{"id":"W3164110046","doi":"10.1016/j.media.2021.102106","title":"Conditional generation of medical images via disentangled adversarial inference","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"","keywords":"Inference; Computer science; Latent variable; Artificial intelligence; Regularization (linguistics); Machine learning; Adversarial system; Image (mathematics); Unsupervised learning; Variable (mathematics); Pattern recognition (psychology); Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008881918,0.0001911718,0.0005425227,0.0002099678,0.0001406289,0.0001470581,0.0009105556,0.0001938631,0.007729854],"category_scores_gemma":[0.002147227,0.000166789,0.0004326852,0.001782575,0.0002977963,0.000574695,0.0004723368,0.0002494678,0.0000454907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003529034,"about_ca_system_score_gemma":0.000538555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001492282,"about_ca_topic_score_gemma":0.0002078966,"domain_scores_codex":[0.9955598,0.0004549062,0.0006164031,0.0005765437,0.002493282,0.000299035],"domain_scores_gemma":[0.9978969,0.0004095731,0.0001824753,0.000569197,0.0005138604,0.000428009],"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":[0.00009697467,0.005524798,0.02373502,0.000213451,0.02036954,0.009044494,0.002204635,0.02118109,0.1846149,0.05036743,0.1017917,0.580856],"study_design_scores_gemma":[0.0006219537,0.00002757478,0.001812452,0.00001680509,0.0004501544,0.00001326103,0.00002505591,0.9603974,0.03488422,0.0008353849,0.0006961533,0.0002196217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002148539,0.0002100017,0.9896024,0.007007162,0.00031598,0.00005276988,0.00002056698,0.00004354275,0.0005989961],"genre_scores_gemma":[0.9665704,0.000175078,0.03113148,0.0009510092,0.0006914663,0.00001244131,0.0003035643,0.000008138629,0.0001564578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9644218,"threshold_uncertainty_score":0.9931772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01862280401033647,"score_gpt":0.2944943717499336,"score_spread":0.2758715677395972,"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."}}