{"id":"W4252321088","doi":"10.32920/ryerson.14661921.v1","title":"Deep Learning for Low-Dose CT Noise Removal Using Dilated Convolution and Perceptual Loss","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Smoothing; Computer science; Normalization (sociology); Artificial intelligence; Deep learning; Noise (video); Residual; Imaging phantom; Convolution (computer science); Mean squared error; Artificial neural network; Image quality; Pixel; Grid; Algorithm; Image (mathematics); Computer vision; Mathematics; Nuclear medicine; Medicine; Statistics","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":[0.0008634663,0.0006964742,0.0004830946,0.0003035644,0.0001761175,0.0004147607,0.0008201853,0.0007573218,0.001227093],"category_scores_gemma":[0.00177968,0.0002784899,0.0003906862,0.0003149011,0.000476736,0.0008395324,0.0007952395,0.001024111,0.0002720612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005693701,"about_ca_system_score_gemma":0.0006061502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002851008,"about_ca_topic_score_gemma":0.003474692,"domain_scores_codex":[0.9997748,0.00004650869,0.00001216258,0.00004650465,0.00008589072,0.00003410933],"domain_scores_gemma":[0.999592,0.0001921743,0.00004861875,0.00004770384,0.00009949733,0.00002001236],"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":[0.0003157758,0.0001889524,0.001068963,0.0001496618,0.00008470532,0.0001868228,0.00007600137,0.5720621,0.05242383,0.005265611,0.002285739,0.3658918],"study_design_scores_gemma":[0.000004628265,0.00003629289,0.0001257322,0.000003779296,0.000006403302,0.0000242025,0.000002719859,0.9927211,0.00594389,0.0008182067,0.0003099102,0.000003141389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04704734,0.0005293353,0.9502325,0.0001799735,0.00003780823,0.00002666837,0.00003637626,0.0008529789,0.001057098],"genre_scores_gemma":[0.7240827,0.0005852235,0.2690722,0.0002422785,0.0000535969,0.00007494372,0.0002421895,0.0001538539,0.005492978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002851008,"threshold_uncertainty_score":0.005668819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01476942640629538,"score_gpt":0.24836615019697,"score_spread":0.2335967237906746,"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."}}