{"id":"W4379650065","doi":"10.1101/2023.06.04.543602","title":"FONDUE: Robust resolution-invariant denoising of MR Images using Nested UNets","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal General Hospital; McGill University; Douglas College","funders":"Natural Sciences and Engineering Research Council of Canada; Alzheimer Society Research Program; Alzheimer Society","keywords":"Artificial intelligence; Noise reduction; Computer science; Invariant (physics); Scanner; Computer vision; Pattern recognition (psychology); Image denoising; Neuroimaging; Voxel; Image quality; Image (mathematics); Mathematics; Psychology; Neuroscience","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001741347,0.0009989053,0.000739077,0.0006606719,0.0003299479,0.0007290832,0.001666387,0.001190001,0.002192925],"category_scores_gemma":[0.004369075,0.000424836,0.0009077304,0.0004262784,0.0005727862,0.001203694,0.001594993,0.001448747,0.0007718873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005652805,"about_ca_system_score_gemma":0.0007745621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005374115,"about_ca_topic_score_gemma":0.009845695,"domain_scores_codex":[0.9996082,0.0001020059,0.00001875714,0.0000915261,0.0001293908,0.00005012864],"domain_scores_gemma":[0.9992943,0.0002611449,0.00006779008,0.00013826,0.0001838818,0.00005452356],"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":[0.0003503125,0.0001349099,0.00166583,0.0001878831,0.0002879839,0.0002566301,0.000172646,0.6197276,0.04012956,0.01452285,0.009656735,0.312907],"study_design_scores_gemma":[0.000007363673,0.00002703717,0.0001319387,0.000007086845,0.00001000878,0.00004138882,0.000007431314,0.9907326,0.005562089,0.002291181,0.001173622,0.000008294279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01397352,0.0001861201,0.9829845,0.0001130826,0.00004453712,0.000028791,0.0001055853,0.001806686,0.0007571412],"genre_scores_gemma":[0.3060952,0.000253584,0.6842564,0.0002819548,0.00006399422,0.0001484925,0.000977313,0.0009280551,0.006995096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005374115,"threshold_uncertainty_score":0.01068562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05244932800021511,"score_gpt":0.2668609059021369,"score_spread":0.2144115779019218,"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."}}