EUVIMEDEUVIMED entdecken
Crossref

Contour attention network for cerebrovascular segmentation from TOF‐MRA volumetric images

Chaozhi Yang, Haiyan Zhang, Dianwei Chi, Yachuan Li, Qian Xiao, Yun Bai, Zongmin Li, Hongyi Li, Hua Li

Medical Physics · 2024-03 · 51 (3) · 2020-2031

DOI: 10.1002/mp.16720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 06.09.2023. Verfasst von Chaozhi Yang und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, China University of Petroleum (EastChina), Qingdao, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Algorithms. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, General Research Projects of Beijing Educations Committee in China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cerebrovascular segmentation is a crucial step in the computer‐assisted diagnosis of cerebrovascular pathologies. However, accurate extraction of cerebral vessels from time‐of‐flight magnetic resonance angiography (TOF‐MRA) data is still challenging due to the complex topology and slender shape.

Purpose

The existing deep learning‐based approaches pay more attention to the skeleton and ignore the contour, which limits the segmentation performance of the cerebrovascular structure. We aim to weight the contour of brain vessels in shallow features when concatenating with deep features. It helps to obtain more accurate cerebrovascular details and narrows the semantic gap between multilevel features.

Methods

This work proposes a novel framework for priority extraction of contours in cerebrovascular structures. We first design a neighborhood‐based algorithm to generate the ground truth of the cerebrovascular contour from original annotations, which can introduce useful shape information for the segmentation network. Moreover, We propose an encoder‐dual decoder‐based contour attention network (CA‐Net), which consists of the dilated asymmetry convolution block (DACB) and the Contour Attention Module (CAM). The ancillary decoder uses the DACB to obtain cerebrovascular contour features under the supervision of contour annotations. The CAM transforms these features into a spatial attention map to increase the weight of the contour voxels in main decoder to better restored the vessel contour details.

Results

The CA‐Net is thoroughly validated using two publicly available datasets, and the experimental results demonstrate that our network outperforms the competitors for cerebrovascular segmentation. We achieved the average dice similarity coefficient () of 68.15 and 99.92% in natural and synthetic datasets. Our method segments cerebrovascular structures with better completeness.

Conclusions

We propose a new framework containing contour annotation generation and cerebrovascular segmentation network that better captures the tiny vessels and improve vessel connectivity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingAlgorithmsMagnetic Resonance AngiographyImage Processing, Computer-Assisted

Stichwörter der Autor:innen

3D U-Netcerebrovascular segmentationcontour attention networkone-voxel-thick contour generation

Autor:innen und Institutionen

  • College of Computer Science and Technology, China University of Petroleum (EastChina), Qingdao, China.
  • Weihai Chest Hospital, Weihai, China.
  • School of Artificial Intelligence, Yantai Institute of Technology, Yantai, China.
  • Shengli College of China University of Petroleum, Dongying, China.
  • Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Science, Beijing, China.
  • Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • General Research Projects of Beijing Educations Committee in China
  • Shandong Provincial Natural Science Foundation
  • National Basic Research Program of China
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Yang, C., Zhang, H., Chi, D., Li, Y., Xiao, Q., Bai, Y., Li, Z., Li, H., & Li, H. (2024). Contour attention network for cerebrovascular segmentation from TOF‐MRA volumetric images. Medical Physics, 51(3), 2020-2031. https://doi.org/10.1002/mp.16720

Vancouver

Yang C, Zhang H, Chi D, Li Y, Xiao Q, Bai Y, et al. Contour attention network for cerebrovascular segmentation from TOF‐MRA volumetric images. Medical Physics. 2024;51(3):2020-2031. doi:10.1002/mp.16720

BibTeX
@article{Yang2024,
  author = {Yang, Chaozhi and Zhang, Haiyan and Chi, Dianwei and Li, Yachuan and Xiao, Qian and Bai, Yun and Li, Zongmin and Li, Hongyi and Li, Hua},
  title = {Contour attention network for cerebrovascular segmentation from TOF‐MRA volumetric images},
  journal = {Medical Physics},
  year = {2024},
  volume = {51},
  number = {3},
  pages = {2020--2031},
  doi = {10.1002/mp.16720}
}
Kostenlos starten →