{"id":"W2762747243","doi":"10.1016/j.nicl.2017.10.015","title":"Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiple sclerosis patients and healthy controls","year":2017,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Multiple Sclerosis Society; Natural Sciences and Engineering Research Council of Canada; Multiple Sclerosis Society of Canada","keywords":"Myelin; Multiple sclerosis; Artificial intelligence; Pattern recognition (psychology); Magnetic resonance imaging; Voxel; Computer science; Feature (linguistics); Feature selection; White matter; Pathology; Neuroscience; Medicine; Psychology; Radiology; Central nervous system","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00166983,0.0002216809,0.0009813951,0.0001455054,0.0003582951,0.0001033541,0.000191301,0.0001383975,0.00000733827],"category_scores_gemma":[0.05887754,0.0002006524,0.00008675905,0.00007897914,0.0004929979,0.0001238233,0.0008506706,0.0009546683,0.000006673551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002833084,"about_ca_system_score_gemma":0.00003324173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005463553,"about_ca_topic_score_gemma":0.0003563003,"domain_scores_codex":[0.9970889,0.0003773362,0.0009290009,0.0006837615,0.0004146212,0.0005063511],"domain_scores_gemma":[0.9961039,0.002358886,0.0003443357,0.0005027829,0.0002122513,0.0004777937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004841271,0.0001492223,0.8867734,0.0001464535,0.00002747761,0.000015795,0.0002980091,0.000005247016,0.00277409,0.00000152895,0.0003282303,0.1089964],"study_design_scores_gemma":[0.006971952,0.001683158,0.9888035,0.0003481912,0.00002669944,0.000001489749,0.00005803489,0.0008157488,0.0002690322,0.000003890252,0.0008729575,0.0001453642],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919935,0.0001742991,0.000111793,0.006285405,0.00010958,0.0009978603,0.00002234753,0.00003112257,0.0002741143],"genre_scores_gemma":[0.9967721,0.0005888309,0.001533167,0.0006409276,0.000309257,0.00002640891,0.00001153133,0.00003597032,0.00008184396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.108851,"threshold_uncertainty_score":0.9490499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1327475426950027,"score_gpt":0.4123054765384498,"score_spread":0.2795579338434472,"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."}}