AI RESEARCH

Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI

arXiv CS.CV

ArXi:2605.14221v1 Announce Type: new Precise segmentation of brain structures in magnetic resonance imaging (MRI) is essential for reliable neuroimaging analysis, yet voxel-wise deep models often yield anatomically inconsistent results that diverge from expert-defined boundaries. In this research, we propose a landmark-guided 3D brain segmentation approach that explicitly mimics the manual segmentation protocol of the Harvard--Oxford Atlas. A Global-to-Local network automatically detects 16 landmarks representing key subcortical reference points.