A dual-modal dynamic contour-based method for cervical vascular ultrasound image instance segmentation
-
Published:2023
Issue:1
Volume:21
Page:1038-1057
-
ISSN:1551-0018
-
Container-title:Mathematical Biosciences and Engineering
-
language:
-
Short-container-title:MBE
Author:
Chang Chenkai1, Qi Fei2, Xu Chang1, Shen Yiwei1, Li Qingwu1
Affiliation:
1. College of Information Science and Engineering, Hohai University, Changzhou 213200, Jiangsu, China 2. Changzhou No.2 People's Hospital, No.29 Xinglong Lane, Changzhou 213004, Jiangsu, China
Abstract
<abstract><p><italic>Objectives:</italic> We intend to develop a dual-modal dynamic contour-based instance segmentation method that is based on carotid artery and jugular vein ultrasound and its optical flow image, then we evaluate its performance in comparison with the classic single-modal deep learning networks. <italic>Method:</italic> We collected 2432 carotid artery and jugular vein ultrasound images and divided them into training, validation and test dataset by the ratio of 8:1:1. We then used these ultrasound images to generate optical flow images with clearly defined contours. We also proposed a dual-stream information fusion module to fuse complementary features between different levels extracted from ultrasound and optical flow images. In addition, we proposed a learnable contour initialization method that eliminated the need for manual design of the initial contour, facilitating the rapid regression of nodes on the contour to the ground truth points. <italic>Results:</italic> We verified our method by using a self-built dataset of carotid artery and jugular vein ultrasound images. The quantitative metrics demonstrated a bounding box detection mean average precision of 0.814 and a mask segmentation mean average precision of 0.842. Qualitative analysis of our results showed that our method achieved smoother segmentation boundaries for blood vessels. <italic>Conclusions:</italic> The dual-modal network we proposed effectively utilizes the complementary features of ultrasound and optical flow images. Compared to traditional single-modal instance segmentation methods, our approach more accurately segments the carotid artery and jugular vein in ultrasound images, demonstrating its potential for reliable and precise medical image analysis.</p></abstract>
Publisher
American Institute of Mathematical Sciences (AIMS)
Subject
Applied Mathematics,Computational Mathematics,General Agricultural and Biological Sciences,Modeling and Simulation,General Medicine
Reference57 articles.
1. S. Wang, M. E. Celebi, Y. D. Zhang, X. Yu, S. Lu, X. Yao, et al., Advances in data preprocessing for biomedical data fusion: An overview of the methods, challenges, and prospects, Inf. Fusion, 76 (2021), 376–421. https://doi.org/10.1016/j.inffus.2021.07.001 2. C. Fournil, N. Boulet, S. Bastide, B. Louart, A. Ambert, C. Boutin, et al., High success rates of ultrasound-guided distal internal jugular vein and axillary vein approaches for central venous catheterization: A randomized controlled open-label pilot trial, J. Clin. Ultrasound, 51 (2023), 158–166. https://doi.org/10.1002/jcu.23383 3. W. Choi, B. Park, S. Choi, D. Oh, J. Kim, C. Kim, Recent advances in contrast-enhanced photoacoustic imaging: Overcoming the physical and practical challenges, Chem. Rev., 123 (2023), 7379–7419. https://doi.org/10.1021/acs.chemrev.2c00627 4. L. Wang, J. Bai, J. Jin, K. Zhi, S. Nie, L. Qu, Treatment of inadvertent cervical arterial catheterization: Single-center experience, Vascular, 31 (2023), 791–798. https://doi.org/10.1177/17085381221083161 5. L. A. Groves, B. VanBerlo, N. Veinberg, A. Alboog, T. M. Peters, E. C. Chen, Automatic segmentation of the carotid artery and internal jugular vein from 2D ultrasound images for 3D vascular reconstruction, Int. J. Comput. Assisted Radiol. Surg., 15 (2020), 1835–1846. https://doi.org/10.1007/s11548-020-02248-2
|
|