{"id":"W4405698662","doi":"10.3390/bioengineering11121305","title":"Clean Self-Supervised MRI Reconstruction from Noisy, Sub-Sampled Training Data with Robust SSDU","year":2024,"lang":"en","type":"article","venue":"Bioengineering","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Engineering and Physical Sciences Research Council; Royal Academy of Engineering; National Institute for Health and Care Research; Canada Research Chairs; Wellcome Trust","keywords":"Undersampling; Computer science; Artificial intelligence; Noise reduction; Noise (video); Pattern recognition (psychology); Benchmark (surveying); Inference; Deep learning; Machine learning; Supervised learning; Data mining; Artificial neural network; 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":[0.00007631523,0.0001500513,0.0001805927,0.00009113393,0.00004835421,0.0000404964,0.0001311318,0.00006687222,0.00004292874],"category_scores_gemma":[0.00001275728,0.0001295671,0.00003222215,0.000274212,0.0000225418,0.0001938322,0.00005243345,0.0002050487,0.00001271872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006482427,"about_ca_system_score_gemma":0.00005361969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003760859,"about_ca_topic_score_gemma":0.0000158645,"domain_scores_codex":[0.99912,0.000003958616,0.0001750632,0.0003921986,0.0001117023,0.0001970848],"domain_scores_gemma":[0.9992597,0.00004626769,0.00002033086,0.0005480488,0.0000260854,0.00009956841],"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":[0.00009633119,0.000115556,0.000703764,0.0004350861,0.0003402064,0.0001552658,0.001308479,0.01041298,0.1516325,0.002961034,0.002432995,0.8294058],"study_design_scores_gemma":[0.0006506802,0.0001275876,0.0007470896,0.0008479275,0.0002429514,0.000301004,0.0005656215,0.9424326,0.01182631,0.0001556413,0.04170531,0.000397309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08136123,0.0005156278,0.9148514,0.0006064565,0.0001476898,0.0003500216,0.0001210532,0.001729094,0.0003174686],"genre_scores_gemma":[0.4009988,0.0002772839,0.5977278,0.00003596894,0.0004112165,0.00004273409,0.0004193762,0.00005791515,0.00002882495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9320196,"threshold_uncertainty_score":0.5283592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05084324428653443,"score_gpt":0.2765445523990724,"score_spread":0.225701308112538,"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."}}