{"id":"W4384557826","doi":"10.3390/info14070410","title":"Breast Cancer Detection in Mammography Images: A CNN-Based Approach with Feature Selection","year":2023,"lang":"en","type":"article","venue":"Information","topic":"AI in cancer detection","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Random forest; Support vector machine; Convolutional neural network; Mammography; Feature selection; Pattern recognition (psychology); Classifier (UML); Breast cancer; Feature extraction; Artificial neural network; Machine learning; Cancer; 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":[0.0002502758,0.000130595,0.000096143,0.0008429973,0.0001281088,0.0001971942,0.000208221,0.0001031056,0.000004019705],"category_scores_gemma":[0.000005314766,0.0001173585,0.00003715938,0.003923422,0.00002326109,0.003126096,0.00002698073,0.0002238995,0.00004242102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002866042,"about_ca_system_score_gemma":0.0001006027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003662353,"about_ca_topic_score_gemma":0.000213994,"domain_scores_codex":[0.9990091,0.00003796184,0.0001862595,0.0001836092,0.0003408905,0.0002421572],"domain_scores_gemma":[0.9994489,0.00001927269,0.0001441925,0.0002012495,0.0001450213,0.00004135155],"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":[0.0002409591,0.00004655256,0.01662505,0.0002226274,0.00002942217,0.000002019335,0.001840963,0.210864,0.0007954225,0.0002261796,0.002278244,0.7668285],"study_design_scores_gemma":[0.0007818723,0.00009216834,0.1540364,0.00005038458,0.000006151697,0.00005699835,0.0001201909,0.8362744,0.007222065,0.0001001097,0.001028927,0.0002304026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02546145,0.00001522216,0.9714077,0.0007100553,0.0003116906,0.0004175057,0.00001054049,0.0008505642,0.0008153191],"genre_scores_gemma":[0.9937043,0.00001106272,0.005676038,0.0001704421,0.00006128056,0.0003187755,0.00002234191,0.000008278057,0.0000274886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9682428,"threshold_uncertainty_score":0.4785743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005280063777756617,"score_gpt":0.2072418453120105,"score_spread":0.2019617815342539,"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."}}