{"id":"W3010232800","doi":"10.1007/s11548-020-02131-0","title":"Recursive multiresolution convolutional neural networks for 3D aortic valve annulus planimetry","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre; University of Ottawa","funders":"","keywords":"Convolutional neural network; Aortic valve replacement; Stenosis; Artificial intelligence; Aortic valve; Cardiac skeleton; Medicine; Orientation (vector space); Aortic valve stenosis; Computer science; Valve replacement; Radiology; Computer vision; Pattern recognition (psychology); Cardiology; Mathematics; Geometry","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":[],"consensus_categories":[],"category_scores_codex":[0.0001373611,0.0001224319,0.0004191096,0.0001353527,0.00005048749,0.00001957448,0.00006606797,0.00009734223,0.00001857708],"category_scores_gemma":[0.0001405894,0.0001023382,0.0009308161,0.00005992605,0.00008180646,0.00009142135,0.00002690842,0.0001652983,0.000001064234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006515784,"about_ca_system_score_gemma":0.00009495528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002621845,"about_ca_topic_score_gemma":1.363401e-7,"domain_scores_codex":[0.9989837,0.00008589101,0.0004334604,0.0001554234,0.0001887769,0.0001527391],"domain_scores_gemma":[0.9983203,0.0006794957,0.0002872309,0.00004724503,0.0004586069,0.0002070647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005475635,0.0002985367,0.8894483,0.00003510618,0.007660951,0.000441889,0.0001002492,0.002118107,0.0000390319,0.0001473931,0.02186572,0.07236905],"study_design_scores_gemma":[0.002217908,0.0003719637,0.8509586,0.00006758016,0.0004771406,0.002097094,0.0000214527,0.142666,0.000003810365,0.00004691441,0.0009739644,0.00009765252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8435423,0.003894849,0.1451893,0.003755534,0.003321124,0.0001875254,0.00007051574,0.00002080133,0.00001805937],"genre_scores_gemma":[0.9920294,0.0001475091,0.002833176,0.002747608,0.002074927,0.000004043661,0.0001492936,0.000009895474,0.000004157309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1484871,"threshold_uncertainty_score":0.4173231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02443783787942991,"score_gpt":0.3133272082637731,"score_spread":0.2888893703843431,"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."}}