{"id":"W4413006736","doi":"10.1148/ryai.240478","title":"Automated Deep Learning–based Segmentation of the Dentate Nucleus Using Quantitative Susceptibility Mapping MRI","year":2025,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Health and Medical Research Council; National Institutes of Health; Friedreich's Ataxia Research Alliance","keywords":"Intraclass correlation; Segmentation; Sørensen–Dice coefficient; Artificial intelligence; Deep learning; Dentate nucleus; Computer science; Magnetic resonance imaging; Medicine; Pattern recognition (psychology); Image segmentation; Psychology; Radiology; Cerebellum; Neuroscience","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002674191,0.0001093936,0.0002271322,0.0001004767,0.0002106511,0.00000614801,0.000131128,0.0000970298,0.0000726056],"category_scores_gemma":[0.0002431035,0.00008821062,0.0000927265,0.000570925,0.0004204118,0.00004109299,0.00004210939,0.000224226,0.00001167216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273725,"about_ca_system_score_gemma":0.000094113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000545206,"about_ca_topic_score_gemma":0.00003717531,"domain_scores_codex":[0.9989032,0.0001449963,0.0004372161,0.0002573903,0.00008348085,0.0001737376],"domain_scores_gemma":[0.9991278,0.0002133696,0.0001966081,0.00026545,0.0001670042,0.00002973392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002627751,0.0002687903,0.01916985,0.00009901223,0.00005498132,0.000004344862,0.0008864843,0.1651782,0.7553127,0.0392306,0.0000696572,0.01946261],"study_design_scores_gemma":[0.00005262156,0.0001024469,0.004767553,0.00008909928,0.00005610646,0.000009229165,0.001310665,0.6148109,0.3717144,0.00688768,0.0001225209,0.00007679544],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3263081,0.00005976373,0.6724139,0.0004154957,0.00008057401,0.0004328394,0.000003326049,0.0001292896,0.0001567446],"genre_scores_gemma":[0.9022448,0.00002436901,0.09743272,0.0001852876,0.00001361286,0.00002791079,0.000008447085,0.000008033487,0.00005481235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5759367,"threshold_uncertainty_score":0.3597125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06647520502677146,"score_gpt":0.4007774601525536,"score_spread":0.3343022551257821,"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."}}