{"id":"W3079188960","doi":"10.1109/tmi.2020.3017275","title":"Direct Quantification of Coronary Artery Stenosis Through Hierarchical Attentive Multi-View Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Stenosis; Artificial intelligence; Segmentation; Medicine; Feature (linguistics); Computer science; Radiology; Coronary artery disease; Artery; Pattern recognition (psychology); Computer vision; Cardiology","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001894346,0.0001741453,0.0003821329,0.00008837183,0.0001444506,0.00001434614,0.0001167525,0.00008262075,0.001303141],"category_scores_gemma":[0.0002199325,0.0001591195,0.0003026238,0.0003022795,0.0002493706,0.0001401769,0.000003835042,0.0007033012,0.0000996886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004497567,"about_ca_system_score_gemma":0.0001039899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003344522,"about_ca_topic_score_gemma":0.000005603877,"domain_scores_codex":[0.9981708,0.0001517992,0.0005315116,0.0003644821,0.0005524482,0.0002289395],"domain_scores_gemma":[0.998828,0.0004445532,0.00009833722,0.0001934766,0.0001305042,0.0003051256],"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":[0.001270875,0.006704034,0.02156737,0.001307626,0.0009414501,0.001225122,0.005036043,0.002693618,0.02424806,0.0001706626,0.001667375,0.9331678],"study_design_scores_gemma":[0.02268587,0.005091734,0.1665712,0.0109505,0.00393175,0.001418989,0.009071685,0.6546689,0.0996142,0.0001177375,0.02379767,0.002079729],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06920674,0.000392306,0.9185113,0.01054947,0.0003474383,0.0003168839,0.00002784535,0.0001481774,0.000499797],"genre_scores_gemma":[0.9951203,0.0006174479,0.002327468,0.001585211,0.00007481043,0.00003715323,0.00002717096,0.00003015544,0.0001803077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.931088,"threshold_uncertainty_score":0.9996098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04891776891529277,"score_gpt":0.3242683476380483,"score_spread":0.2753505787227555,"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."}}