{"id":"W3091088513","doi":"10.1016/j.media.2020.101916","title":"Fully automated left atrium segmentation from anatomical cine long-axis MRI sequences using deep convolutional neural network with unscented Kalman filter","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Canadian VIGOUR Centre","funders":"Servier; Mitacs","keywords":"Artificial intelligence; Convolutional neural network; Segmentation; Computer science; Kalman filter; Sørensen–Dice coefficient; Pattern recognition (psychology); Computer vision; Artificial neural network; Image segmentation; Deep learning; Ground truth","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004502192,0.0008173707,0.0007924088,0.0009241222,0.0003033252,0.0008522803,0.0006059914,0.0009868484,0.001463467],"category_scores_gemma":[0.0008761899,0.0006575559,0.00085646,0.0004832054,0.0002470022,0.0004676493,0.0006704323,0.0008933009,0.001010827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004226557,"about_ca_system_score_gemma":0.001482176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01179075,"about_ca_topic_score_gemma":0.0302868,"domain_scores_codex":[0.9998159,0.00002207188,0.00001229518,0.00006431864,0.00004760426,0.00003797153],"domain_scores_gemma":[0.9997211,0.000102647,0.00003720801,0.00003561183,0.00007899232,0.00002439665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006302826,0.0001502424,0.004527122,0.0003158833,0.0002260417,0.0004628635,0.0002244384,0.1596861,0.1226802,0.002794626,0.008315279,0.6999869],"study_design_scores_gemma":[0.0000121244,0.00003671114,0.001741232,0.00002594946,0.00003338873,0.0001989628,0.00001955246,0.978501,0.01603455,0.001475491,0.001902294,0.00001870649],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02604352,0.0006714826,0.9692806,0.0001508891,0.00005222965,0.00004584695,0.0003583938,0.002585215,0.000811728],"genre_scores_gemma":[0.4010901,0.001025078,0.5895249,0.000264087,0.0001078732,0.0001161999,0.002063606,0.0006381238,0.005170028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01179075,"threshold_uncertainty_score":0.02344424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01682712962209134,"score_gpt":0.3152889253414733,"score_spread":0.298461795719382,"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."}}