{"id":"W2142366297","doi":"10.1371/journal.pone.0070059","title":"Using Manifold Learning for Atlas Selection in Multi-Atlas Segmentation","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; Medical Research Council; National Institute of Biomedical Imaging and Bioengineering; University of California, Los Angeles; Canadian Institutes of Health Research; National Institutes of Health; Servier; Eisai; Eli Lilly and Company; Alzheimer's Research Trust; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; University of California, San Diego; Biogen; BioClinica; University College London Hospitals NHS Foundation Trust; Engineering and Physical Sciences Research Council; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; F. Hoffmann-La Roche; Versus Arthritis; AstraZeneca; Bristol-Myers Squibb; Synarc; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Atlas (anatomy); Isomap; Nonlinear dimensionality reduction; Segmentation; Artificial intelligence; Manifold alignment; Computer science; Embedding; Pattern recognition (psychology); Manifold (fluid mechanics); Selection (genetic algorithm); Machine learning; Dimensionality reduction; Biology; Anatomy","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":[0.01036747,0.002402942,0.002767488,0.006029494,0.001961129,0.002959547,0.002215168,0.002769223,0.002586887],"category_scores_gemma":[0.0180576,0.001125009,0.002756145,0.004451667,0.002009205,0.003616931,0.003225716,0.002538207,0.001878199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001728918,"about_ca_system_score_gemma":0.002356182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00518738,"about_ca_topic_score_gemma":0.007609499,"domain_scores_codex":[0.9945478,0.002197371,0.0003770863,0.001372125,0.00113725,0.0003683866],"domain_scores_gemma":[0.9927186,0.003310406,0.0007450502,0.001502944,0.00149707,0.0002259334],"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":[0.0006284393,0.0002550015,0.006895897,0.0006499191,0.0007224753,0.0004287783,0.00117435,0.3473491,0.03734652,0.01413343,0.009779986,0.5806361],"study_design_scores_gemma":[0.00005078689,0.0002071768,0.00306928,0.00007967059,0.0001191355,0.0004094015,0.0002713056,0.9327931,0.02761099,0.02919755,0.006089321,0.0001024033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02571575,0.0009233335,0.9678345,0.0002187917,0.00009115107,0.0002268987,0.0001813235,0.003889628,0.0009185745],"genre_scores_gemma":[0.2116081,0.0004574025,0.7843691,0.000153156,0.00006200444,0.000227064,0.0009256797,0.001191856,0.001005704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01036747,"threshold_uncertainty_score":0.05482906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1120585600870232,"score_gpt":0.3153095464240938,"score_spread":0.2032509863370706,"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."}}