{"id":"W4390722060","doi":"10.1101/2024.01.03.24300794","title":"SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Spinal Cord Injury Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; HORIZON EUROPE Framework Programme; Canada First Research Excellence Fund; National Institutes of Health; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Institut pour la Recherche sur la Moelle épinière et l'Encéphale; Craig H. Neilsen Foundation; Boettcher Foundation; Ministerstvo Zdravotnictví Ceské Republiky; Institut de Valorisation des Données; European Commission","keywords":"Intramedullary rod; Spinal cord injury; Segmentation; Medicine; Spinal cord; Cord; Computer science; Artificial intelligence; Anatomy; Surgery","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":[0.001000282,0.0003737807,0.0008491225,0.001426545,0.00003909906,0.000045516,0.0003962138,0.0004002561,0.0006008464],"category_scores_gemma":[0.0004246752,0.0003340486,0.0002308782,0.001044514,0.0002419977,0.00005038107,0.001041018,0.00210924,0.0002505757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004290876,"about_ca_system_score_gemma":0.00111163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001745672,"about_ca_topic_score_gemma":0.00002794593,"domain_scores_codex":[0.9965267,0.0002159939,0.001013151,0.0007063102,0.001087055,0.0004507439],"domain_scores_gemma":[0.998324,0.00009561165,0.0002290357,0.0008582408,0.000259523,0.0002336281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.014347,0.001358118,0.08373874,0.02300582,0.0006138783,0.001669712,0.0004719497,0.000008500971,0.1398029,0.0007516317,0.004366508,0.7298653],"study_design_scores_gemma":[0.002863763,0.02148787,0.7788032,0.02927917,0.001168109,0.0002634033,0.0008547727,0.02075098,0.1207453,0.02150419,0.0008797892,0.001399491],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930547,0.001528992,0.00009563974,0.00156787,0.0008795737,0.001581726,0.00005584267,0.0001670192,0.001068612],"genre_scores_gemma":[0.9931298,0.0003582804,0.005261725,0.0001210217,0.0002180835,0.0002418833,0.0001286011,0.00008112909,0.0004594967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7284657,"threshold_uncertainty_score":0.9999111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06139885595236808,"score_gpt":0.4179001335150021,"score_spread":0.356501277562634,"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."}}