{"id":"W4391506213","doi":"10.1162/imag_a_00218","title":"Automatic segmentation of the spinal cord nerve rootlets","year":2024,"lang":"en","type":"preprint","venue":"Imaging Neuroscience","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"HORIZON EUROPE Framework Programme; Natural Sciences and Engineering Research Council of Canada; European Commission; Institut de Valorisation des Données; Craig H. Neilsen Foundation; Canada First Research Excellence Fund; Ministerstvo Zdravotnictví Ceské Republiky","keywords":"Spinal cord; Segmentation; Sørensen–Dice coefficient; Convolutional neural network; Coefficient of variation; Magnetic resonance imaging; Computer science; Pattern recognition (psychology); Artificial intelligence; Medicine; Image segmentation; Neuroscience; Radiology; Psychology; Mathematics; Statistics","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":[0.0002075947,0.0001748711,0.0001929614,0.0001241835,0.00005593981,0.0001486683,0.0005960938,0.00002968163,0.00001221187],"category_scores_gemma":[0.0001301854,0.0001284431,0.0001484134,0.0004370787,0.0002406543,0.00005400453,0.0005156724,0.00056747,0.00001424603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004606814,"about_ca_system_score_gemma":0.00006310151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003614206,"about_ca_topic_score_gemma":7.347807e-7,"domain_scores_codex":[0.9986591,0.00004012496,0.0002948478,0.0003259096,0.0004684155,0.0002115468],"domain_scores_gemma":[0.9993755,0.00001890585,0.00007749263,0.0004360576,0.0000286247,0.00006346803],"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":[0.0000030176,0.00007260227,0.007548328,0.005731093,0.00004724796,0.0001607567,0.0005346888,0.09070918,0.4061437,0.0002043963,0.00924161,0.4796034],"study_design_scores_gemma":[0.00003625415,0.000006334987,0.005037038,0.0008108331,0.0000827414,0.0000200544,0.0000158307,0.9834588,0.009003348,0.001198967,0.0001816387,0.0001481859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9739029,0.001779332,0.01195985,0.002205452,0.007984138,0.0002473235,0.00002712605,0.0007105748,0.001183321],"genre_scores_gemma":[0.9991871,0.00002100213,0.0004009131,0.0001876093,0.00006440446,0.00001295677,0.000001320089,0.00002357776,0.0001010747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8927496,"threshold_uncertainty_score":0.5237759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01866862039060179,"score_gpt":0.2924666393515591,"score_spread":0.2737980189609573,"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."}}