{"id":"W4313402121","doi":"10.3390/curroncol30010042","title":"A Deep Learning Workflow for Mass-Forming Intrahepatic Cholangiocarcinoma and Hepatocellular Carcinoma Classification Based on MRI","year":2022,"lang":"en","type":"article","venue":"Current Oncology","topic":"Cholangiocarcinoma and Gallbladder Cancer Studies","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Feature (linguistics); Preprocessor; Pattern recognition (psychology); Hepatocellular carcinoma; Workflow; Discriminative model; Computer science; Feature extraction; Intrahepatic Cholangiocarcinoma; Deep learning; Medicine; Block (permutation group theory); Convolutional neural network; Pathology; Internal medicine; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004111161,0.0002397598,0.0004778387,0.000271331,0.0005412423,0.00002029211,0.0001151281,0.00007990335,0.00008367287],"category_scores_gemma":[0.0001311942,0.0002365357,0.0001674295,0.0002537785,0.0000936921,0.0000472815,0.00008753506,0.0005917645,0.000006302631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006536127,"about_ca_system_score_gemma":0.000180814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001142022,"about_ca_topic_score_gemma":0.000006778636,"domain_scores_codex":[0.9982625,0.0001594259,0.0003411002,0.0005263481,0.0002840554,0.0004265738],"domain_scores_gemma":[0.9989917,0.0003112469,0.0001726615,0.000265683,0.0001020109,0.0001567428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007574528,0.0002994618,0.8757515,0.0002407767,0.00005355708,0.00004523157,0.001036186,0.0001330704,0.0006357704,0.0002208113,0.0009585122,0.1198677],"study_design_scores_gemma":[0.005716723,0.003880161,0.3982226,0.00006663085,0.0003777037,0.00007069692,0.001460419,0.4672378,0.0001409623,0.0001827483,0.122294,0.0003496336],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9697872,0.009344063,0.01317268,0.003308716,0.001258364,0.001686383,0.00001708298,0.0001291212,0.001296374],"genre_scores_gemma":[0.9962787,0.0001091071,0.001362506,0.0003923644,0.0003475617,0.001153597,0.0002084298,0.00004192369,0.0001058071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4775289,"threshold_uncertainty_score":0.9645647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08024096916480415,"score_gpt":0.3373923528633022,"score_spread":0.257151383698498,"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."}}