{"id":"W4387891881","doi":"10.48550/arxiv.2310.13349","title":"DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"False discovery rate; Voxel; Neuroimaging; Computer science; Artificial intelligence; Segmentation; Multiple comparisons problem; Deep learning; Pattern recognition (psychology); Machine learning; Mathematics; Psychology; Neuroscience","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03194593,0.0007000134,0.002266112,0.000244781,0.0001738983,0.0006014654,0.002322905,0.0005646066,0.00002230657],"category_scores_gemma":[0.5760843,0.0006439271,0.0005823612,0.0002593568,0.0001909211,0.0001721969,0.002292405,0.001944203,0.00002404243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001407141,"about_ca_system_score_gemma":0.0001905707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003812537,"about_ca_topic_score_gemma":0.00003238446,"domain_scores_codex":[0.9878362,0.006014943,0.002086004,0.002195239,0.0006333658,0.001234198],"domain_scores_gemma":[0.7549537,0.2406426,0.001171333,0.002698089,0.0002224936,0.0003117987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003837535,0.001035609,0.001493981,0.009527478,0.003051572,0.0002720041,0.0001217046,0.01966743,0.00005178809,0.04134855,0.01621701,0.9033753],"study_design_scores_gemma":[0.002886253,0.000030917,0.002578911,0.0001110221,0.001197901,0.000001357158,0.00001243029,0.2236076,0.00007430069,0.7671603,0.001739505,0.0005995178],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001117737,0.0001079441,0.9817259,0.00283662,0.003776266,0.007310266,0.00322569,0.0007681865,0.0001373819],"genre_scores_gemma":[0.008079092,0.00003760369,0.9728062,0.00103542,0.001400856,0.01485731,0.0002734014,0.0003939543,0.00111619],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9027758,"threshold_uncertainty_score":0.9996012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6565402295534531,"score_gpt":0.5467922017018985,"score_spread":0.1097480278515547,"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."}}