{"id":"W4362458848","doi":"10.59275/j.melba.2022-354b","title":"QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation – Analysis of Ranking Scores and Benchmarking Results","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"National Institutes of Health; National Cancer Institute; Instituto Tecnológico de Costa Rica; Natural Sciences and Engineering Research Council of Canada; National Institute of Neurological Disorders and Stroke; Canadian Institute for Advanced Research","keywords":"Benchmarking; Segmentation; Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Task (project management); Ranking (information retrieval); Reliability (semiconductor); Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03058192,0.004683376,0.00295296,0.007261533,0.001713354,0.005185036,0.004239805,0.005044406,0.005284136],"category_scores_gemma":[0.07986124,0.0006472375,0.002394594,0.003291812,0.002139397,0.003510639,0.005540349,0.002944477,0.003826377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00406472,"about_ca_system_score_gemma":0.003782749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01803184,"about_ca_topic_score_gemma":0.01770958,"domain_scores_codex":[0.9730242,0.009963234,0.002107991,0.003837432,0.009594728,0.001472444],"domain_scores_gemma":[0.9643677,0.01576795,0.002039358,0.004683817,0.01058985,0.002551329],"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":[0.004305622,0.001159511,0.03065875,0.00319033,0.002074703,0.0006123665,0.0005721729,0.2822837,0.0092761,0.009786684,0.264234,0.391846],"study_design_scores_gemma":[0.0006071425,0.001481071,0.01590331,0.0004779166,0.0003155376,0.0006516432,0.0004066793,0.9084808,0.02129158,0.01524152,0.03488247,0.0002603865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4377577,0.03176253,0.3345249,0.01241855,0.006690423,0.003271615,0.05452178,0.06388196,0.05517048],"genre_scores_gemma":[0.7029419,0.002209162,0.1713562,0.002186252,0.0007420994,0.001009443,0.1069734,0.003686096,0.008895233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03058192,"threshold_uncertainty_score":0.1617346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01864686215268765,"score_gpt":0.3230956487698615,"score_spread":0.3044487866171738,"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."}}