{"id":"W2937006295","doi":"10.1016/j.mri.2019.04.009","title":"Open-source pipeline for multi-class segmentation of the spinal cord with deep learning","year":2019,"lang":"en","type":"article","venue":"Magnetic Resonance Imaging","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; Canada First Research Excellence Fund; Canada Foundation for Innovation","keywords":"Segmentation; Pipeline (software); Computer science; Artificial intelligence; Grey matter; Market segmentation; Pattern recognition (psychology); White matter; Deep learning; Spinal cord; Homogeneous; Artificial neural network; Open source; Software; Neuroscience; Medicine; Magnetic resonance imaging; Radiology; Mathematics; Psychology","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":[0.0002069904,0.0001044606,0.0001156372,0.00003922146,0.0001741332,0.00009914147,0.0004045568,0.00001632372,0.00005830677],"category_scores_gemma":[0.0002168965,0.00007680625,0.00003648508,0.0002821628,0.0001168677,0.0001764414,0.00009430452,0.0001361178,0.00001821289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003520251,"about_ca_system_score_gemma":0.00002806521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002724211,"about_ca_topic_score_gemma":0.00001365922,"domain_scores_codex":[0.9989598,0.0001068674,0.0002070058,0.0003544768,0.0001861088,0.0001857266],"domain_scores_gemma":[0.9993602,0.00007371455,0.0002070163,0.0002644839,0.00006686078,0.00002771489],"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":[0.0003739513,0.00004371246,0.009027558,0.00003184385,3.593002e-7,5.12198e-7,0.0001135,0.000238125,0.3244353,0.0003028094,0.00003962605,0.6653927],"study_design_scores_gemma":[0.002875687,0.0005063511,0.07041465,0.0001607109,0.00001398592,0.00004348255,0.0006914542,0.661483,0.2023937,0.00005152054,0.06115242,0.0002130126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8902569,0.0008609758,0.1003259,0.002174625,0.0005091693,0.002735895,0.00000605695,0.0001217327,0.003008654],"genre_scores_gemma":[0.9877849,0.00001193161,0.002073135,0.0005576173,0.00002189858,0.00007991977,8.917746e-7,0.00002348233,0.009446177],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6651797,"threshold_uncertainty_score":0.3132068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03267243715276794,"score_gpt":0.295982363835969,"score_spread":0.2633099266832011,"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."}}