{"id":"W2014940628","doi":"10.1016/j.media.2011.04.003","title":"New methods for MRI denoising based on sparseness and self-similarity","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":280,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Canadian Institutes of Health Research","keywords":"Thresholding; Artificial intelligence; Noise reduction; Pattern recognition (psychology); Similarity (geometry); Image denoising; Computer science; Exploit; Filter (signal processing); Discrete cosine transform; USable; Invariant (physics); Mathematics; Computer vision; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003421597,0.0002274568,0.0005427403,0.0004630818,0.0002107291,0.0002203358,0.00083615,0.0001618194,0.0002483514],"category_scores_gemma":[0.0008044072,0.0001890613,0.0003327841,0.001458428,0.00008509503,0.0003526881,0.000185129,0.0002364093,0.000008800708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003251364,"about_ca_system_score_gemma":0.0002023439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000238446,"about_ca_topic_score_gemma":0.00001826297,"domain_scores_codex":[0.9972583,0.0007305224,0.0003742469,0.0006870329,0.0005364881,0.0004134211],"domain_scores_gemma":[0.9973703,0.001104353,0.0001112712,0.0007428352,0.0001515446,0.0005196861],"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":[0.0000930171,0.0004420897,0.00123895,0.00006887822,0.0009398671,0.0002349176,0.001165514,0.00005577374,0.001642915,0.002446533,0.002052934,0.9896186],"study_design_scores_gemma":[0.001167218,0.0001585215,0.003470141,0.0000274835,0.001066929,0.000009859083,0.00001427845,0.9610282,0.02149818,0.006987162,0.004196288,0.0003757882],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003352003,0.0001804743,0.9966855,0.001105064,0.000141786,0.0001268926,0.000001099414,0.0001703172,0.001253642],"genre_scores_gemma":[0.006853841,0.00002577595,0.9904429,0.002389988,0.0001022614,0.00001089561,0.000004286605,0.00001441868,0.0001556644],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9892429,"threshold_uncertainty_score":0.7709696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03962570295564427,"score_gpt":0.3544762924274026,"score_spread":0.3148505894717584,"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."}}