An improved contrastive learning network for semi-supervised multi-structure segmentation in echocardiography

Abstract

Cardiac diseases have high mortality rates and are a significant threat to human health. Echocardiography is a commonly used imaging technique to diagnose cardiac diseases because of its portability, non-invasiveness and low cost. Precise segmentation of basic cardiac structures is crucial for cardiologists to efficiently diagnose cardiac diseases, but this task is challenging due to several reasons, such as: (1) low image contrast, (2) incomplete structures of cardiac, and (3) unclear border between the ventricle and the atrium in some echocardiographic images. In this paper, we applied contrastive learning strategy and proposed a semi-supervised method for echocardiographic images segmentation. This proposed method solved the above challenges effectively and made use of unlabeled data to achieve a great performance, which could help doctors improve the accuracy of CVD diagnosis and screening. We evaluated this method on a public dataset (CAMUS), achieving mean Dice Similarity Coefficient (DSC) of 0.898, 0.911, 0.916 with 1/4, 1/2 and full labeled data on two-chamber (2CH) echocardiography images, and of 0.903, 0.921, 0.928 with 1/4, 1/2 and full labeled data on four-chamber (4CH) echocardiography images. Compared with other existing methods, the proposed method had fewer parameters and better performance. The code and models are available at https://github.com/gpgzy/CL-Cardiac-segmentation.