Dual attention enhancement feature fusion network for segmentation and quantitative analysis of paediatric echocardiography
| Autor: | Cheng Zhao, Jing Qin, Bei Xia, Jie Du, Tianfu Wang, Alejandro F. Frangi, Weiling Chen, Baiying Lei, Libao Guo, Pengpeng Shi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Channel (digital image)
Computer science Feature extraction Health Informatics 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Humans Radiology Nuclear Medicine and imaging Segmentation Child Feature fusion Radiological and Ultrasound Technology business.industry Pattern recognition Speckle noise DUAL (cognitive architecture) Computer Graphics and Computer-Aided Design Semantics Quantitative analysis (finance) Echocardiography Key (cryptography) Computer Vision and Pattern Recognition Artificial intelligence Artifacts business 030217 neurology & neurosurgery |
| ISSN: | 1361-8415 |
| Popis: | Paediatric echocardiography is a standard method for screening congenital heart disease (CHD). The segmentation of paediatric echocardiography is essential for subsequent extraction of clinical parameters and interventional planning. However, it remains a challenging task due to (1) the considerable variation of key anatomic structures, (2) the poor lateral resolution affecting accurate boundary definition, (3) the existence of speckle noise and artefacts in echocardiographic images. In this paper, we propose a novel deep network to address these challenges comprehensively. We first present a dual-path feature extraction module (DP-FEM) to extract rich features via a channel attention mechanism. A high- and low-level feature fusion module (HL-FFM) is devised based on spatial attention, which selectively fuses rich semantic information from high-level features with spatial cues from low-level features. In addition, a hybrid loss is designed to deal with pixel-level misalignment and boundary ambiguities. Based on the segmentation results, we derive key clinical parameters for diagnosis and treatment planning. We extensively evaluate the proposed method on 4,485 two-dimensional (2D) paediatric echocardiograms from 127 echocardiographic videos. The proposed method consistently achieves better segmentation performance than other state-of-the-art methods, whichdemonstratesfeasibility for automatic segmentation and quantitative analysis of paediatric echocardiography. Our code is publicly available at https://github.com/end-of-the-century/Cardiac. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect