{"id":"W2757633676","doi":"10.1016/j.media.2017.09.005","title":"Full left ventricle quantification via deep multitask relationships learning","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":161,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Softmax function; Multi-task learning; Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology); Classifier (UML); Convolutional neural network; Ventricle; Machine learning; Task (project management); Cardiology; Medicine","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001061248,0.0001221205,0.0003827517,0.0002629715,0.0006676643,0.0001367302,0.0001772787,0.0001255059,0.0009682412],"category_scores_gemma":[0.01905605,0.0001104126,0.0003791849,0.0002919083,0.0002262777,0.0001676559,0.00007400298,0.0005714475,0.0006157886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005183289,"about_ca_system_score_gemma":0.00006000157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002608131,"about_ca_topic_score_gemma":0.0001085866,"domain_scores_codex":[0.9982912,0.0001376703,0.0003246268,0.0003141997,0.0006889049,0.0002433922],"domain_scores_gemma":[0.9980194,0.0004453027,0.000190433,0.0007589257,0.0002265737,0.0003593536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004455298,0.0001881675,0.9746234,0.00002821621,0.0008271983,0.000284442,0.000244253,0.0001436988,0.001277613,0.00003586107,0.001231903,0.02107071],"study_design_scores_gemma":[0.0008844348,0.00004378064,0.8136407,0.00003945623,0.004158282,0.00004625551,0.0001680924,0.1774699,0.0006697802,0.00005722202,0.002659714,0.0001623404],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3632933,0.0008664184,0.6168538,0.01184078,0.0002872272,0.0002146733,0.000006383243,0.0002261051,0.006411282],"genre_scores_gemma":[0.9957969,0.00008255114,0.002696568,0.0001710654,0.0002412148,0.000006205356,0.0001846028,0.00001662311,0.0008043158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6325035,"threshold_uncertainty_score":0.999945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02350027649408587,"score_gpt":0.3230192351613346,"score_spread":0.2995189586672488,"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."}}