SOURCE-LINKED INTELLIGENCE

Improving Cross-Site Whole-Heart Segmentation

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Whole-heart segmentation from CT and MRI is essential for quantitative cardiac image analysis, but remains challenging under multi-center and multi-modality distribution shift. In the CARE whole-heart segmentation task, models must generalize from limited labeled sites to unseen acquisition distributions, where variation in spacing, intensity, reconstruction texture, and anatomy can degrade out-of-distribution performance. We propose a modality-routed 3D cardiac segmentation pipeline that combines TotalSegmentator-initialized nnU-Netv2 models with site-characterized, label-preserving appearanc

Read original source ↗ Open in workspace

recordType

paper

region

Global