{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008495643,0.000240634,0.0008211284,0.001224454,0.0004409886,0.0000426254,0.0003018189,0.00003847337,0.00006551982],"category_scores_gemma":[0.003202766,0.000174481,0.0002811259,0.001248767,0.0002835176,0.0001217422,0.0001778527,0.001835519,2.184537e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001870235,"about_ca_system_score_gemma":0.0001315953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004006559,"about_ca_topic_score_gemma":0.00002519841,"domain_scores_codex":[0.9962125,0.0008184285,0.001253041,0.000308427,0.001006514,0.0004010636],"domain_scores_gemma":[0.995773,0.002545381,0.001172435,0.0001962675,0.0001187228,0.0001942443],"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":[0.01317549,0.001480099,0.168977,0.0008844918,0.003101543,0.0008625587,0.0222915,0.3417287,0.06087932,0.0003592401,0.002963288,0.3832968],"study_design_scores_gemma":[0.006483148,0.001607656,0.01754442,0.0006471961,0.001102197,0.0004401219,0.002340989,0.9661822,0.0001069618,0.0001442423,0.003184259,0.0002166131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9580169,0.002365769,0.006875873,0.03189471,0.000350279,0.0003728508,0.00002432974,0.00002528138,0.00007400839],"genre_scores_gemma":[0.9961842,0.0002730864,0.001755653,0.00133473,0.0002494758,0.000008127273,0.0001307191,0.00003758892,0.00002639624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6244535,"threshold_uncertainty_score":0.797452,"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."}}