{"id":"W4396930028","doi":"10.1038/s41597-024-03350-9","title":"A multi-institutional meningioma MRI dataset for automated multi-sequence image segmentation","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Meningioma and schwannoma management","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Toronto; University of Ottawa","funders":"National Cancer Institute; National Institutes of Health; Perelman School of Medicine, University of Pennsylvania; Instituto Tecnológico de Costa Rica; American Society of Neuroradiology; University of Pennsylvania; Foundation for the National Institutes of Health","keywords":"Meningioma; Fluid-attenuated inversion recovery; Segmentation; Sequence (biology); Contrast (vision); Radiology; Medicine; Computer science; Magnetic resonance imaging; Medical physics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001324994,0.001919814,0.001051799,0.002658467,0.0008173803,0.001114729,0.002653728,0.001949488,0.004455049],"category_scores_gemma":[0.003517288,0.0005010696,0.001629663,0.001841339,0.0004584584,0.0006108132,0.001626377,0.001350276,0.006019715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001127796,"about_ca_system_score_gemma":0.001789675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01428341,"about_ca_topic_score_gemma":0.03046886,"domain_scores_codex":[0.9991968,0.0001132327,0.000115134,0.0002761113,0.0002088493,0.00008984185],"domain_scores_gemma":[0.9988937,0.0002150078,0.0001257814,0.0003284053,0.0003111237,0.0001260924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002621769,0.001361224,0.02771155,0.003871613,0.001493723,0.003125163,0.0005039713,0.0276682,0.04246319,0.002686818,0.7210288,0.165464],"study_design_scores_gemma":[0.001854424,0.001041851,0.1329844,0.001195955,0.0008951244,0.01010983,0.0008819589,0.1229595,0.04705333,0.0113808,0.669077,0.0005658119],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.09006181,0.003101417,0.02240474,0.00107376,0.0003655938,0.001092328,0.8637607,0.01371153,0.004428124],"genre_scores_gemma":[0.03752755,0.0005004795,0.02761465,0.0001473434,0.00005782986,0.0005794446,0.9320419,0.0003890413,0.001141759],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01428341,"threshold_uncertainty_score":0.02840054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1666244615822458,"score_gpt":0.4157804038618527,"score_spread":0.2491559422796069,"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."}}