{"id":"W4200634542","doi":"10.1109/tmi.2022.3173669","title":"Echocardiography Segmentation With Enforced Temporal Consistency","year":2022,"lang":"en","type":"preprint","venue":"IEEE Transactions on Medical Imaging","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; LabEx PRIMES; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Labex; Agence Nationale de la Recherche; Compute Canada","keywords":"Segmentation; Artificial intelligence; Leverage (statistics); Cardiac cycle; Computer science; Pattern recognition (psychology); Convolutional neural network; Consistency (knowledge bases); Autoencoder; Regularization (linguistics); Deep learning; 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":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005415785,0.000416154,0.0007237667,0.000714472,0.0003566962,0.00005642868,0.0001597913,0.0002247827,0.004226944],"category_scores_gemma":[0.00001798926,0.0003401016,0.00120281,0.00049361,0.0002897966,0.0000768704,0.000008840029,0.002561466,0.00003001104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002760212,"about_ca_system_score_gemma":0.0007392917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003811294,"about_ca_topic_score_gemma":0.00001902226,"domain_scores_codex":[0.9961646,0.0001976366,0.0004960664,0.0007248936,0.002069934,0.0003468939],"domain_scores_gemma":[0.9983863,0.00009582527,0.0001392467,0.0007327776,0.0001325234,0.0005133242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004202593,0.002810515,0.09712564,0.002487124,0.01673247,0.005997682,0.003334622,0.05758025,0.0008450648,0.00005340392,0.01014752,0.7986831],"study_design_scores_gemma":[0.1289397,0.007214033,0.1052294,0.01949893,0.06496321,0.02216342,0.06306028,0.1744888,0.05109872,0.0007754709,0.3438933,0.01867463],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02919663,0.0003906316,0.9581377,0.002181507,0.004104115,0.001235117,0.00009186784,0.0005947065,0.004067743],"genre_scores_gemma":[0.9942467,0.0007795839,0.001650942,0.001754315,0.0002228387,0.0003350482,0.0002432071,0.00009233985,0.0006749989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9650501,"threshold_uncertainty_score":0.9999051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01339531173731523,"score_gpt":0.2729997696967166,"score_spread":0.2596044579594013,"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."}}