SOURCE-LINKED INTELLIGENCE

Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation

arXiv · AI, language, vision and robotics · article · Aug 24, 2026 · UTC

Segmenting ischemic stroke lesions on T1-weighted (T1w) MRI acquired across different scanners and protocols without intensity standardization is difficult because lesions are subtle and share intensity characteristics with cerebrospinal fluid. Standard deep learning architectures trained across multiple centers plateau around Dice 0.66, with acute lesions ($\le 7$ days post-stroke) performing substantially worse due to severe sample scarcity. We combine a MedNeXt-L ($k=5$) backbone with on-the-fly 3D CarveMix augmentation that pastes real lesion patches into healthy brain regions during train

Read original source ↗ Open in workspace

recordType

paper

region

Global