{"paper":{"title":"Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A landmark-guided method segments subcortical brain structures in MRI by first detecting 16 reference points, producing coarse labels, and then splitting them into 26 precise structures to match manual protocols.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Rekik, Linda Marrakchi-Kacem, R. Jarrett Rushmore, Sylvain Bouix","submitted_at":"2026-05-14T00:31:02Z","abstract_excerpt":"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. Then, a semantic segmentation model produces a coarse segmentation of 12 anatomical "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate consistent improvements in boundary accuracy by integrating learned landmarks that align segmentations more closely with manual protocols.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that automatically detected landmarks can reliably enforce local anatomical constraints to separate coarse labels into distinct structures without errors in varied MRI data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A three-stage pipeline detects 16 landmarks, coarsely segments 12 labels, and refines them into 26 structures using landmark constraints to improve accuracy in subcortical MRI segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A landmark-guided method segments subcortical brain structures in MRI by first detecting 16 reference points, producing coarse labels, and then splitting them into 26 precise structures to match manual protocols.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6ebb3551e1150ff6878e6cc11597443dec5904b7d458f417089736286b67c40c"},"source":{"id":"2605.14221","kind":"arxiv","version":1},"verdict":{"id":"e59e3abe-5621-44d9-a2c3-02f015760399","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:57:21.233740Z","strongest_claim":"Experimental results demonstrate consistent improvements in boundary accuracy by integrating learned landmarks that align segmentations more closely with manual protocols.","one_line_summary":"A three-stage pipeline detects 16 landmarks, coarsely segments 12 labels, and refines them into 26 structures using landmark constraints to improve accuracy in subcortical MRI segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that automatically detected landmarks can reliably enforce local anatomical constraints to separate coarse labels into distinct structures without errors in varied MRI data.","pith_extraction_headline":"A landmark-guided method segments subcortical brain structures in MRI by first detecting 16 reference points, producing coarse labels, and then splitting them into 26 precise structures to match manual protocols."},"references":{"count":17,"sample":[{"doi":"","year":2012,"title":"B. Fischl, “FreeSurfer,”NeuroImage, vol. 62, no. 2, pp. 774–781, 2012","work_id":"faa46249-cab9-4b98-b995-940afdbdc774","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"A Bayesian model of shape and appearance for subcortical brain segmen- tation,","work_id":"473b35b1-70ce-45bb-b958-ac7651bbe4a1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Multi-atlas segmentation of biomedi- cal images: A survey,","work_id":"da847842-67fd-430a-9cca-97ecea992ceb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"U-Net: Convolutional net- works for biomedical image segmentation,","work_id":"902cfa78-cadc-4eda-b2bf-74faa20ce0bd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","work_id":"ffa2ac60-2755-4390-9f66-07815aa6cb27","ref_index":5,"cited_arxiv_id":"2102.04306","is_internal_anchor":true}],"resolved_work":17,"snapshot_sha256":"5cb3de63df1ada775702f9c4f156816077a84fe320bf8311e23f61fbfeece5cd","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}