{"id":"W4200084039","doi":"10.1371/journal.pone.0259692","title":"Prediction of post transarterial chemoembolization MR images of hepatocellular carcinoma using spatio-temporal graph convolutional networks","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Canadian Institutes of Health Research; Nvidia","keywords":"Magnetic resonance imaging; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Hepatocellular carcinoma; Discriminant; Linear discriminant analysis; Graph; Dynamic contrast; Dynamic contrast-enhanced MRI; Radiology; Medicine; Internal medicine","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":[0.0003790559,0.0006171854,0.0003245182,0.0006656674,0.0001370281,0.0003830173,0.0004924219,0.0006113743,0.0005720052],"category_scores_gemma":[0.001657576,0.0002503509,0.000494969,0.0003095114,0.0002697609,0.0003507494,0.0003286216,0.0006220651,0.0001658141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009326764,"about_ca_system_score_gemma":0.0005186356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01876368,"about_ca_topic_score_gemma":0.01956807,"domain_scores_codex":[0.9998755,0.00002506231,0.000006004523,0.00004240733,0.0000212725,0.00002981066],"domain_scores_gemma":[0.9995455,0.0002212354,0.00007968014,0.00002732011,0.00009508339,0.00003115368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004018145,0.0001599479,0.01378743,0.00006175599,0.0001022311,0.0002455251,0.00003428834,0.8833098,0.00948892,0.001092881,0.001679449,0.08963595],"study_design_scores_gemma":[0.000001528195,0.000009368718,0.0007636665,0.000001332109,0.000004280579,0.000009668094,0.000001855989,0.9985003,0.0004463883,0.000227381,0.00003259738,0.000001589557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7317724,0.001237282,0.262837,0.0008030889,0.00008480429,0.00005959021,0.0007283075,0.001002555,0.001474935],"genre_scores_gemma":[0.9839247,0.0002159678,0.01383327,0.00006862889,0.00001650611,0.00002237568,0.0006087804,0.00002483996,0.001284861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01876368,"threshold_uncertainty_score":0.03730893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02977217262452653,"score_gpt":0.2318512881363759,"score_spread":0.2020791155118493,"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."}}