{"id":"W2581270879","doi":"10.1002/jmri.25622","title":"Topologically preserving straightening of spinal cord MRI","year":2017,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Cervical and Thoracic Myelopathy","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Montreal Heart Institute; University of Toronto; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Spinal cord; Segmentation; Magnetic resonance imaging; Voxel; Medicine; Robustness (evolution); Algorithm; Mathematics; Computer science; Artificial intelligence; Radiology","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":[0.0006115571,0.0001292856,0.0004598198,0.00009073567,0.0001438223,0.00006363886,0.0004449332,0.0000433228,0.0006722198],"category_scores_gemma":[0.0007250938,0.00009281923,0.0001858995,0.00005861362,0.0002284242,0.0002242971,0.0001589667,0.0003662239,0.00000467014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002502185,"about_ca_system_score_gemma":0.0001029413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002911271,"about_ca_topic_score_gemma":0.000002228706,"domain_scores_codex":[0.9984351,0.00003838749,0.0006501548,0.0001501883,0.00047114,0.0002550376],"domain_scores_gemma":[0.9982609,0.00006085331,0.0007282789,0.0004043776,0.0003808407,0.0001647727],"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":[0.001578926,0.00007920892,0.07317302,0.0001042591,0.00001057932,0.0007005198,0.00005053678,0.000001753388,0.006011562,0.0001957738,0.0001697189,0.9179242],"study_design_scores_gemma":[0.00143784,0.002265738,0.9722813,0.00124044,0.0001109093,0.001449821,0.0001203984,0.0005659504,0.001422797,0.002327506,0.01665623,0.0001210877],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9274371,0.03054525,0.00168657,0.01032547,0.0004705306,0.0001860622,0.000003237602,0.00001480472,0.02933095],"genre_scores_gemma":[0.9788797,0.0006064028,0.01922093,0.0001958906,0.0003961963,0.000001083316,2.678437e-7,0.00001225804,0.0006872471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.917803,"threshold_uncertainty_score":0.7360335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02656570006057281,"score_gpt":0.3320379098800536,"score_spread":0.3054722098194808,"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."}}