{"id":"W4312964864","doi":"10.1161/atvb.42.suppl_1.347","title":"Abstract 347: Using Deep Convolutional Neural Networks To Automate Classification Of Carotid Plaques From Ultrasound Imaging","year":2022,"lang":"en","type":"article","venue":"Arteriosclerosis Thrombosis and Vascular Biology","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Interpretability; Medicine; Convolutional neural network; Stroke (engine); Carotid arteries; Artificial intelligence; Ultrasound; Radiology; Risk stratification; Risk assessment; Pattern recognition (psychology); Internal medicine; Computer science","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":[0.0009868715,0.001894392,0.0005622756,0.001242581,0.0003457598,0.0007756851,0.00110257,0.0009672389,0.003152997],"category_scores_gemma":[0.00208256,0.0005181553,0.0009948522,0.0005535418,0.0002480392,0.0006394364,0.000858083,0.001031378,0.002302185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001207759,"about_ca_system_score_gemma":0.001191358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02109597,"about_ca_topic_score_gemma":0.01688327,"domain_scores_codex":[0.9996567,0.00004955189,0.00001979423,0.0001316796,0.00007111458,0.00007120878],"domain_scores_gemma":[0.9995342,0.0001244734,0.0000495609,0.00007298688,0.0001800138,0.00003868024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001069834,0.0006956288,0.0183144,0.0002986304,0.0004888308,0.000466612,0.0001417887,0.257761,0.06895185,0.001035647,0.01645722,0.6343186],"study_design_scores_gemma":[0.0000173846,0.0001031198,0.002510104,0.00002062282,0.00005359601,0.00006990857,0.00001187876,0.9808977,0.01445423,0.0008176279,0.001029029,0.00001477992],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4980548,0.002301725,0.4642298,0.001097307,0.0004358919,0.0005094918,0.004678698,0.02177975,0.006912459],"genre_scores_gemma":[0.8247833,0.0005968909,0.1558646,0.0004020514,0.0001172371,0.0002349938,0.009098457,0.0003332443,0.008569251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02109597,"threshold_uncertainty_score":0.04194635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03207232574886362,"score_gpt":0.2847862292484264,"score_spread":0.2527139034995628,"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."}}