{"id":"W3017135785","doi":"10.1109/tnnls.2020.2984955","title":"Multitask Learning for Estimating Multitype Cardiac Indices in MRI and CT Based on Adversarial Reverse Mapping","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Medical Research Council; Special Project for Research and Development in Key areas of Guangdong Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Deep learning; Multi-task learning; Magnetic resonance imaging; Adversarial system; Pattern recognition (psychology); Modality (human–computer interaction); Machine learning; Task (project management); Radiology; Medicine; Engineering","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":[0.0002268822,0.0001713692,0.0003306939,0.00009766792,0.0004042347,0.00004139147,0.00003576532,0.00008076296,0.000003080844],"category_scores_gemma":[0.00004244974,0.0001621914,0.00007529755,0.0002080192,0.00004292565,0.00007695879,0.000001675563,0.0008388801,9.255638e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003349198,"about_ca_system_score_gemma":0.000013139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001158278,"about_ca_topic_score_gemma":0.000003878588,"domain_scores_codex":[0.9989377,0.0001128311,0.0002633951,0.0003549167,0.0001122786,0.0002188417],"domain_scores_gemma":[0.9992149,0.0004148296,0.0001188751,0.0000880867,0.00003164723,0.0001316716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000170416,0.00002547825,0.001045909,0.0001233621,0.00001138494,0.000006305844,0.0002245095,0.9799154,0.0002564848,0.000005651314,0.00003076444,0.01818429],"study_design_scores_gemma":[0.001170295,0.0004901437,0.0002637074,0.0003663218,0.00004726647,0.000006968408,0.0006105739,0.9938107,0.00003867363,6.958398e-7,0.003045186,0.0001494355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05244511,0.0001300741,0.9453746,0.0005785186,0.0002445913,0.001003259,0.000005873756,0.0001856342,0.00003231115],"genre_scores_gemma":[0.9859843,0.00006071867,0.01322547,0.0002049443,0.0002465066,0.0001605104,0.00001327264,0.00003210276,0.00007221378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335392,"threshold_uncertainty_score":0.6613972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02348687710062469,"score_gpt":0.2770911227830383,"score_spread":0.2536042456824136,"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."}}