{"id":"W4399117227","doi":"10.1117/12.3025375","title":"Towards improved breast cancer detection on digital mammograms using local self-attention-based transformer","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Adaptability; Pattern recognition (psychology); Transformer; Feature extraction; Artificial neural network; Mammography; Deep learning; Workload; Breast cancer; Residual neural network; Machine learning; Cancer","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":[0.0005805494,0.0006509059,0.0006031524,0.000909959,0.0001562087,0.0004954795,0.001063067,0.000529029,0.001150087],"category_scores_gemma":[0.001029734,0.0002808207,0.0005866385,0.0004751622,0.0003585843,0.001044253,0.0008695202,0.0005485145,0.000492443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007275767,"about_ca_system_score_gemma":0.000621248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004547238,"about_ca_topic_score_gemma":0.007695323,"domain_scores_codex":[0.9998287,0.00002776249,0.000007087922,0.00005462898,0.000049501,0.00003240394],"domain_scores_gemma":[0.9996744,0.0001173985,0.00004539545,0.00004259663,0.00009299009,0.00002726987],"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":[0.0005209452,0.0003796644,0.01039057,0.0001457165,0.0001587843,0.0002318436,0.0001164777,0.2043736,0.06987907,0.003682752,0.004689595,0.705431],"study_design_scores_gemma":[0.000008062346,0.00005016024,0.0009575598,0.000004434026,0.00002109292,0.00007171822,0.00000966692,0.9873717,0.009944022,0.001164287,0.0003930987,0.000004285548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1757918,0.0006267338,0.8168116,0.0003799582,0.00004633414,0.000102982,0.000228082,0.003418861,0.002593561],"genre_scores_gemma":[0.8959342,0.0003380336,0.09830546,0.0003535751,0.00004183146,0.00004891181,0.0005150663,0.000118013,0.004344871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004547238,"threshold_uncertainty_score":0.009041548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009465053917809621,"score_gpt":0.2487526869988386,"score_spread":0.239287633081029,"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."}}