AI RESEARCH

Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI

arXiv CS.CV

ArXi:2604.08015v1 Announce Type: new We propose a unified objective function, termed CATMIL, that augments the base segmentation loss with two auxiliary supervision terms operating at different levels. The first term, Component-Adaptive Tversky, reweights voxel contributions based on connected components to balance the influence of lesions of different sizes. The second term, based on Multiple Instance Learning,