{"id":"W4378803851","doi":"10.20944/preprints202305.2209.v1","title":"Breast Cancer Detection in Mammography Images: A CNN-Based Approach with Feature Selection","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Radiological Society of North America","keywords":"Convolutional neural network; Mammography; Artificial intelligence; Computer science; Feature selection; Breast cancer; Pattern recognition (psychology); Classifier (UML); Feature extraction; Artificial neural network; Feature (linguistics); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008472112,0.0006143859,0.0005245367,0.001154454,0.0001955491,0.0001633898,0.001401899,0.0006575785,0.00003720448],"category_scores_gemma":[0.00002707538,0.0006144417,0.0002421781,0.002678602,0.0001161012,0.0004399375,0.001085738,0.002272116,0.0001244642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169515,"about_ca_system_score_gemma":0.0005671179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004122683,"about_ca_topic_score_gemma":0.001733706,"domain_scores_codex":[0.9954006,0.0003066812,0.0004543708,0.002401451,0.0007839107,0.0006529901],"domain_scores_gemma":[0.9972969,0.00006746427,0.0004963558,0.001648579,0.0003338981,0.0001567854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003577914,0.0002649726,0.8079914,0.0006993979,0.0002118164,0.00002463799,0.0006445679,0.166438,0.003967538,0.00003686572,0.0001139056,0.01924906],"study_design_scores_gemma":[0.0008056076,0.00005287764,0.8491925,0.0004809863,0.00005798005,0.0000845554,0.00004145391,0.102555,0.04499714,0.0007038431,0.0001686135,0.0008594397],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2479846,0.0002127585,0.7416824,0.001848515,0.002292356,0.002306214,0.00005833676,0.002745447,0.0008694535],"genre_scores_gemma":[0.9897251,0.00008551993,0.006889825,0.00009669216,0.0003233489,0.002323257,0.0000193273,0.00009956455,0.0004373941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7417405,"threshold_uncertainty_score":0.9996307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05680739561498406,"score_gpt":0.3013425763835118,"score_spread":0.2445351807685277,"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."}}