{"id":"W3210987080","doi":"10.1002/jmri.27984","title":"Improving Sensitivity of Arterial Spin Labeling Perfusion <scp>MRI</scp> in Alzheimer's Disease Using Transfer Learning of Deep Learning‐Based <scp>ASL</scp> Denoising","year":2021,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Norman Cousins Center for Psychoneuroimmunology; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Northern California Institute for Research and Education; Pfizer; BioClinica; Biogen; GE Healthcare; Alzheimer's Association; Fujirebio US; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Roche; Merck; Alzheimer's Drug Discovery Foundation; Eisai Incorporated; Takeda Pharmaceutical Company; AbbVie; National Institute on Aging; Foundation for the National Institutes of Health","keywords":"Cerebral blood flow; Medicine; Magnetic resonance imaging; Arterial spin labeling; Nuclear medicine; Perfusion; Perfusion scanning; Artificial intelligence; Internal medicine; Radiology; Computer science","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":[0.002097726,0.0004775742,0.0003842391,0.0007030013,0.0001730905,0.0005269927,0.0004719335,0.0005843627,0.0005783747],"category_scores_gemma":[0.003672317,0.000193558,0.0004090873,0.000277147,0.0003074563,0.0004405479,0.0005002985,0.0005287419,0.0002157307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003857251,"about_ca_system_score_gemma":0.0004221675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002465837,"about_ca_topic_score_gemma":0.003637058,"domain_scores_codex":[0.999755,0.00008440847,0.00001644457,0.0000729302,0.0000437528,0.00002752862],"domain_scores_gemma":[0.9991041,0.0004648908,0.0001205502,0.00006959792,0.0001860902,0.00005486853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003244198,0.0006433809,0.1580227,0.0007829184,0.0008679809,0.0007913019,0.0004875925,0.1063269,0.1336199,0.001147905,0.004009123,0.590056],"study_design_scores_gemma":[0.0001171872,0.0009966076,0.08980562,0.0000931128,0.0003557347,0.001032659,0.0001636504,0.8420727,0.05940786,0.003466777,0.002417157,0.0000708888],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8695102,0.001835248,0.1255239,0.0004956845,0.00004815116,0.00008060264,0.0003988511,0.0005663786,0.001540933],"genre_scores_gemma":[0.9732847,0.0004578846,0.02510406,0.0001040295,0.00003856284,0.00003551687,0.0004253681,0.00004103623,0.0005089254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002465837,"threshold_uncertainty_score":0.01109397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01322848124755459,"score_gpt":0.2825893919342456,"score_spread":0.269360910686691,"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."}}