{"id":"W1147193425","doi":"10.1109/tmi.2015.2470529","title":"Triaging Diagnostically Relevant Regions from Pathology Whole Slides of Breast Cancer: A Texture Based Approach","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Kela; Sunnybrook Research Institute","keywords":"Breast cancer; Digital pathology; Texture (cosmology); Pathology; Computer science; Medicine; Artificial intelligence; Cancer; Computer vision; Image (mathematics); Internal medicine","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":[0.0007042426,0.0005336336,0.000666211,0.003572985,0.0003270273,0.00105631,0.0005042831,0.0006515969,0.000923625],"category_scores_gemma":[0.002222486,0.0003587701,0.0005963487,0.001445161,0.0004166682,0.0007389372,0.0005958973,0.0004971033,0.0006053876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003545677,"about_ca_system_score_gemma":0.0003470942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001050457,"about_ca_topic_score_gemma":0.002241052,"domain_scores_codex":[0.9995506,0.00005955045,0.00004144078,0.00009973955,0.0001910056,0.00005751475],"domain_scores_gemma":[0.99893,0.0003353444,0.0002284348,0.0001212943,0.0003084495,0.00007647981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008233734,0.000202926,0.02263255,0.0005443923,0.0001244169,0.0004537963,0.0002553325,0.004747112,0.4283583,0.0003556712,0.001780654,0.5397215],"study_design_scores_gemma":[0.0001249485,0.001774331,0.2581969,0.0001597694,0.0008600581,0.01066191,0.001000052,0.3649171,0.3466159,0.003623415,0.01185769,0.0002078563],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4167296,0.003160839,0.5741876,0.0006314268,0.0001355058,0.0004135388,0.0004176174,0.002102859,0.002220964],"genre_scores_gemma":[0.6691266,0.001232878,0.3270052,0.0002203472,0.0001613034,0.0001398058,0.0005337853,0.0001711486,0.001408898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003572985,"threshold_uncertainty_score":0.003724456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01958976026000064,"score_gpt":0.2679687745154472,"score_spread":0.2483790142554465,"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."}}