{"id":"W3183868427","doi":"10.1016/j.nicl.2021.102766","title":"Automatic multiclass intramedullary spinal cord tumor segmentation on MRI with deep learning","year":2021,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada Foundation for Innovation; National Natural Science Foundation of China; Canada First Research Excellence Fund; Canada Research Chairs; Nvidia; National Science Foundation","keywords":"Segmentation; Spinal cord; Medicine; Deep learning; Lumbar; Minimum bounding box; Cord; Artificial intelligence; Radiology; Computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002827501,0.0001609743,0.0003022021,0.00005078085,0.00006633944,0.00007459237,0.0001047417,0.00005120661,0.0002630591],"category_scores_gemma":[0.0008295724,0.0001397913,0.0001119035,0.0002403125,0.0001026355,0.00007720318,0.00002863149,0.0008133267,0.0001956588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002381924,"about_ca_system_score_gemma":0.00002974084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002209458,"about_ca_topic_score_gemma":0.000003289959,"domain_scores_codex":[0.9984322,0.0002134464,0.0004515946,0.0003404156,0.0003110962,0.0002512411],"domain_scores_gemma":[0.9990182,0.000413383,0.00005872704,0.0002541975,0.00005458883,0.000200931],"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":[0.00009996359,0.0004182789,0.0322501,0.000281555,0.0002070806,0.003884387,0.0001018266,0.01746908,0.004497397,0.00001926305,0.001532853,0.9392383],"study_design_scores_gemma":[0.0009481259,0.0005572959,0.02655381,0.0002155253,0.0001298429,0.00009511668,0.000158226,0.9684092,0.001308218,0.00001372802,0.001379906,0.0002309785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793408,0.0001113241,0.01845719,0.0005512775,0.0003651983,0.00007282242,0.000001178087,0.0004560486,0.0006441437],"genre_scores_gemma":[0.9863331,0.0001473734,0.01191454,0.001138664,0.0002353521,0.000009692956,0.00002201508,0.00004707426,0.0001522443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9509401,"threshold_uncertainty_score":0.5700523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02793730199582332,"score_gpt":0.3311391495736721,"score_spread":0.3032018475778487,"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."}}