Shear wave trajectory detection in ultra-fast M-mode images for liver fibrosis assessment: A deep learning-based line detection approach

• Published in: Ultrasonics 2024-08, Vol.142, p.107358, Article 107358
• Main Authors: Wang, Xinyi, Liu, Bo, Wu, Chonglin, Huang, Zihao, Zhou, Yongjin, Wu, Xiaoming, Zheng, Yongping
• Format: Article
• Language: English
• Subjects: Deep learning; Line detection; Liver fibrosis; Transformer; Transient ultrasound elastography
• ISSN: 0041-624X; 1874-9968; 1874-9968
• DOI: 10.1016/j.ultras.2024.107358

•Stiffness measurement via shear wave propagation velocity is a common noninvasive method for liver fibrosis assessment.•Detecting shear wave trajectory is challenging due to noise.•We developed a deep learning-based approach for detecting wave propagation trace in liver fibrosis assessment.•We propose a domain-specific framework and a tailored evaluation metric by considering the characteristic of this task.•Extensive experiments demonstrate the superior performance of our approach compared to state-of-the-art methods.•The study provides a novel baseline in using deep learning for shear wave trajectory detection in liver fibrosis assessment. Stiffness measurement using shear wave propagation velocity has been the most common non-invasive method for liver fibrosis assessment. The velocity is captured through a trace recorded by transient ultrasonographic elastography, with the slope indicating the velocity of the wave. However, due to various factors such as noise and shear wave attenuation, detecting shear wave trajectory on wave propagation maps is a challenging task. In this work, we made the first attempt to use deep learning methods for shear wave trajectory detection on wave propagation maps. Specifically, we adopted five deep learning models in this task and evaluated them by using a well-acknowledged metric based on EA-Angular-Score (EAA) and task-specific metric based on Young s-Score (Ys) in the line-detection field. Furthermore, we proposed an end-to-end framework based on a Transformer and Hough transform, named Transformer-enhanced Hough Transform (TEHT). It took a wave propagation map as input image and directly output the slope of the shear wave trajectory. The framework extracts multi-scale local features from wave propagation maps, employs a deformable attention mechanism for feature fusion, identifies the target line using the Hough transform’s voting mechanism, and calculates the contribution of each scale through channel attention. Wave propagation maps from 68 patients were utilized in this study, with manual annotation performed by a rater who was trained as a radiologist, serving as the reference value. The evaluation revealed that the SLNet model exhibited F-measure of EA and Ys values as 40.33 % and 40.72 %, respectively, while the TEHT model showed F-measure of EA and Ys values as 80.96 % and 98.00 %, respectively. TEHT yielded significantly better performance than other deep learning models. Moreover, TEHT demonstrated strong con