{"id":"W4404107931","doi":"10.1148/ryai.240005","title":"SCIseg: Automatic Segmentation of Intramedullary Lesions in Spinal Cord Injury on T2-weighted MRI Scans","year":2024,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"National Institute of Neurological Disorders and Stroke; Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; HORIZON EUROPE Framework Programme; Alliance de recherche numérique du Canada; Institut pour la Recherche sur la Moelle épinière et l'Encéphale; Boettcher Foundation; Ministerstvo Zdravotnictví Ceské Republiky; Institut de Valorisation des Données; Eunice Kennedy Shriver National Institute of Child Health and Human Development; European Commission; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Canada First Research Excellence Fund; Canada Research Chairs; Craig H. Neilsen Foundation; Canadian Institutes of Health Research; National Science Foundation","keywords":"Medicine; Lesion; Spinal cord; Intramedullary rod; Magnetic resonance imaging; Sagittal plane; Radiology; Spinal cord injury; Segmentation; Cord; Lumbar; Surgery; Artificial intelligence; Computer science","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":[0.0003274202,0.0001398738,0.0002633813,0.0004156384,0.00003818527,0.00002109866,0.000159068,0.00011222,0.0003656032],"category_scores_gemma":[0.0000930524,0.0001282739,0.00007273059,0.0006958295,0.0002120319,0.00007142434,0.00001517797,0.0003373222,0.0002037808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008459223,"about_ca_system_score_gemma":0.00004480534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003250696,"about_ca_topic_score_gemma":0.00001871219,"domain_scores_codex":[0.9987766,0.0000864105,0.0005194793,0.0002310451,0.0001435402,0.0002429671],"domain_scores_gemma":[0.9995089,0.0001945926,0.00002951544,0.0001683136,0.00002211187,0.00007663202],"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":[0.00004650227,0.00006210506,0.0001595424,0.0001690288,0.0000702972,0.00006061336,0.0003141685,0.009522492,0.01397613,0.007288631,0.000812409,0.9675181],"study_design_scores_gemma":[0.00001537267,0.000286917,0.0003194644,0.0004097046,0.0000422121,0.00001596755,0.0002464424,0.935114,0.05604618,0.00721302,0.0001282401,0.0001624642],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8129585,0.0009046147,0.1837096,0.0006075457,0.0009432912,0.0001461102,0.00001354195,0.0002820341,0.0004348005],"genre_scores_gemma":[0.9976838,0.0002901491,0.001785725,0.00006335411,0.0001066623,0.00001938337,0.00001344712,0.00001607355,0.00002146679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9673556,"threshold_uncertainty_score":0.5230857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03020416481156932,"score_gpt":0.3285246762146629,"score_spread":0.2983205114030935,"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."}}