{"id":"W4400768355","doi":"10.1016/j.media.2024.103278","title":"Generating multi-pathological and multi-modal images and labels for brain MRI","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"EPSRC Centre for Doctoral Training in Medical Imaging; Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Avid Radiopharmaceuticals; Genentech; Royal Academy of Engineering; IXICO; H. Lundbeck A/S; Centre For Medical Engineering, King’s College London; Servier; Eisai; King's College London; National Institutes of Health; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Nvidia; Wellcome Trust; University of Southern California; Pfizer; BioClinica; Biogen; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; European Commission; National Center for Advancing Translational Sciences; Medical Research Council; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer's Association","keywords":"Computer science; Segmentation; Artificial intelligence; Categorical variable; Generative model; Synthetic data; Modal; Pattern recognition (psychology); Machine learning; Generative grammar","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":[0.001444358,0.0007153712,0.0004496179,0.0007367244,0.0002585134,0.0009158873,0.0009856937,0.001134454,0.001775817],"category_scores_gemma":[0.003748924,0.0004981291,0.0008832273,0.0005438339,0.001021973,0.0008976464,0.001199937,0.001806147,0.0007363528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007383459,"about_ca_system_score_gemma":0.0005002465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001090743,"about_ca_topic_score_gemma":0.002633099,"domain_scores_codex":[0.9995373,0.0001791795,0.00001374818,0.0001408275,0.00009361475,0.00003536079],"domain_scores_gemma":[0.9989611,0.0005676916,0.00009624934,0.0002396486,0.0000816725,0.00005367703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005472918,0.0002060961,0.005108506,0.0002868341,0.0001477571,0.0006229839,0.0003203255,0.6767379,0.04929911,0.03047998,0.009797572,0.2264458],"study_design_scores_gemma":[0.00001659759,0.00004995145,0.0006572049,0.0000214833,0.00001249282,0.0003469584,0.00003844214,0.960806,0.01294424,0.02278677,0.002296482,0.00002343789],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04186599,0.0003767846,0.9528108,0.0008875409,0.0001019125,0.00009504419,0.0006229011,0.001363298,0.001875734],"genre_scores_gemma":[0.5634788,0.0004925773,0.4284463,0.0007090786,0.0001105836,0.0001926073,0.002052598,0.0006127827,0.003904722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001775817,"threshold_uncertainty_score":0.007638574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0184652090631952,"score_gpt":0.3049406073021934,"score_spread":0.2864753982389982,"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."}}