{"id":"W2590760288","doi":"10.1016/j.knosys.2017.02.025","title":"Automatic computation of regions of interest by robust principal component analysis. Application to automatic dementia diagnosis","year":2017,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Pfizer; Novartis Pharmaceuticals Corporation; Ministerio de Ciencia e Innovación; F. Hoffmann-La Roche; GE Healthcare; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Takeda Pharmaceutical Company; Eli Lilly and Company; Bristol-Myers Squibb; Merck","keywords":"Computer science; Principal component analysis; Computation; Dementia; Component (thermodynamics); Artificial intelligence; Data mining; Pattern recognition (psychology); Algorithm; Medicine; Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009433159,0.0001928462,0.0005768859,0.0004979574,0.0001882638,0.0001755937,0.001394153,0.00008135008,0.00001275502],"category_scores_gemma":[0.0002229326,0.0001851268,0.0001648138,0.0006384035,0.0001455178,0.0002424523,0.0002372844,0.00008660906,0.00003265099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001240941,"about_ca_system_score_gemma":0.00009975186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003473386,"about_ca_topic_score_gemma":0.0001236426,"domain_scores_codex":[0.9975892,0.0003170341,0.001059941,0.000425054,0.0003948616,0.0002138743],"domain_scores_gemma":[0.9966438,0.0002693926,0.001224163,0.001282725,0.0003836174,0.0001962481],"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":[0.00004805864,0.01090185,0.1749187,0.01556411,0.006287606,0.00002193415,0.01108937,0.06003494,0.09063511,0.0279967,0.07372309,0.5287785],"study_design_scores_gemma":[0.0003926382,0.0001183752,0.009091009,0.0004736344,0.0002325714,8.646472e-7,0.00004111234,0.9600415,0.02927325,0.00004641698,0.0001144141,0.0001741767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05047636,0.0001828691,0.9475092,0.0002048394,0.0002098836,0.001027014,0.00001848617,0.0002350713,0.0001362989],"genre_scores_gemma":[0.936044,0.000002025278,0.06334224,0.000033003,0.00001995957,0.0004939284,0.00003750825,0.00001238146,0.00001499835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9000066,"threshold_uncertainty_score":0.7549251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05652803893087573,"score_gpt":0.3291563381050803,"score_spread":0.2726282991742046,"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."}}