New benchmark and dataset for segmenting brain's Circle of Willis arteries

Researchers have introduced the TopCoW benchmark challenge, accompanied by a new dataset for segmenting the Circle of Willis (CoW) arteries from CT and MR angiography scans. This initiative addresses the challenge of manually characterizing the CoW's complex and variable anatomy, which is crucial for understanding neurovascular diseases. The benchmark includes voxel-level annotations for 13 vessel components, evaluated on internal and external test sets, with top-performing algorithms achieving high accuracy in segmentation and variant classification. AI

IMPACT This benchmark could accelerate the development and clinical adoption of AI algorithms for neurovascular disease risk assessment and diagnosis.

RANK_REASON The cluster describes a new benchmark and dataset for a specific medical imaging task, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• circle of Willis
• computed tomography angiography
• Kaiyuan Yang
• MR angiography
• TopCoW

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →