{"id":"W2069494733","doi":"10.1371/journal.pone.0073021","title":"Diffusion Weighted Image Denoising Using Overcomplete Local PCA","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":447,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"Agence Nationale de la Recherche","keywords":"Noise reduction; Pattern recognition (psychology); Artificial intelligence; Noise (video); Computer science; Diffusion; Principal component analysis; Filter (signal processing); Non-local means; Diffusion MRI; Signal-to-noise ratio (imaging); Diffusion process; Mathematics; Image denoising; Image (mathematics); Computer vision; Statistics; Physics; Medicine; Magnetic resonance imaging; Radiology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002601689,0.0001078668,0.0001950121,0.00006189911,0.0001122031,0.000022301,0.00006959177,0.00003850846,0.0002106242],"category_scores_gemma":[0.00002558724,0.00009800578,0.00003509755,0.0001842337,0.00008107241,0.0001289111,0.00007574127,0.0001740018,0.0001176114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005273173,"about_ca_system_score_gemma":0.00001793188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006638363,"about_ca_topic_score_gemma":5.017787e-7,"domain_scores_codex":[0.9991931,0.00001200262,0.0001653022,0.0002239262,0.0002063558,0.0001993497],"domain_scores_gemma":[0.9993371,0.00003007629,0.0000545999,0.0003374503,0.0001363802,0.000104409],"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":[0.00001107148,0.0005928637,0.001928785,0.00006413346,0.0000181872,0.00000757342,0.00001935078,6.685349e-7,0.9946243,0.0002185852,0.000238799,0.002275662],"study_design_scores_gemma":[0.002160425,0.0003280042,0.03538295,0.001807822,0.0005680165,0.0001163816,0.00006410997,0.3048209,0.6396402,0.01266506,0.001785716,0.0006605135],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8471729,0.00004964973,0.1500419,0.001176529,0.000006320065,0.0005085344,0.000002874488,0.0002932622,0.0007479973],"genre_scores_gemma":[0.728654,0.00002667749,0.2703631,0.0005788023,0.00008374907,0.0000331328,0.00001241143,0.00003219025,0.0002159651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3549842,"threshold_uncertainty_score":0.399656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1265591498420025,"score_gpt":0.3172248596930318,"score_spread":0.1906657098510293,"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."}}