{"id":"W3183478831","doi":"10.1002/mp.15017","title":"SCU‐Net: A deep learning method for segmentation and quantification of breast arterial calcifications on mammograms","year":2021,"lang":"en","type":"article","venue":"Medical Physics","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Jaccard index; Metric (unit); Segmentation; Artificial intelligence; Context (archaeology); Pattern recognition (psychology); Computer science; Correlation; Mammography; Digital mammography; Mathematics; Medicine; Breast cancer; Internal 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001379222,0.001729859,0.0008806494,0.002542263,0.0004820031,0.0009331733,0.001688425,0.00154814,0.002295941],"category_scores_gemma":[0.002718125,0.0006070724,0.0008783357,0.001169852,0.0005566211,0.0008312771,0.001023549,0.001072975,0.0009424884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001324386,"about_ca_system_score_gemma":0.001584154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01524815,"about_ca_topic_score_gemma":0.02039819,"domain_scores_codex":[0.999514,0.00007923902,0.00004107124,0.0001412204,0.000168884,0.00005558598],"domain_scores_gemma":[0.9992718,0.0002276025,0.0001155231,0.00007416642,0.0002587226,0.00005214349],"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":[0.0006051561,0.0002624013,0.006685416,0.0003317367,0.0004238488,0.0002684978,0.0001148418,0.2440707,0.01671609,0.003212631,0.02281676,0.704492],"study_design_scores_gemma":[0.00002101285,0.00006318442,0.001121553,0.00003038931,0.00003440937,0.00009536553,0.0000124474,0.987304,0.007680852,0.001479463,0.002141522,0.00001571373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08322351,0.002965896,0.8865974,0.0006413069,0.0002482635,0.0003378165,0.002274387,0.0195822,0.004129212],"genre_scores_gemma":[0.4053036,0.001386258,0.5742692,0.0008496205,0.0001847761,0.000460825,0.006702598,0.0007476283,0.01009548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01524815,"threshold_uncertainty_score":0.0303188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02409596940262398,"score_gpt":0.344108656775204,"score_spread":0.32001268737258,"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."}}