{"id":"W3168477867","doi":"10.1101/2021.06.04.446768","title":"Automated Generation of Cerebral Blood Flow Maps Using Deep Learning and Multiple Delay Arterial Spin-Labelled MRI","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Heart and Stroke Foundation; University of Toronto; Sunnybrook Health Science Centre","funders":"Sunnybrook Research Institute","keywords":"Ground truth; Generalizability theory; Arterial spin labeling; Convolutional neural network; Deep learning; Cerebral blood flow; Dropout (neural networks); Computer science; Pipeline (software); Artificial intelligence; Magnetic resonance imaging; Artificial neural network; Pattern recognition (psychology); Machine learning; Medicine; Cardiology; Mathematics; Statistics; 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":[0.0009547184,0.0006190386,0.0003551314,0.0007752433,0.0002023466,0.0007344066,0.0008098701,0.0006290888,0.001218353],"category_scores_gemma":[0.002678539,0.0003785506,0.0004042223,0.0003478498,0.0002152649,0.0005674062,0.000494133,0.0006995158,0.0005091873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000693502,"about_ca_system_score_gemma":0.0008758315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006479484,"about_ca_topic_score_gemma":0.009994567,"domain_scores_codex":[0.9998497,0.00003981825,0.00000699073,0.00004780186,0.0000319804,0.00002371225],"domain_scores_gemma":[0.9994426,0.0002335649,0.00008446043,0.00006845459,0.0001395528,0.00003130247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007668079,0.0003169865,0.01074343,0.0002483753,0.0002152051,0.0003592151,0.0001562219,0.2892819,0.09928221,0.00188144,0.005183996,0.5915643],"study_design_scores_gemma":[0.00001985502,0.00006594406,0.002825713,0.00001449248,0.00002623559,0.0001419273,0.00001460297,0.9665468,0.02802829,0.001577758,0.00071896,0.00001955005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2028031,0.0005275019,0.7891675,0.0003250019,0.00007422015,0.0001360447,0.0007329284,0.004964132,0.001269479],"genre_scores_gemma":[0.7185176,0.0002392485,0.2783853,0.0001659081,0.00003774132,0.0001125031,0.0007820933,0.0002415419,0.001518084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006479484,"threshold_uncertainty_score":0.01288354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01961412944569689,"score_gpt":0.2669270168681745,"score_spread":0.2473128874224776,"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."}}