{"id":"W2944052783","doi":"10.1109/tmi.2019.2914656","title":"Adaptive Augmentation of Medical Data Using Independently Conditional Variational Auto-Encoders","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Segmentation; Sørensen–Dice coefficient; Generative model; Pattern recognition (psychology); Image segmentation; Residual; Latent variable; Data modeling; Medical imaging; Artificial neural network; Test data; Machine learning; Generative grammar; Algorithm","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001109634,0.0001532516,0.0001952398,0.0002571441,0.0001492889,0.0000556308,0.001341186,0.0001463784,0.001674461],"category_scores_gemma":[0.00004776583,0.0001590507,0.00006656819,0.0004348941,0.0001615313,0.001376208,0.00002747501,0.0005886274,0.00007046185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002367267,"about_ca_system_score_gemma":0.001043861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002493429,"about_ca_topic_score_gemma":0.000029397,"domain_scores_codex":[0.9953157,0.000159848,0.0004572694,0.0005698873,0.003253287,0.0002439549],"domain_scores_gemma":[0.9984907,0.0003866217,0.0001748504,0.0005891687,0.0001291903,0.0002294693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000317784,0.001687647,0.001111119,0.0002131816,0.0007932425,0.0001738244,0.002436513,0.436767,0.005256718,0.02081203,0.002270522,0.5281604],"study_design_scores_gemma":[0.001078795,0.00004063989,0.0002850475,0.0001236393,0.00002380411,0.0001088317,0.000116726,0.994848,0.001827872,0.001300646,0.00009536434,0.0001506009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003517844,0.00002353607,0.9916022,0.002498378,0.001810736,0.0001881884,0.00005263514,0.0001095215,0.0001969869],"genre_scores_gemma":[0.977616,0.00001813038,0.02133128,0.0008411429,0.0001122214,0.00001191824,0.00002535265,0.00001461709,0.00002941292],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740981,"threshold_uncertainty_score":0.9992381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04094005066835326,"score_gpt":0.3249513722629255,"score_spread":0.2840113215945723,"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."}}