{"id":"W2939203921","doi":"10.1109/ijcnn.2019.8852092","title":"Double Transfer Learning for Breast Cancer Histopathologic Image Classification","year":2019,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Transfer of learning; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Computer science; Breast cancer; Classifier (UML); Feature extraction; Magnification; Feature vector; Contextual image classification; Machine learning; Cancer; Image (mathematics); Medicine","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":[0.0009001537,0.0008198891,0.0006445714,0.001149348,0.0002950164,0.0005882375,0.00135754,0.0009354972,0.002641216],"category_scores_gemma":[0.001580281,0.0002242406,0.0006987745,0.0007834836,0.0004154999,0.0008339269,0.0009488423,0.0008764906,0.00154867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005845245,"about_ca_system_score_gemma":0.0006425526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002345131,"about_ca_topic_score_gemma":0.002310007,"domain_scores_codex":[0.9994882,0.00008439086,0.000023279,0.000134704,0.0001705917,0.00009882743],"domain_scores_gemma":[0.9994097,0.0001344147,0.00005544872,0.000150129,0.0002075243,0.00004287942],"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":[0.0003107338,0.0003899879,0.00498029,0.000149542,0.0001257848,0.0001732971,0.00007520619,0.04490773,0.04495157,0.001528675,0.006163044,0.8962442],"study_design_scores_gemma":[0.0000200366,0.0002496445,0.003919296,0.00001646436,0.0000476814,0.0002837051,0.00006102547,0.9443684,0.04295506,0.004201623,0.003855987,0.00002098803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2126939,0.002039027,0.7700393,0.0005008297,0.0002163566,0.0002564306,0.0005053255,0.007956987,0.005791899],"genre_scores_gemma":[0.8360572,0.0004616998,0.1530007,0.0002445295,0.0001255736,0.0001545348,0.001299193,0.0001794602,0.008477108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002641216,"threshold_uncertainty_score":0.008835673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04793985607655581,"score_gpt":0.2981739568520222,"score_spread":0.2502341007754664,"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."}}