{"id":"W3126538905","doi":"10.3174/ajnr.a6970","title":"A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images","year":2021,"lang":"en","type":"article","venue":"American Journal of Neuroradiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Janssen Alzheimer Immunotherapy Research And Development; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Health Sciences, University of Arizona; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Hyperintensity; Fluid-attenuated inversion recovery; Convolutional neural network; Pattern recognition (psychology); White matter; Artificial intelligence; Sørensen–Dice coefficient; Segmentation; Medicine; Magnetic resonance imaging; Computer science; Radiology; Image segmentation","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":[0.0008944111,0.001014162,0.0005809811,0.0005334965,0.0003106419,0.0004167489,0.0009442772,0.0006588654,0.0009512745],"category_scores_gemma":[0.001149252,0.0003943603,0.0009772805,0.0003801158,0.0003449234,0.0007499087,0.0009616227,0.0009477523,0.000411439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006034143,"about_ca_system_score_gemma":0.001002928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0106851,"about_ca_topic_score_gemma":0.01883109,"domain_scores_codex":[0.9997702,0.00003834928,0.000009632163,0.0000791117,0.00005538536,0.00004728969],"domain_scores_gemma":[0.9996545,0.00007588451,0.00004303044,0.00007417785,0.000111151,0.00004117322],"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":[0.0005561998,0.0002650811,0.01038367,0.000105478,0.0004962134,0.0003129528,0.0001156925,0.437903,0.04397544,0.002170956,0.008767303,0.494948],"study_design_scores_gemma":[0.000006940047,0.00006926232,0.001440935,0.000008680844,0.00004417322,0.00005609974,0.00001143902,0.9897254,0.007238226,0.0006981394,0.0006883725,0.00001234489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3587624,0.001907978,0.6281549,0.0005518068,0.0002145915,0.00009357578,0.0008177012,0.006409669,0.003087416],"genre_scores_gemma":[0.8497457,0.0005371076,0.1437073,0.000299994,0.00006418028,0.00006647073,0.001633067,0.00021677,0.003729328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0106851,"threshold_uncertainty_score":0.02124584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01841858073840959,"score_gpt":0.2799579750883418,"score_spread":0.2615393943499322,"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."}}