{"id":"W2947272707","doi":"10.1186/s13104-019-4121-7","title":"BreCaHAD: a dataset for breast cancer histopathological annotation and diagnosis","year":2019,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"AI in cancer detection","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Breast cancer; Histopathology; H&E stain; Cancer; Medicine; Pathology; Histology; Mammography; Artificial intelligence; Computer science; Immunohistochemistry; Internal 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001100559,0.00008081042,0.0001113046,0.000140046,0.0001643153,0.0001663733,0.0004226457,0.00006443314,0.00006083297],"category_scores_gemma":[0.0003267423,0.00006929482,0.00002479276,0.0003334062,0.00009658203,0.0004996497,0.0002862225,0.0001614929,0.00004859791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000149799,"about_ca_system_score_gemma":0.0001215256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004030032,"about_ca_topic_score_gemma":0.0002009018,"domain_scores_codex":[0.9984967,0.0001775927,0.0001218341,0.0004896453,0.0003850255,0.0003292301],"domain_scores_gemma":[0.9978051,0.001458347,0.00003840298,0.0004152735,0.0001994074,0.00008347727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002557831,0.0001489377,0.3270416,0.0003544042,0.00001562227,0.000008351885,0.000596162,0.0002553218,0.005698349,0.005600739,0.04361047,0.6164142],"study_design_scores_gemma":[0.00151197,0.000859699,0.8321379,0.0001288326,0.000009208697,0.00008239663,0.00006608147,0.08402421,0.006749252,0.01095248,0.06300598,0.0004719681],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6342739,0.001629397,0.3436109,0.01241038,0.001119677,0.002668603,0.003937044,0.0002101333,0.000140043],"genre_scores_gemma":[0.9759516,0.0002497779,0.02227842,0.0001745215,0.0002090893,0.0009531144,0.00006473063,0.00001210016,0.0001067107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6159423,"threshold_uncertainty_score":0.2825761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1961177858867512,"score_gpt":0.4389822763232035,"score_spread":0.2428644904364524,"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."}}