{"id":"W4408560758","doi":"10.1162/imag_a_00526","title":"Microstructure-informed brain tissue classification using clustering of quantitative MRI measures","year":2025,"lang":"en","type":"article","venue":"Imaging Neuroscience","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Philips (Canada); International Collaboration On Repair Discoveries; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Multiple Sclerosis Society of Canada; Canadian Institutes of Health Research; Biogen; Sanofi","keywords":"White matter; Magnetic resonance imaging; Voxel; Brain tissue; Fractional anisotropy; Cluster analysis; Multiple sclerosis; Pathology; Segmentation; Medicine; Diffusion MRI; Pathological; Artificial intelligence; Computer science; Pattern recognition (psychology); Radiology; Biomedical engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000122833,0.0001126621,0.0001666106,0.000203603,0.0001523295,0.0000323033,0.0001938263,0.00001932296,0.000001702411],"category_scores_gemma":[0.0005148268,0.0001076271,0.00003774127,0.000670156,0.0003613661,0.0001891095,0.00008574384,0.0001393848,7.536713e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000058703,"about_ca_system_score_gemma":0.000160804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002344252,"about_ca_topic_score_gemma":0.000001861303,"domain_scores_codex":[0.999006,0.00002104998,0.0002679068,0.0003332018,0.0001804308,0.000191389],"domain_scores_gemma":[0.9992203,0.00009672965,0.000139736,0.0003636077,0.0001330663,0.00004661567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001656827,0.0000200021,0.005170281,0.00005114807,9.318558e-7,0.000003079118,0.00006891516,0.000253186,0.9866523,0.002449896,0.0003450197,0.004968725],"study_design_scores_gemma":[0.000651855,0.00009169767,0.1388596,0.0004623278,0.00005545124,0.0001939485,0.0001876976,0.3213259,0.4964504,0.002385015,0.03906494,0.0002712512],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04587569,0.00009277085,0.9453477,0.006562771,0.0001946549,0.0004546103,0.00001078593,0.0001718732,0.001289199],"genre_scores_gemma":[0.913853,0.00002756031,0.08366948,0.002190923,0.00001054973,0.0000122758,0.000002417971,0.0000120828,0.0002216811],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8679773,"threshold_uncertainty_score":0.4388906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.119661480073597,"score_gpt":0.4527645983547297,"score_spread":0.3331031182811326,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}