{"id":"W2581493794","doi":"10.1364/boe.8.001203","title":"Deep feature learning for automatic tissue classification of coronary artery using optical coherence tomography","year":2017,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Kawasaki Disease and Coronary Complications","field":"Medicine","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine; École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Optical coherence tomography; Convolutional neural network; Artificial intelligence; Kawasaki disease; Random forest; Artery; Support vector machine; Feature extraction; Medicine; Computer science; Pattern recognition (psychology); Feature (linguistics); Radiology; Internal medicine","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":[0.000138542,0.0001619694,0.0003349821,0.0001133326,0.0003408543,0.00004881461,0.0003300935,0.0001971759,0.00005363682],"category_scores_gemma":[0.0003002551,0.0001460386,0.0001353313,0.000100107,0.0005387862,0.000124838,0.000094626,0.0002026315,0.000007520964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003383321,"about_ca_system_score_gemma":0.0001404755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003442279,"about_ca_topic_score_gemma":6.312265e-7,"domain_scores_codex":[0.9986694,0.00002924543,0.0003356368,0.0003121173,0.0003830543,0.000270535],"domain_scores_gemma":[0.9983247,0.0001675288,0.0002574818,0.0007105789,0.0002104732,0.0003292163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000513666,0.002236292,0.02883825,0.001450663,0.0004701698,0.0001149632,0.0003911365,0.00005975811,0.8103264,0.006109443,0.001756805,0.1477325],"study_design_scores_gemma":[0.002939092,0.001173109,0.6210963,0.0008239148,0.0007974224,0.0002189475,0.0003883029,0.3599477,0.005371556,0.0008715624,0.005923721,0.0004483166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8306614,0.0004495969,0.1640184,0.002016373,0.0002862323,0.00112428,0.00003289673,0.0001237435,0.001287146],"genre_scores_gemma":[0.9485412,0.00001783624,0.05073158,0.00006333996,0.000196601,0.00009469053,0.0001565668,0.00002445172,0.000173761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8049548,"threshold_uncertainty_score":0.5955279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04206254618045371,"score_gpt":0.3293638129411396,"score_spread":0.2873012667606859,"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."}}