptation network with anatomical structure preservation for unpaired cross-modality medical image segmentation. (October 2022)

• Record Type: Journal Article
• Authors: Liu, Hong; Zhuang, Yuzhou; Song, Enmin; Xu, Xiangyang; Hung, Chih-Cheng
• Is Part Of: Computers in biology and medicine. Volume 149(2022)
• Publication Date: 2022-10
• Subjects: Unsupervised domain adaptation -- Contrastive learning -- Adversarial learning -- Anatomical structure consistency -- Cross-modality medical image segmentation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105964
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Multi-modal medical image segmentation has achieved great success through supervised deep learning networks. However, because of domain shift and limited annotation information, unpaired cross-modality segmentation tasks are still challenging. The unsupervised domain adaptation (UDA) methods can alleviate the segmentation degradation of cross-modality segmentation by knowledge transfer between different domains, but current methods still suffer from the problems of model collapse, adversarial training instability, and mismatch of anatomical structures. To tackle these issues, we propose a bidirectional multilayer contrastive adaptation network (BMCAN) for unpaired cross-modality segmentation. The shared encoder is first adopted for learning modality-invariant encoding representations in image synthesis and segmentation simultaneously. Secondly, to retain the anatomical structure consistency in cross-modality image synthesis, we present a structure-constrained cross-modality image translation approach for image alignment. Thirdly, we construct a bidirectional multilayer contrastive learning approach to preserve the anatomical structures and enhance encoding representations, which utilizes two groups of domain-specific multilayer perceptron (MLP) networks to learn modality-specific features. Finally, a semantic information adversarial learning approach is designed to learn structural similarities of semantic outputs for output space alignment. Our proposed method was tested on three different cross-modality segmentation tasks: brain tissue, brain tumor, and cardiac substructure segmentation. Compared with other UDA methods, experimental results show that our proposed BMCAN achieves state-of-the-art segmentation performance on the above three tasks, and it has fewer training components and better feature representations for overcoming overfitting and domain shift problems. Our proposed method can efficiently reduce the annotation burden of radiologists in cross-modality image analysis. Highlights: We proposed an end-to-end cross-modality segmentation framework for unpaired brain tissue, brain tumor, and cardiac substructure segmentation. We present a structure-constrained cross-modality image translation approach for image synthesis. We design a bidirectional multilayer contrastive learning approach to preserve anatomical details and enhance representations. We present a semantic information adversarial learning approach for learning structural similarities. Our method exhibits low model complexity and achieves state-of-the-art performance on three benchmark datasets.