{"id":"W2969706100","doi":"10.1002/jbio.201900112","title":"An automatic diagnostic system of coronary artery lesions in Kawasaki disease using intravascular optical coherence tomography imaging","year":2019,"lang":"en","type":"article","venue":"Journal of Biophotonics","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Optical coherence tomography; Artery; Convolutional neural network; Coronary artery disease; Radiology; Intravascular ultrasound; Lesion; Calcification; Pathological; Cardiology; Internal medicine; Pathology; Artificial intelligence; Computer science","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":[0.0004237572,0.0001570443,0.0005143506,0.0004243159,0.00003077402,0.00002332037,0.0001703626,0.00006048416,0.0001113295],"category_scores_gemma":[0.0002832974,0.0001344667,0.0003529125,0.0003190466,0.0000907518,0.0001972077,0.00004005654,0.0002844932,0.000006600008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571193,"about_ca_system_score_gemma":0.0003411584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001962386,"about_ca_topic_score_gemma":0.000004656941,"domain_scores_codex":[0.9982163,0.00008211422,0.0009136889,0.0001624004,0.0003995773,0.0002259569],"domain_scores_gemma":[0.9982752,0.0004095432,0.0003691576,0.0003857682,0.0002396175,0.0003206803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003403563,0.002230088,0.9618409,0.001542572,0.0001918359,0.005086894,0.0001959013,0.002148635,0.0195485,0.0003113851,0.00003521921,0.006527763],"study_design_scores_gemma":[0.002301598,0.001020863,0.8408811,0.007248153,0.0005956535,0.002523868,0.00136011,0.1428715,0.0009240005,0.00006332047,0.00002513184,0.000184753],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962025,0.00229696,0.0005513443,0.00007542797,0.0004114955,0.0003836777,0.00001806515,0.00001513821,0.00004542513],"genre_scores_gemma":[0.9962553,0.0001243317,0.00349171,0.00005093555,0.00004353066,0.000003660755,0.000006596733,0.00002040335,0.000003515161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1407228,"threshold_uncertainty_score":0.5483394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01185436948828537,"score_gpt":0.2735848359709288,"score_spread":0.2617304664826434,"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."}}