{"id":"W4390402711","doi":"10.1007/s00034-023-02575-0","title":"Low-Dose CT Image Denoising with a Residual Multi-scale Feature Fusion Convolutional Neural Network and Enhanced Perceptual Loss","year":2023,"lang":"en","type":"article","venue":"Circuits Systems and Signal Processing","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Saskatchewan; Saskatchewan Health Authority; Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Residual; Noise reduction; Image quality; Feature (linguistics); Noise (video); Pattern recognition (psychology); Image (mathematics); Block (permutation group theory); Image fusion; Computer vision; Algorithm; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007474116,0.0005882712,0.0004248332,0.0003985268,0.0001648041,0.0005240933,0.0005677931,0.0006802104,0.00106787],"category_scores_gemma":[0.001219979,0.0002145105,0.0005823667,0.0003499136,0.0003471995,0.0007512505,0.000746486,0.000708124,0.0002788643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000358321,"about_ca_system_score_gemma":0.0005977036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001934331,"about_ca_topic_score_gemma":0.002873389,"domain_scores_codex":[0.9997957,0.00002928149,0.00001340088,0.00004117217,0.00009741814,0.00002310195],"domain_scores_gemma":[0.9997719,0.00005213537,0.00002958427,0.00004217753,0.0000899035,0.00001438859],"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":[0.001047672,0.0002888723,0.002501647,0.0003612452,0.0002082469,0.0003624791,0.0001337499,0.2402998,0.2489155,0.008869559,0.003692792,0.4933185],"study_design_scores_gemma":[0.00001386877,0.0001107357,0.001145283,0.00001548955,0.0000594983,0.0002639978,0.00001241421,0.9465409,0.04903996,0.001328846,0.001450114,0.00001882612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04774395,0.0005002396,0.949429,0.000279378,0.00007081887,0.00004412644,0.0000931297,0.0005121938,0.001327063],"genre_scores_gemma":[0.5874274,0.0006612082,0.4057516,0.000230164,0.00007070538,0.00005979397,0.000356386,0.0002058476,0.005236889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001934331,"threshold_uncertainty_score":0.003952742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02357966195169346,"score_gpt":0.2868989450312209,"score_spread":0.2633192830795274,"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."}}