arXiv · 2611.13884
Region-Wise Logit Fusion and Utility-Gated Refinement for Brain Metastasis Segmentation
Abstract
BraTS-METS 2026 Task 1 evaluates segmentation of brain metastases and postoperative resection cavities on heterogeneous multiparametric MRI, requiring detection of small enhancing foci while preserving the geometry and hierarchy of enhancing tumor (ET), tumor core (TC), whole tumor (WT), and resection cavity (RC). We present COMPASS-METS (Component-Aware Multi-Trainer Probability Assembly with Structured Segmentation), which combines three five-fold nnU-Net configurations into aligned regional probability ensembles. A structured-probability anchor applies region-specific component decisions, TC boundary completion, RC filtering, and hierarchy-preserving conversion. Omitted ET candidates are recovered additively using learned component confidence and deterministic multi-trainer support for ET and its TC/WT parents; a final utility gate admits only disconnected candidates with sufficient lesion-existence and geometry-safety probabilities. On the reused 179-case challenge development cohort, COMPASS-METS (Team: MicroBT) achieved Small F1 0.354, lesion-wise DSC 0.712, NSD 0.714, All F1 0.779, and HD95 56.6 mm. Relative to ResEncXL, it improved DSC, NSD, and All F1 and reduced HD95, while Small F1 changed from 0.367 to 0.354. Stagewise analysis attributes the principal geometric gains to structured probability construction and shows that guarded ET refinement recovers most of the associated small-lesion detection loss. These 179-case results remain selection-aware development estimates. The source code is publicly available at https://github.com/leonlou921/COMPASS-METS.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Zhenye Lou, Qing Xu, Wenting Duan, Zhen Chen. 2026-11-10. Region-Wise Logit Fusion and Utility-Gated Refinement for Brain Metastasis Segmentation. https://searcharxiv.com/abs/2611.13884
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.