{"id":"W2159013813","doi":"10.1007/s10278-013-9587-6","title":"Automatic Detection of the Nipple in Screen-Film and Full-field Digital Mammograms Using a Novel Hessian-Based Method","year":2013,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Universidade de São Paulo","keywords":"Hessian matrix; Artificial intelligence; Mammography; Digital mammography; Computer vision; Computer science; Pixel; Distortion (music); Pattern recognition (psychology); Mathematics; Breast 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":[0.0002699982,0.0001221726,0.0002045695,0.0002349619,0.00006016781,0.0007669553,0.0003790446,0.00003466527,0.000003275286],"category_scores_gemma":[0.0001699832,0.00009102168,0.0001116542,0.0005142435,0.00005293458,0.003520258,0.0001349648,0.0002391147,8.414017e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001127323,"about_ca_system_score_gemma":0.00009424376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000661583,"about_ca_topic_score_gemma":0.000009109397,"domain_scores_codex":[0.9987887,0.00003107376,0.0004921881,0.0001533008,0.0003425119,0.0001921966],"domain_scores_gemma":[0.9988389,0.0002085706,0.0005258016,0.0002161551,0.0001435801,0.0000669841],"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":[0.0000161728,0.0001049943,0.02445283,0.00004764155,0.00002513331,0.000006463677,0.0002458985,0.002134556,0.05610429,0.00003388299,0.0000150818,0.9168131],"study_design_scores_gemma":[0.0006464102,0.0001319928,0.008562878,0.0003037594,0.00001213902,0.0006980418,0.000162855,0.9678916,0.01974804,0.001660016,0.0000415594,0.000140757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3774129,0.00005694753,0.6217397,0.0003927408,0.0001726675,0.00008862503,0.00000124898,0.00001414858,0.0001210736],"genre_scores_gemma":[0.9573596,6.074724e-7,0.04249638,0.00008322841,0.00004404461,0.000001909658,8.637183e-8,0.00001009165,0.000004035952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.965757,"threshold_uncertainty_score":0.7395767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01341263259708858,"score_gpt":0.2588320018610167,"score_spread":0.2454193692639282,"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."}}