[论文解读] Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA
该论文提出 TopCoW 挑战及数据集,用于成对 CTA 和 MRA 图像中 Willis Circle 的拓扑感知多类别分割,在许多组件上报告接近 90% 的 Dice,并分析基于拓扑的度量。
The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neurovascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two non-invasive angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited datasets with annotations on CoW anatomy, especially for CTA. Therefore, we organized the TopCoW challenge with the release of an annotated CoW dataset. The TopCoW dataset is the first public dataset with voxel-level annotations for 13 CoW vessel components, enabled by virtual reality technology. It is also the first large dataset using 200 pairs of MRA and CTA from the same patients. As part of the benchmark, we invited submissions worldwide and attracted over 250 registered participants from six continents. The submissions were evaluated on both internal and external test datasets of 226 scans from over five centers. The top performing teams achieved over 90% Dice scores at segmenting the CoW components, over 80% F1 scores at detecting key CoW components, and over 70% balanced accuracy at classifying CoW variants for nearly all test sets. The best algorithms also showed clinical potential in classifying fetal-type posterior cerebral artery and locating aneurysms with CoW anatomy. TopCoW demonstrated the utility and versatility of CoW segmentation algorithms for a wide range of downstream clinical applications with explainability. The annotated datasets and best performing algorithms have been released as public Zenodo records to foster further methodological development and clinical tool building.
研究动机与目标
- 为 CTA 和 MRA 提供一个公开的体素级注释 Willis 解剖数据集。
- 将 Willis 分割形式化为一个具有拓扑感知评估的多类别任务。
- 评估并基准自动分割方法的全局与拓扑表现。
- 分析跨 MRA 和 CTA 的评审者间一致性与模态特异性一致性。
- 突出开放挑战与 Willis 拓扑感知分析的未来方向。
提出的方法
- 发布带有十三个 Willis 圈血管分量的体素级多类别注释的成对 CTA–MRA 数据集。
- 使用 VR 标注以实现高效的三维标注和临床专家验证。
- 定义 Willis ROI,并在此 ROI 内对两种模态进行分割。
- 使用 Dice、centerline Dice (clDice) 和 Betti-0 误差来评估提交,以捕捉形态和拓扑。
- 在两个模态轨道(CTA 和 MRA)上提供多类别和二进制分割任务。
- 允许外部训练数据,并将模态间和评审间分析作为基准的一部分报告。
实验结果
研究问题
- RQ1自动方法在保持拓扑完整性的前提下,能否在 MRA 和 CTA 中准确分割十三个 Willis 血管组件?
- RQ2体素级分割性能和基于拓扑的度量在模态及变体 Willis 解剖结构之间有何比较?
- RQ3VR 标注中的多类别 Willis 注释的评审者间一致性水平是多少?
- RQ4在自动预测中,Willis 变体拓扑匹配的常见失败模式是什么?
主要发现
- TopCoW 吸引了来自四大洲、27支团队的 146 名注册参与者,其中 18 支团队对最终挑战论文作出贡献。
- TopCoW 训练集包含 90 名患者,验证集 5 名,测试集 35 名,总计 130 个成对 MRA–CTA 案例。
- 对五个测试案例子集的评审者间 Dice 平均约在大多数 13 个类别上超过 90%,但 R-Pcom、L-Pcom、Acom 和 3rd-A2 的分数较低。
- 评审者之间的二值 Dice 平均约为 95%,表明合并后的 Willis 掩模总体一致性较高。
- 模态之间在前部变体上的一致性较高,而在后部变体上更具变异性,因为 CTA 与骨区域接近。
- 在许多血管组件上,表现最好的方法 Dice 约为 90%,但在 communicating 动脉和罕见变体以及拓扑错误方面存在弱点,即使 Dice 较高。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。