A Deep-Learning-Based Framework for Automatic Segmentation and Labelling of Intracranial Artery

Yi Lv, Weibin Liao, Wenjin Liu, Zhensen Chen, Xuesong Li

Abstract

Automatic segmentation and labelling of intracranial arteries is important for the clinical diagnosis and research of cerebrovascular disease, but inter-individual differences in intracranial arterial structure pose a serious challenge to automatic processing pipeline. Existing approaches model the arterial labelling task as a centre-line classification problem, neglecting the significance of image-level vessel segmentation and labelling for clinical research. In this paper, we propose a deep learning based automated processing pipeline for joint segmentation and labelling of intracranial arteries, and further again a centre-line vessel type prediction algorithm based on voting model that is capable of obtaining both image-level and centre-line-level arterial labelling results. We used a private dataset containing 167 individual MRA(Magnetic resonance angiography) scans and the public dataset TubeTK for training and testing. The experimental results show that our approach achieves a labelling dice score of 88.3% for 21 intracranial arteries and an average centre-line prediction accuracy of 95%, showing stable and robust results.
BibTeX
@inproceedings{lv2023deep,
  author = {Yi Lv and Weibin Liao and Wenjin Liu and Zhensen Chen and Xuesong Li},
  title = {{A Deep-Learning-Based Framework for Automatic Segmentation and Labelling of Intracranial Artery}},
  booktitle = {ISBI},
  year = {2023},
  doi = {10.1109/isbi53787.2023.10230456},
}

Loading related content...

Figure