{"id":"W2789256791","doi":"10.1016/j.compmedimag.2018.02.002","title":"Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":85,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Janssen Alzheimer Immunotherapy Research And Development; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Lembaga Pengelola Dana Pendidikan; H. Lundbeck A/S; Servier; Eisai; Johnson and Johnson Pharmaceutical Research and Development; Mrs Gladys Row Fogo Charitable Trust; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation","keywords":"Artificial intelligence; Convolutional neural network; Boltzmann machine; Segmentation; Pattern recognition (psychology); Hyperintensity; Computer science; Deep learning; Support vector machine; Magnetic resonance imaging; Random forest; Similarity (geometry); White matter; Medicine; Radiology","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":[0.0005748346,0.0004412817,0.000225435,0.001814028,0.000228789,0.000802459,0.0003587618,0.0006274135,0.0006303987],"category_scores_gemma":[0.001796133,0.000314,0.0002857415,0.0004709435,0.0003615123,0.0003877326,0.0003233967,0.0002386275,0.0002043114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004051256,"about_ca_system_score_gemma":0.0006630913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01080841,"about_ca_topic_score_gemma":0.01838995,"domain_scores_codex":[0.9998944,0.0000184407,0.00001418998,0.00002463016,0.00001826404,0.00003015774],"domain_scores_gemma":[0.9996681,0.0001421899,0.00005686855,0.00003162071,0.00005856553,0.00004274473],"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":[0.005833471,0.0004649604,0.198375,0.0006621548,0.0003888177,0.006805757,0.0008812739,0.05654742,0.2379839,0.002061401,0.00366918,0.4863267],"study_design_scores_gemma":[0.00006591092,0.0003593636,0.2384947,0.0001285806,0.0003424843,0.006220493,0.0006255858,0.6398941,0.1078407,0.003298077,0.002672266,0.00005780409],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756867,0.0007660915,0.02215342,0.0002105707,0.00001956199,0.00004573273,0.0002856225,0.0001528579,0.0006795322],"genre_scores_gemma":[0.9853333,0.0004252389,0.01307891,0.00003229484,0.00002140893,0.00001175303,0.0003219814,0.00004904583,0.0007260884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01080841,"threshold_uncertainty_score":0.02149099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02570801081130878,"score_gpt":0.294413530707176,"score_spread":0.2687055198958672,"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."}}