{"id":"W3138973186","doi":"10.1016/j.media.2021.102032","title":"Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Ontario Research Foundation","keywords":"Representation (politics); Artificial intelligence; Computer science; Training (meteorology); Image (mathematics); Computer vision; Pattern recognition (psychology); Geography","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":[0.0009112873,0.001158925,0.0004781288,0.0008023913,0.000267178,0.0005322828,0.001413327,0.000846316,0.001890874],"category_scores_gemma":[0.002635025,0.000451207,0.0004690214,0.0005748237,0.0003569669,0.00107623,0.0007888734,0.0008555843,0.000713809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009452304,"about_ca_system_score_gemma":0.0009593844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01079401,"about_ca_topic_score_gemma":0.01487627,"domain_scores_codex":[0.9997519,0.00003766252,0.00001376837,0.00009766669,0.00004496009,0.00005406722],"domain_scores_gemma":[0.9994748,0.0001703492,0.00005049546,0.00009659914,0.000168389,0.00003933705],"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":[0.0006811635,0.0005910614,0.01314649,0.0004136859,0.0002417036,0.0003484584,0.00022576,0.3962601,0.0534796,0.002204887,0.01279007,0.519617],"study_design_scores_gemma":[0.00002861111,0.0001512761,0.001880083,0.00001896542,0.00003042058,0.0000683276,0.0000449671,0.976594,0.01875523,0.0008147127,0.001600752,0.00001253813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6401109,0.001183716,0.3352655,0.0005969382,0.0003204641,0.0004361926,0.001524313,0.01403514,0.006526848],"genre_scores_gemma":[0.8493689,0.0002800489,0.1421006,0.0003223745,0.00003401136,0.0003136313,0.003577371,0.0002902658,0.003712865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01079401,"threshold_uncertainty_score":0.02146238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03861681853481116,"score_gpt":0.3334691023019692,"score_spread":0.294852283767158,"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."}}