{"id":"W4294975187","doi":"10.1109/embc48229.2022.9871809","title":"Vision Transformers for Classification of Breast Ultrasound Images","year":2022,"lang":"en","type":"article","venue":"2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Breast ultrasound; Computer science; Convolutional neural network; Pattern recognition (psychology); Breast cancer; Deep learning; Contextual image classification; Medical imaging; Ultrasound; Artificial neural network; Machine learning; Mammography; Medicine; Image (mathematics); Radiology","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":[0.0008236154,0.0001450308,0.000241043,0.0001695242,0.00009107567,0.000008773391,0.001074556,0.00008094936,0.00008958554],"category_scores_gemma":[0.0001268157,0.000120625,0.000154727,0.0005224942,0.0002076782,0.0001936746,0.0001162056,0.0003606874,5.651784e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001885693,"about_ca_system_score_gemma":0.0001021787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001506847,"about_ca_topic_score_gemma":0.00002807641,"domain_scores_codex":[0.9986601,0.00007090313,0.0004395191,0.0003083186,0.0003252382,0.0001959186],"domain_scores_gemma":[0.9988483,0.0003276933,0.0002457928,0.0002471912,0.0002952007,0.00003577663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001133515,0.0001510035,0.003053388,0.0001236123,0.0002087233,2.011548e-7,0.005250591,0.01481717,0.9414265,0.009288576,0.01911012,0.006456741],"study_design_scores_gemma":[0.007391404,0.002467617,0.1116141,0.0006113948,0.0001409758,0.0002753916,0.006784388,0.7649709,0.03029317,0.008876983,0.0651913,0.001382359],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.103739,0.0001367048,0.8847216,0.006459763,0.003857174,0.0004243962,0.0003398538,0.00005975727,0.0002617533],"genre_scores_gemma":[0.9940585,0.0001474416,0.005152442,0.0001168062,0.0001310799,0.0001058344,0.0000587384,0.00001084341,0.000218299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9111333,"threshold_uncertainty_score":0.4918943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03043471752350013,"score_gpt":0.306323042800441,"score_spread":0.2758883252769408,"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."}}