{"id":"W4366826222","doi":"10.1101/2023.04.20.537642","title":"GAN-MAT: Generative Adversarial Network-based Microstructural Profile Covariance Analysis Toolbox","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Ministry of Science and ICT, South Korea; Canada First Research Excellence Fund; McGill University; National Research Foundation of Korea; Institute for Information and Communications Technology Promotion; Inha University; National Research Foundation; Institute for Basic Science; Seoul National University","keywords":"Human Connectome Project; Toolbox; Diffusion MRI; Computer science; Covariance; Artificial intelligence; Magnetic resonance imaging; Pattern recognition (psychology); Generative adversarial network; Neuroimaging; Neuroscience; Functional connectivity; Deep learning; Mathematics; Psychology; Medicine; Radiology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007188925,0.001119325,0.0006197114,0.0004490454,0.0001636934,0.0004951403,0.001284985,0.0009462991,0.006597017],"category_scores_gemma":[0.00240499,0.0004163554,0.0007615823,0.0002851094,0.000395074,0.0005155079,0.0009448077,0.001838466,0.002299075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005297952,"about_ca_system_score_gemma":0.0008302317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004063085,"about_ca_topic_score_gemma":0.006889768,"domain_scores_codex":[0.9998191,0.00006222889,0.000008136361,0.00004793511,0.00004130622,0.00002127783],"domain_scores_gemma":[0.9995471,0.0002806094,0.00003167069,0.00005026823,0.00006498732,0.00002540221],"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":[0.00009291875,0.00003955085,0.0006143322,0.0001235276,0.0001000014,0.0001355629,0.00003535678,0.8843579,0.003131746,0.009596913,0.01528292,0.08648925],"study_design_scores_gemma":[0.000005464903,0.000007018407,0.00004542468,0.000004920977,0.000003347278,0.00002268153,0.000001815735,0.995893,0.0004886977,0.002516636,0.001007775,0.000003274203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004142318,0.0003178102,0.9851428,0.0002080013,0.00005430915,0.0000548647,0.0006330637,0.007525047,0.001921821],"genre_scores_gemma":[0.3175325,0.0006271818,0.6626886,0.0007852059,0.0001148481,0.0007518982,0.005072899,0.002558744,0.009868122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006597017,"threshold_uncertainty_score":0.02206922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03145048232743815,"score_gpt":0.2430390955637917,"score_spread":0.2115886132363535,"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."}}