Boundary attention with multi-task consistency constraints for semi-supervised 2D echocardiography segmentation

作者全名："Zhao, Yiyang; Liao, Kangla; Zheng, Yineng; Zhou, Xiaoli; Guo, Xingming"

作者地址："[Zhao, Yiyang; Zhou, Xiaoli; Guo, Xingming] Chongqing Univ, Coll Bioengn, Key Lab Biorheol Sci & Technol, Minist Educ, Chongqing 400044, Peoples R China; [Liao, Kangla] Chongqing Med Univ, Dept Cardiol, Affiliated Hosp 1, Chongqing 400016, Peoples R China; [Zheng, Yineng] Chongqing Med Univ, Dept Radiol, Affiliated Hosp 1, Chongqing 400016, Peoples R China; [Guo, Xingming] 174 Shazheng St, Chongqing 400044, Peoples R China"

通信作者："Liao, KL (通讯作者)，Chongqing Med Univ, Dept Cardiol, Affiliated Hosp 1, Chongqing 400016, Peoples R China.; Guo, XM (通讯作者)，174 Shazheng St, Chongqing 400044, Peoples R China."

来源：COMPUTERS IN BIOLOGY AND MEDICINE

ESI学科分类：COMPUTER SCIENCE

WOS号：WOS:001181733400001

JCR分区：Q1

影响因子：7

年份：2024

卷号：171

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Echocardiography semantic segmentation; Semi -supervised learning; Multi -task consistency constraints; Boundary attention module; Self -attention mechanism

摘要："The 2D echocardiography semantic automatic segmentation technique is important in clinical applications for cardiac function assessment and diagnosis of cardiac diseases. However, automatic segmentation of 2D echocardiograms also faces the problems of loss of image boundary information, loss of image localization information, and limitations in data acquisition and annotation. To address these issues, this paper proposes a semisupervised echocardiography segmentation method. It consists of two models: (1) a boundary attention transformer net (BATNet) and (2) a multi-task level semi-supervised model with consistency constraints on boundary features (semi-BATNet). BATNet is able to capture the location and spatial information of the input feature maps by using the self-attention mechanism. The multi-task level semi-supervised model with boundary feature consistency constraints (semi-BATNet) encourages consistent predictions of boundary features at different scales from the student and teacher networks to calculate the multi-scale consistency loss for unlabeled data. The proposed semi-BATNet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and self-collected echocardiography dataset from the First Affiliated Hospital of Chongqing Medical University. Experimental results on the CAMUS dataset showed that when only 25% of the images are labeled, the proposed method greatly improved the segmentation performance by utilizing unlabeled images, and it also outperformed five state-of-the-art semi-supervised segmentation methods. Moreover, when only 50% of the images labeled, semi-BATNet achieved the Dice coefficient values of 0.936, the Jaccard similarity of 0.881 on self-collected echocardiography dataset. Semi-BATNet can complete a more accurate segmentation of cardiac structures in 2D echocardiograms, indicating that it has the potential to accurately and efficiently assist cardiologists."

基金机构：National Natural Science Foundation of China [31870980]

基金资助正文：This study was supported by the National Natural Science Foundation of China [Grant No. 31870980] . The authors would like to acknowledge the First Affiliated Hospital of Chongqing Medical University in building the self-collected dataset.