{"id":"W2964004560","doi":"10.1371/journal.pone.0190783","title":"Automatic labeling of molecular biomarkers of immunohistochemistry images using fully convolutional networks","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency; Occupational Cancer Research Centre; University of British Columbia","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); RGB color model; Deep learning; Biomarker; Immunohistochemistry; Computer vision; Digital pathology; Image (mathematics); Scanner; Imaging biomarker; Pathology; Biology; Medicine; Magnetic resonance imaging; Radiology","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":[0.0008480189,0.001262004,0.0005752092,0.001528179,0.0002817019,0.0009428972,0.001085754,0.001137875,0.0008961218],"category_scores_gemma":[0.001514874,0.0005993727,0.0007622118,0.0007899883,0.0004108711,0.000916023,0.0006968085,0.0007318091,0.0005980064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001081874,"about_ca_system_score_gemma":0.0009235417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004459698,"about_ca_topic_score_gemma":0.008251649,"domain_scores_codex":[0.9995093,0.00007688948,0.00002679552,0.0001775741,0.0001392423,0.00007009132],"domain_scores_gemma":[0.9993306,0.0002002493,0.000159301,0.00009801194,0.0001803326,0.00003143915],"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":[0.0004454536,0.0002027055,0.006087423,0.0004007856,0.000191046,0.0003321829,0.0001424482,0.1264755,0.2765522,0.002734615,0.003820274,0.5826154],"study_design_scores_gemma":[0.00001306864,0.00008447545,0.003917877,0.00004166678,0.00005576504,0.0001810183,0.00002694251,0.9008262,0.08905898,0.002761007,0.00300282,0.00003017948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09981135,0.001424453,0.8919156,0.0002794631,0.00008190056,0.0001068298,0.0004356948,0.004207858,0.00173682],"genre_scores_gemma":[0.4317558,0.001213496,0.5607806,0.0002670905,0.0000539745,0.000168383,0.00152449,0.0002268341,0.004009228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004459698,"threshold_uncertainty_score":0.008867502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02449611317589408,"score_gpt":0.2445954790128,"score_spread":0.2200993658369059,"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."}}