annotation of vessels for 271 TOF-MRA volumes

We manually annotated 271 (healthy : pathological = 150 : 121) TOF-MRA volumes, including 28,128 slices. This annotated dataset, named CereVessMRA, supports the development of deep learning methods for cerebrovascular segmentation (please also refer to our work: https://github.com/YingChen7/HQA_Cerebrovasculature/blob/data/2_CereVessSeg_CereVessPro/README.md). The 150 annotated healthy TOF-MRA volumes from UK subjects were sourced from three different institutions, as part of the UK-Hset. The 121 annotated pathological TOF-MRA volumes from Chinese subjects were provided by Datian General Hospital in Fujian Province, China. This large-scale and multi-center cerebral arterial annotation dataset facilitated the development of generalizable deep learning models for automatic and precise cerebral arterial segmentation.If you use this dataset, please cite following paper:Guo, B., Chen, Y., Lin, J. et al. Self-supervised learning for accurately modelling hierarchical evolutionary patterns of cerebrovasculature. Nat Commun 15, 9235 (2024). https://doi.org/10.1038/s41467-024-53550-5

本团队人工标注了271例TOF-MRA（Time-of-Flight Magnetic Resonance Angiography，时间飞跃法磁共振血管成像）容积数据，其中健康组与病变组的比例为150:121，共计包含28128层切片。
本标注数据集命名为CereVessMRA，可支撑脑血管分割相关深度学习方法的研发，具体可参考我们的研究工作：https://github.com/YingChen7/HQA_Cerebrovasculature/blob/data/2_CereVessSeg_CereVessPro/README.md。
150例来自英国受试者的健康TOF-MRA容积标注数据来源于三家不同机构，属于UK-Hset数据集的一部分。
121例来自中国受试者的病变TOF-MRA容积标注数据由中国福建省大田总医院提供。
本大规模多中心脑动脉标注数据集，可推动可泛化的自动精准脑动脉分割深度学习模型的研发。
若使用本数据集，请引用以下论文：Guo, B., Chen, Y., Lin, J. 等. 用于精准建模脑血管层级演化模式的自监督学习方法. 《自然·通讯》（Nature Communications）, 15, 9235 (2024). https://doi.org/10.1038/s41467-024-53550-5

搜集汇总

背景与挑战

背景概述

该数据集包含271个TOF-MRA体积的手动注释，支持脑血管分割的深度学习研究，数据来源于多个中心，包括健康与病理样本。