{"id":"W3092442943","doi":"10.1002/mrm.28547","title":"BISON: Brain tissue segmentation pipeline using T <sub>1</sub> ‐weighted magnetic resonance images and a random forest classifier","year":2020,"lang":"en","type":"article","venue":"Magnetic Resonance in Medicine","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Canadian Institutes of Health Research","keywords":"Segmentation; Random forest; Magnetic resonance imaging; Artificial intelligence; Hyperintensity; White matter; Computer science; Image segmentation; Pattern recognition (psychology); Kappa; Nuclear medicine; Medicine; Radiology; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009044909,0.0003971981,0.0006505208,0.0002759651,0.0001195434,0.0001103187,0.0006896175,0.0001510775,0.0001543401],"category_scores_gemma":[0.0009981222,0.0003465605,0.00004066502,0.001385791,0.0005943672,0.0005139909,0.0002740099,0.0004294639,0.00001983735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008566771,"about_ca_system_score_gemma":0.00009378111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000114979,"about_ca_topic_score_gemma":0.00004261591,"domain_scores_codex":[0.9961352,0.000384693,0.0009954118,0.0009845347,0.0009301875,0.0005699475],"domain_scores_gemma":[0.9981919,0.0005442258,0.0002214627,0.0005223153,0.0001502802,0.0003698198],"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":[0.0001023905,0.00004346366,0.001499959,0.00008912904,0.000001448338,0.0002151917,0.001207875,0.000005233998,0.1766919,0.0001071969,0.01304543,0.8069908],"study_design_scores_gemma":[0.02505611,0.004459511,0.05515536,0.002118912,0.00009039274,0.0002488928,0.0006280176,0.5687848,0.2963926,0.004143647,0.04132029,0.001601441],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06668939,0.05700729,0.845046,0.02857025,0.0002716699,0.001618119,0.00001045353,0.0003557368,0.0004311221],"genre_scores_gemma":[0.3280237,0.01348014,0.6154329,0.03950111,0.001511264,0.0005855603,0.00007701218,0.0001829969,0.001205259],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8053893,"threshold_uncertainty_score":0.9998986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02346908784418475,"score_gpt":0.2960747590620479,"score_spread":0.2726056712178632,"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."}}