{"id":"W4393336171","doi":"10.48550/arxiv.2403.19508","title":"Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"HORIZON EUROPE Framework Programme; Circle Cardiovascular Imaging; Barts Health NHS Trust; National Institute for Health and Care Research; Medical Research Council; Barts Charity; Queen Mary University of London","keywords":"Debiasing; Diffusion; Computer science; Psychology; Cognitive science; Physics; Thermodynamics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004644709,0.0009895755,0.0009976332,0.00067535,0.0005254032,0.001269283,0.002132326,0.001437172,0.002112428],"category_scores_gemma":[0.0158001,0.0004653159,0.0008258755,0.0007457965,0.001305041,0.001860977,0.002293505,0.00258253,0.0008725471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205166,"about_ca_system_score_gemma":0.001222278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002919706,"about_ca_topic_score_gemma":0.004904482,"domain_scores_codex":[0.9989975,0.0003839986,0.00005666864,0.0002704167,0.0002073272,0.00008404766],"domain_scores_gemma":[0.9946421,0.003040274,0.0004648555,0.0009507332,0.0006409602,0.0002610368],"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":[0.000861932,0.0003558414,0.004225443,0.0002185733,0.00009783595,0.0002127598,0.0003654773,0.7120156,0.01692338,0.01853761,0.009345335,0.2368402],"study_design_scores_gemma":[0.00001865939,0.00003611596,0.0001752897,0.000008120245,0.000005240845,0.00002351285,0.00001155701,0.988547,0.002465789,0.007947236,0.0007530501,0.000008400836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03643117,0.0005033326,0.9581249,0.001061683,0.0001844509,0.0001255233,0.0005166372,0.002023698,0.001028591],"genre_scores_gemma":[0.6344361,0.0004036893,0.3559729,0.001092848,0.0003193662,0.0004131528,0.00223495,0.0005597786,0.004567275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004644709,"threshold_uncertainty_score":0.02456385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1310471993832416,"score_gpt":0.2765588862868102,"score_spread":0.1455116869035686,"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."}}