A contrastive consistency semi-supervised left atrium segmentation model. (July 2022)

• Record Type: Journal Article
• Authors: Liu, Yashu; Wang, Wei; Luo, Gongning; Wang, Kuanquan; Li, Shuo
• Is Part Of: Computerized medical imaging and graphics. Volume 99(2022)
• Publication Date: 2022-07
• Subjects: Left atrium segmentation -- Semi-supervised learning -- Contrastive learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102092
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Accurate segmentation for the left atrium (LA) is a key process of clinical diagnosis and therapy for atrial fibrillation. In clinical, the semantic-level segmentation of LA consumes much time and labor. Although supervised deep learning methods can somewhat solve this problem, a high-efficient deep learning model requires abundant labeled data that is hard to acquire. Therefore, the research on automatic LA segmentation of leveraging unlabeled data is highly required. In this paper, we propose a semi-supervised LA segmentation framework including a segmentation model and a classification model. The segmentation model takes volumes from both labeled and unlabeled data as input and generates predictions of LAs. And then, a classification model maps these predictions to class-vectors for each input. Afterward, to leverage the class information, we construct a contrastive consistency loss function based on these class-vectors, so that the model can enlarge the discrepancy of the inter-class and compact the similarity of the intra-class for learning more distinguishable representation. Moreover, we set the class-vectors from the labeled data as references to the class-vectors from the unlabeled data to relieve the influence of the unreliable prediction for the unlabeled data. At last, we evaluate our semi-supervised LA segmentation framework on a public LA dataset using four universal metrics and compare it with recent state-of-the-art models. The proposed model achieves the best performance on all metrics with a Dice Score of 89.81 %, Jaccard of 81.64 %, 95 % Hausdorff distance of 7.15 mm, and Average Surface Distance of 1.82 mm. The outstanding performance of the proposed framework shows that it may have a significant contribution to assisting the therapy of patients with atrial fibrillation. Code is available at: https://github.com/PerceptionComputingLab/SCC . Highlights: A semi-supervised LA segmentation framework to leverage unlabeled data for automatic and accurate LA segmentation. A contrastive consistency loss function based on the class-vector for learning more distinguishable representations. A classification model based on the class-aware information to improve the performance of segmentation model.