MHAHF-UNet: a multi-scale hybrid attention hierarchy fusion network for carotid artery segmentation
International Journal of Computer Assisted Radiology and Surgery · 2025
DOI: 10.1007/s11548-025-03449-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Changshuo Jiang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Chengdu University of Information Technology, Chengdu, 610225, China. Hauptthemen laut MEDLINE: Carotid Arteries, Carotid Artery Diseases, Plaque, Atherosclerotic, Image Interpretation, Computer-Assisted. Die Arbeit nennt 33 Literaturangaben. Gefördert von: Medical Image Post-processing ù Research on Key Technologies of Intelligent Image Registration, Supported by the Natural Science Foundation of Sichuan Province….
Abstract (Originalsprache)
PURPOSE: Carotid plaque is an early manifestation of carotid atherosclerosis, and its accurate segmentation helps to assess cardiovascular disease risk. However, existing carotid artery segmentation algorithms are difficult to accurately capture the structural features of morphologically diverse plaques and lack effective utilization of multilayer features. METHODS: In order to solve the above problems, this paper proposes a multi-scale hybrid attention hierarchical fusion U-network structure (MHAHF-UNet) for segmenting ambiguous plaques in carotid artery images in order to improve the segmentation accuracy for complex structured images. The structure firstly introduces the median-enhanced orthogonal convolution module (MEOConv), which not only effectively suppresses the noise interference in ultrasound images, but also maintains the ability to perceive multi-scale features by combining the median-enhanced ternary channel mechanism and the depth-orthogonal convolution space mechanism. Secondly, it adopts the multi-fusion group convolutional gating module, which realizes the effective integration of shallow detailed features and deep semantic features through the adaptive control strategy of group convolution, and is able to flexibly regulate the transfer weights of features at different levels. RESULTS: Experiments show that the MHAHF-UNet model achieves a Dice coefficient of 82.46 ± 0.31 % and an IOU of 71.45 ± 0.37 % in the carotid artery segmentation task. CONCLUSION: The model is expected to provide strong support for the prevention and treatment of cardiovascular diseases.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Chengdu University of Information Technology, Chengdu, 610225, China.
- The Affiliated Hospital of Panzhihua University, Panzhihua, 617000, China. 3270155343@qq.com.
- The Affiliated Hospital of Panzhihua University, Panzhihua, 617000, China.
Förderung
- Medical Image Post-processing ù Research on Key Technologies of Intelligent Image Registration, Supported by the Natural Science Foundation of Sichuan Province…
Zitieren
APA
Jiang, C., Gao, L., Li, W., Zou, M., Zheng, Q., & Qiao, X. (2025). MHAHF-UNet: a multi-scale hybrid attention hierarchy fusion network for carotid artery segmentation. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-025-03449-3
Vancouver
Jiang C, Gao L, Li W, Zou M, Zheng Q, Qiao X. MHAHF-UNet: a multi-scale hybrid attention hierarchy fusion network for carotid artery segmentation. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-025-03449-3
BibTeX
@article{Jiang2025,
author = {Jiang, Changshuo and Gao, Lin and Li, Wei and Zou, Maoyang and Zheng, Qingxiao and Qiao, Xuhua},
title = {MHAHF-UNet: a multi-scale hybrid attention hierarchy fusion network for carotid artery segmentation},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2025},
doi = {10.1007/s11548-025-03449-3}
}
EUVIMED