{"id":"W3015500759","doi":"10.1002/mp.14168","title":"Automated glioma grading on conventional MRI images using deep convolutional neural networks","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":164,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute; National Institutes of Health","keywords":"Convolutional neural network; Glioma; Grading (engineering); Artificial intelligence; Computer science; Medical imaging; Artificial neural network; Magnetic resonance imaging; Medical physics; Pattern recognition (psychology); Radiology; Medicine; Engineering","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":[0.0003527839,0.001058584,0.0003422569,0.001834807,0.0001689631,0.0005731278,0.000640104,0.0004844739,0.001174624],"category_scores_gemma":[0.001026365,0.0002455612,0.0004235949,0.0007151428,0.0001906059,0.0004865196,0.0005721475,0.0003744845,0.0007788771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006244685,"about_ca_system_score_gemma":0.0005596672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01143585,"about_ca_topic_score_gemma":0.01910267,"domain_scores_codex":[0.9996998,0.00003748892,0.00001841813,0.00008285185,0.0001161515,0.00004522911],"domain_scores_gemma":[0.9996687,0.00005909265,0.00007621566,0.00005327052,0.0001201812,0.00002257981],"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":[0.0007328197,0.0002351339,0.01204257,0.0002810719,0.0001690621,0.0004653767,0.00007963141,0.07621333,0.08367588,0.000592567,0.006477824,0.8190347],"study_design_scores_gemma":[0.00002649172,0.0001622814,0.01299446,0.00003430841,0.00006370451,0.0003874521,0.0000528202,0.9388083,0.04392145,0.0009613798,0.002558804,0.00002854446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5895095,0.002911115,0.3880427,0.0004114093,0.0001834689,0.0003939945,0.003313693,0.009673811,0.005560152],"genre_scores_gemma":[0.8643651,0.0009519946,0.1261322,0.0001276855,0.00005665509,0.00008773121,0.004462947,0.0001673399,0.003648225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01143585,"threshold_uncertainty_score":0.02273852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05407122301156024,"score_gpt":0.2956170731417934,"score_spread":0.2415458501302332,"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."}}