{"id":"W2149152304","doi":"10.1109/42.974917","title":"Detection of breast masses in mammograms by density slicing and texture flow-field analysis","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":230,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Artificial intelligence; Receiver operating characteristic; Mammography; Pattern recognition (psychology); Computer science; Pixel; False positive paradox; Digital mammography; Computer vision; Medicine; Breast cancer; Cancer","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":[0.0003488132,0.0001282875,0.0002191466,0.0004168962,0.0001165867,0.00005248802,0.0002219139,0.00009945754,0.00005209475],"category_scores_gemma":[0.00001788152,0.0001266864,0.00009073605,0.001578233,0.00007054696,0.0003727782,0.000004782509,0.0004417171,0.000002008153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008727367,"about_ca_system_score_gemma":0.00003271761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001193632,"about_ca_topic_score_gemma":0.00153078,"domain_scores_codex":[0.998578,0.00008457652,0.0002795127,0.0003643366,0.0004667738,0.0002268428],"domain_scores_gemma":[0.9992874,0.0001846905,0.00006731877,0.0002692984,0.00005146396,0.000139882],"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":[0.00002468067,0.00007759526,0.003744601,0.0000131756,0.00005810487,0.00002195474,0.0001959354,0.001437507,0.006845644,0.000002501627,0.00002112974,0.9875572],"study_design_scores_gemma":[0.0004878253,0.0000554228,0.004934932,0.00008020362,0.0001119247,0.0002756261,0.000126301,0.9474827,0.04601764,0.0001055905,0.000124605,0.0001972249],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09433789,0.00007153792,0.9036006,0.001488925,0.0002884823,0.00006939682,0.000002098849,0.00008660588,0.00005448471],"genre_scores_gemma":[0.9974078,0.0001418253,0.00204776,0.0003406899,0.00002795703,0.00001058856,4.73643e-7,0.000007397206,0.00001551597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9873599,"threshold_uncertainty_score":0.5166122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004700363833605204,"score_gpt":0.2358045023866887,"score_spread":0.2311041385530835,"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."}}