{"id":"W2069716978","doi":"10.1118/1.4736530","title":"Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c‐means clustering and support vector machine segmentation","year":2012,"lang":"en","type":"article","venue":"Medical Physics","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":215,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto; University of Pennsylvania; National Cancer Institute; National Institutes of Health; American Cancer Society; U.S. Department of Defense","keywords":"Mammography; Artificial intelligence; Computer science; Digital mammography; Cluster analysis; Breast cancer; Support vector machine; Thresholding; Pattern recognition (psychology); Segmentation; Computer vision; Medicine; Cancer; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001275723,0.0001267618,0.0002252215,0.00008256492,0.00002775926,0.00002716498,0.00003295034,0.00004916852,0.00001065864],"category_scores_gemma":[0.0000402189,0.0001084795,0.00004856845,0.0002090662,0.0001772719,0.0006555897,0.00004580839,0.0001506456,9.279707e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001523142,"about_ca_system_score_gemma":0.0000258598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003745659,"about_ca_topic_score_gemma":0.000006828715,"domain_scores_codex":[0.999109,0.00001249379,0.0002037093,0.0001517443,0.000328274,0.0001947645],"domain_scores_gemma":[0.9995484,0.00006419336,0.00006441946,0.00007543159,0.00003791626,0.0002096812],"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":[0.0004039679,0.0005823566,0.2418899,0.0004946575,0.00006204885,0.00001858858,0.001095641,0.000007285983,0.0017953,0.00004312824,0.00003127412,0.7535759],"study_design_scores_gemma":[0.003481311,0.000828045,0.9598831,0.0007205499,0.0001857072,0.000948374,0.00056685,0.01911171,0.01266917,0.001225295,0.000006807232,0.0003730679],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9178154,0.000134564,0.08050828,0.0005769589,0.00005710092,0.0002537436,0.00002476958,0.00003007689,0.0005990351],"genre_scores_gemma":[0.9992775,0.00001860189,0.0003889342,0.0001401335,0.00008424794,0.0000064247,0.00006895008,0.00001041638,0.000004808524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7532028,"threshold_uncertainty_score":0.4423667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007082296463329534,"score_gpt":0.2423381494468425,"score_spread":0.235255852983513,"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."}}