{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002042587,0.00008753403,0.0001202401,0.0001531406,0.00008323835,0.0001297143,0.0001883203,0.00005287161,0.00006821757],"category_scores_gemma":[0.0001393855,0.00009264567,0.00002350701,0.0002797703,0.0000122716,0.0008414611,0.00005643302,0.0001343071,0.00005397393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001271592,"about_ca_system_score_gemma":0.00002616976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001904666,"about_ca_topic_score_gemma":0.000017393,"domain_scores_codex":[0.9989793,0.00007324645,0.0002315921,0.0002519533,0.0002616866,0.0002022351],"domain_scores_gemma":[0.999547,0.00008105555,0.0001015924,0.00008957426,0.0001215058,0.00005926412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002446663,0.0004178454,0.004772869,0.00006393189,0.00002018341,8.524867e-7,0.0004374415,0.0001017845,0.9838334,0.000124689,0.0001272311,0.01009731],"study_design_scores_gemma":[0.0003508744,0.00007061246,0.001723333,0.00006448019,0.000007449534,9.332829e-7,0.000038913,0.4778751,0.5195763,0.0002004349,0.000003425236,0.00008807512],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1686166,0.00001276387,0.8303226,0.0001144681,0.00002061753,0.0006626808,1.996105e-7,0.0002066438,0.00004341121],"genre_scores_gemma":[0.2077955,0.000009409276,0.7914564,0.0001440205,0.00003205119,0.0001967366,0.000005774524,0.00001028111,0.0003498363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4777734,"threshold_uncertainty_score":0.3777981,"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."}}