{"id":"W4385289051","doi":"10.1109/tci.2023.3299212","title":"A Theoretical Framework for Self-Supervised MR Image Reconstruction Using Sub-Sampling via Variable Density Noisier2Noise","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Imaging","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute for Health and Care Research; Engineering and Physical Sciences Research Council; Wellcome Trust; Royal Academy of Engineering; NIHR Sheffield Biomedical Research Centre; Canada Research Chairs","keywords":"Undersampling; Computer science; Artificial intelligence; Robustness (evolution); Weighting; Sampling (signal processing); Machine learning; Pattern recognition (psychology); Variable (mathematics); Supervised learning; Iterative reconstruction; Artificial neural network; Data mining; Computer vision; 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":[0.0002180377,0.0001915806,0.0002393758,0.0002641118,0.0005463053,0.00005218429,0.00007285721,0.00008878289,0.00007475317],"category_scores_gemma":[0.00002580283,0.0002066498,0.0001588828,0.0006673185,0.0001398928,0.0002055768,0.000002846222,0.000334604,0.00002849787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001827873,"about_ca_system_score_gemma":0.0001218196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007556591,"about_ca_topic_score_gemma":3.709736e-7,"domain_scores_codex":[0.9986811,0.0000276134,0.0003324085,0.0004145085,0.0002307312,0.0003135874],"domain_scores_gemma":[0.9986147,0.000608251,0.00007853984,0.0002210956,0.0003446487,0.0001327621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000420705,0.0006598741,0.0001176636,0.0002305541,0.0001459052,0.00002040342,0.000339726,0.6504729,0.1395102,0.09736667,0.0001338836,0.1105815],"study_design_scores_gemma":[0.00048198,0.00003327041,0.00006226425,0.0001305433,0.0001211805,0.0001919661,0.00006009002,0.7806253,0.01359963,0.2044948,0.00003479319,0.0001642154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03794757,0.000006662292,0.9590307,0.001046128,0.0002448673,0.0007613666,0.00005569971,0.0008490676,0.00005796909],"genre_scores_gemma":[0.4041115,0.000009228595,0.5953693,0.0002511719,0.00008829172,0.00009854352,0.00003160887,0.00003476309,0.000005538495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3661639,"threshold_uncertainty_score":0.8426936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02559828272249988,"score_gpt":0.3330444411402733,"score_spread":0.3074461584177734,"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."}}