{"id":"W2042563007","doi":"10.1117/12.2079935","title":"Color model comparative analysis for breast cancer diagnosis using H and E stained images","year":2015,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Color space; Artificial intelligence; RGB color model; Feature extraction; Pattern recognition (psychology); Benchmark (surveying); Grayscale; Histopathology; Feature (linguistics); Computer vision; Image (mathematics); Pathology; 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":[0.002967446,0.0005854671,0.000448487,0.002167146,0.0003238311,0.001175047,0.0004501675,0.0006283625,0.001775009],"category_scores_gemma":[0.005254907,0.0001609971,0.0009721937,0.00095113,0.0003334568,0.0008787308,0.0005948401,0.0004696274,0.0004487141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000906064,"about_ca_system_score_gemma":0.000633091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007355778,"about_ca_topic_score_gemma":0.006200534,"domain_scores_codex":[0.9991131,0.0003153778,0.00004864887,0.0001221969,0.0002985376,0.000102069],"domain_scores_gemma":[0.9978591,0.001110622,0.000132786,0.0002221782,0.0006074696,0.00006791665],"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":[0.002578779,0.0005300049,0.03001373,0.0004234337,0.000444946,0.0003175806,0.0003137421,0.4632824,0.04605765,0.007435219,0.005139309,0.4434632],"study_design_scores_gemma":[0.00001112881,0.0002021786,0.00763022,0.00001588839,0.00006280906,0.0001061477,0.0001047888,0.9740295,0.01584774,0.001211053,0.0007537335,0.00002485704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6183652,0.001763211,0.3719316,0.0005959976,0.0001038492,0.0001536405,0.0006373181,0.001474293,0.004974881],"genre_scores_gemma":[0.9172722,0.0005758863,0.07942694,0.0001006813,0.00002182513,0.00004241178,0.0009974252,0.0000822948,0.001480333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007355778,"threshold_uncertainty_score":0.01569355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03284761775567852,"score_gpt":0.2817156189121414,"score_spread":0.2488680011564629,"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."}}