{"id":"W4283020131","doi":"10.1016/j.compmedimag.2022.102092","title":"A contrastive consistency semi-supervised left atrium segmentation model","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Hausdorff distance; Jaccard index; Leverage (statistics); Semi-supervised learning","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":[0.0004258688,0.000145431,0.0003234644,0.0001765522,0.000323557,0.00003363841,0.00007993418,0.00003690752,0.0001858514],"category_scores_gemma":[0.0001074949,0.0001347592,0.0001289622,0.0001987349,0.0001712702,0.00007726651,0.0002081982,0.0002774016,0.00000190689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003013256,"about_ca_system_score_gemma":0.0001263647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009890812,"about_ca_topic_score_gemma":6.402076e-7,"domain_scores_codex":[0.9984888,0.00009438343,0.0003145702,0.0002814661,0.0006089631,0.0002117862],"domain_scores_gemma":[0.999297,0.0001717588,0.00007769305,0.0001386537,0.00006991385,0.0002449699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002978188,0.0003542324,0.6367399,0.001083821,0.001405205,0.001177044,0.006944643,0.001502938,0.01913925,0.03734415,0.03414059,0.2571901],"study_design_scores_gemma":[0.006141239,0.00008580169,0.009783413,0.00004906654,0.0001905693,0.0001586163,0.0004309212,0.9751323,0.00003207985,0.00130681,0.006492666,0.0001965182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4762643,0.00246942,0.4573299,0.0589707,0.00152465,0.001385097,0.00004410367,0.0005435652,0.001468268],"genre_scores_gemma":[0.98795,0.0002775944,0.004058479,0.00694288,0.000282779,0.000006976586,0.0001396736,0.0000196884,0.0003219878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9736294,"threshold_uncertainty_score":0.5495322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03366524962674061,"score_gpt":0.3082796713224614,"score_spread":0.2746144216957208,"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."}}