{"id":"W3207478520","doi":"10.1093/neuonc/noab238","title":"Improving the noninvasive classification of glioma genetic subtype with deep learning and diffusion-weighted imaging","year":2021,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Cancer Institute","keywords":"Convolutional neural network; Radiogenomics; Diffusion MRI; Glioma; Magnetic resonance imaging; Artificial intelligence; Medicine; Computer science; Machine learning; Radiology; Nuclear medicine; Radiomics; Cancer research","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":[0.00006428301,0.0001124619,0.0002421834,0.00007187654,0.000119934,0.00001392658,0.00004070564,0.000054387,0.00004469241],"category_scores_gemma":[0.0001759107,0.00007101684,0.00003807354,0.0002286918,0.0001238981,0.00002541796,0.00006244517,0.0001768402,0.000004152055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006054009,"about_ca_system_score_gemma":0.0001735252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003237373,"about_ca_topic_score_gemma":0.00006149364,"domain_scores_codex":[0.9990804,0.0001464425,0.0001892222,0.000278357,0.0001364294,0.0001691977],"domain_scores_gemma":[0.9988793,0.0004977722,0.0001743103,0.0001890077,0.0001872165,0.00007246857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00008379892,0.0001884778,0.1848544,0.00002384349,0.00003452561,0.001093227,0.0003169906,0.000002858772,0.7375219,0.00006866385,0.00001648557,0.07579478],"study_design_scores_gemma":[0.006607921,0.001933807,0.603126,0.00008355515,0.0007139099,0.004853406,0.002271571,0.01129143,0.3625422,0.00005004644,0.00634256,0.0001835083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994684,0.001453272,0.0001691848,0.002773548,0.00008238938,0.0002501506,9.469296e-7,0.00002253151,0.0005639992],"genre_scores_gemma":[0.9984974,0.0002258855,0.0008574937,0.0002841141,0.00005496892,0.00004126731,0.00001154988,0.00001958074,0.000007693549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4182716,"threshold_uncertainty_score":0.2895983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114566150997251,"score_gpt":0.2578165132133335,"score_spread":0.2463598981136084,"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."}}