{"id":"W2889829193","doi":"10.1371/journal.pone.0196945","title":"Improving the SIENA performance using BEaST brain extraction","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"NeuroRx Research (Canada); McGill University; Montreal Neurological Institute and Hospital","funders":"Genentech; National Institutes of Health; Mitacs; Eisai; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Eli Lilly and Company; U.S. Department of Defense; Compute Canada; Northern California Institute for Research and Education; Acorda Therapeutics; McGill University; Pfizer; Biogen; BioClinica; Sanofi Genzyme; F. Hoffmann-La Roche; University of Southern California; Sanofi; Alzheimer's Disease Neuroimaging Initiative; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Reproducibility; Brain size; Medicine; Segmentation; Nuclear medicine; Magnetic resonance imaging; Mathematics; Computer science; Artificial intelligence; 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":[0.003048612,0.001572157,0.001458474,0.002388045,0.0006245,0.002035366,0.001701188,0.001141032,0.00401075],"category_scores_gemma":[0.008936442,0.0008515765,0.00185567,0.001222447,0.0004643062,0.00199981,0.002100689,0.001124951,0.002949655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005574647,"about_ca_system_score_gemma":0.00127212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005462157,"about_ca_topic_score_gemma":0.01283937,"domain_scores_codex":[0.9986664,0.0002323014,0.0001183153,0.0003994787,0.0004623713,0.0001211185],"domain_scores_gemma":[0.9980752,0.0006729825,0.0001870274,0.000378427,0.0006236001,0.00006277036],"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":[0.001567946,0.0002260216,0.01566171,0.0005804611,0.0009636929,0.000360532,0.0005000214,0.02639279,0.1180784,0.004824592,0.0136465,0.8171974],"study_design_scores_gemma":[0.0001941065,0.0005439881,0.04072371,0.00008883318,0.0006215914,0.002324805,0.0002472573,0.7583227,0.1536052,0.01224384,0.03081989,0.0002640845],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0570422,0.0008662676,0.9198776,0.0002930264,0.0001202502,0.0002541089,0.001416786,0.0184215,0.001708157],"genre_scores_gemma":[0.1897658,0.0004427819,0.7980328,0.0003099249,0.00006296603,0.0004326847,0.004908434,0.001714982,0.004329502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005462157,"threshold_uncertainty_score":0.01612282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06385642346107932,"score_gpt":0.2833986253565527,"score_spread":0.2195422018954734,"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."}}