计算机科学
对偶(语法数字)
分割
人工智能
艺术
文学类
作者
Jiapeng Zhang,Yongxiong Wang,Lijun Chen,Jinlong Liu,Sunjie Zhang,Zhiqun Pan,Zhe Wang,Zhenhui Tang,Ying Guo
出处
期刊:IEEE Transactions on Industrial Informatics
[Institute of Electrical and Electronics Engineers]
日期:2023-12-01
卷期号:19 (12): 11675-11686
被引量:1
标识
DOI:10.1109/tii.2023.3249904
摘要
Segmentation of left and right ventricles from 3-D echocardiographic images is premised and key for the quantitative analysis of cardiac function, which is important for pediatric cardiac diagnosis. Compared with 2-D echocardiography, 3-D echocardiography can fully represent a ventricular structure without geometric inference. However, it usually takes experts several hours to obtain a 3-D segmentation mask of the left and right ventricles. Therefore, a fast and automatic segmentation method is highly desired. Unfortunately, 3-D echocardiography suffers from low contrast, unclear left and right ventricles borders, and blind zone. Existing segmentation methods usually have poor performance at ventricular boundaries. To deal with these problems, we propose a novel dual-branch TransV-Net (DBTV). DBTV comprises two parallel, interleaved, and relatively independent V-shaped encoder窶電ecoder branches. The main branch acts on the original data to extract image features, and the auxiliary branch acts on edge maps to extract the additional edge features. To suppress noise and enhance the edge information, extra concatenations are added to bridge the features from the main and auxiliary branches. To reduce object missing caused by blind zone, a 3-D transformer-based module is proposed in the bottom layer of the dual-branch structure to extract the global contexts. We do experiments on a self-collected dataset with 120 3-D echocardiographic images from 60 cardiac sequences, and the dice scores of 0.913 and 0.880 are obtained in the left and right ventricle segments, respectively. Each inference takes about two-thirds of a second for a single 3-D frame.
科研通智能强力驱动
Strongly Powered by AbleSci AI