{"id":"W3106174756","doi":"10.1109/access.2020.3036662","title":"On Segmentation of Pectoral Muscle in Digital Mammograms by Means of Deep Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Deep learning; Mammography; Convolutional neural network; Digital mammography; Pattern recognition (psychology); Pectoral muscle; Image segmentation; Shortest path problem; Graph; Artificial neural network; Computer vision; Anatomy; Breast cancer; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00005461348,0.00006179947,0.0001019871,0.00005219393,0.00001748414,0.00007511573,0.000432217,0.00002753824,0.00001120194],"category_scores_gemma":[0.00003735434,0.00006466142,0.00002910596,0.0004505196,0.00002227559,0.0008740322,0.00006432455,0.0000976014,0.000003639446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004307085,"about_ca_system_score_gemma":0.00001403182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009020107,"about_ca_topic_score_gemma":0.00002860685,"domain_scores_codex":[0.9992959,0.00002234634,0.0001785485,0.0001874316,0.0002179063,0.00009779323],"domain_scores_gemma":[0.9996329,0.00005029159,0.000128976,0.0001124715,0.00003595145,0.00003942848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008136402,0.000164106,0.04335748,0.0001249973,0.00002114683,0.000006844044,0.004993633,0.06064969,0.051692,0.0003267199,0.0004737782,0.8381082],"study_design_scores_gemma":[0.00164257,0.001324618,0.02688022,0.00008980477,0.000009763226,0.000001839767,0.0003343887,0.3919678,0.5749685,0.001926038,0.0004438879,0.0004105555],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6432154,0.00001691165,0.35614,0.0001070317,0.000143864,0.00007400013,0.000002067616,0.00003633952,0.0002644023],"genre_scores_gemma":[0.9993019,0.000003541987,0.0005756085,0.00007618564,0.00002330938,0.000006242054,0.000002326371,0.00000586525,0.000005015795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8376977,"threshold_uncertainty_score":0.2636816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02242769437002175,"score_gpt":0.2787437578239427,"score_spread":0.256316063453921,"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."}}