{"id":"W2340846151","doi":"10.1016/j.jalz.2015.06.344","title":"P1‐146: Accurate automatic segmentation of white matter hyperintensities using a linear regression classifier","year":2015,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Neurological Disease Mechanisms and Treatments","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Douglas Mental Health University Institute; McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Fluid-attenuated inversion recovery; Hyperintensity; Segmentation; Thresholding; Artificial intelligence; Pattern recognition (psychology); Voxel; Gold standard (test); Kappa; Dementia; Nuclear medicine; Computer science; Medicine; Magnetic resonance imaging; Mathematics; Radiology; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002318727,0.001604544,0.001514265,0.001518019,0.0006740395,0.001704409,0.002052124,0.002121147,0.005592547],"category_scores_gemma":[0.004496123,0.0006219776,0.00108499,0.001021954,0.0003510008,0.001275891,0.0009292677,0.001501664,0.006724222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006695103,"about_ca_system_score_gemma":0.001686927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006971315,"about_ca_topic_score_gemma":0.006046588,"domain_scores_codex":[0.9985526,0.0002024657,0.0000982449,0.0006034779,0.0003488832,0.0001942844],"domain_scores_gemma":[0.9988417,0.0003374426,0.0001126892,0.0001446467,0.0005112232,0.00005245515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009070335,0.0006106845,0.006922764,0.0002240281,0.0002174662,0.0003956505,0.0001004834,0.04104556,0.07141872,0.001245866,0.02332422,0.8535876],"study_design_scores_gemma":[0.00005213003,0.0001825423,0.005401779,0.00002741888,0.00005196053,0.0003094081,0.00003232983,0.9540315,0.03492974,0.0007446393,0.004204018,0.00003253937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1123939,0.0008521187,0.8553997,0.0003789051,0.0002268416,0.0005718688,0.001862553,0.02350577,0.004808437],"genre_scores_gemma":[0.3700054,0.0003957873,0.6038799,0.0003487379,0.0001805402,0.0006843961,0.007065715,0.001118475,0.01632107],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006971315,"threshold_uncertainty_score":0.01870894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1367437594750919,"score_gpt":0.3273889262871021,"score_spread":0.1906451668120102,"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."}}