{"id":"W2972491395","doi":"10.1007/s10278-019-00274-4","title":"Deep Learning for Low-Dose CT Denoising Using Perceptual Loss and Edge Detection Layer","year":2019,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":149,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan; Saskatchewan Health Authority; University of Waterloo; Toronto Metropolitan University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Smoothing; Residual; Noise reduction; Deep learning; Convolution (computer science); Feature (linguistics); Enhanced Data Rates for GSM Evolution; Bilateral filter; Diagonal; Artificial neural network; Perception; Grid; Pixel; Mean squared error; Image quality; Pattern recognition (psychology); Computer vision; Image (mathematics); Algorithm; 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":[0.000231835,0.0001083593,0.0002387881,0.0001390737,0.00008835027,0.0001507129,0.00005926147,0.00002157458,0.00001367001],"category_scores_gemma":[0.000260078,0.00009118381,0.0001156678,0.0001015914,0.0000696205,0.000562758,0.00004071435,0.0003166463,0.000004378294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007858053,"about_ca_system_score_gemma":0.00004349619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002684546,"about_ca_topic_score_gemma":1.483244e-7,"domain_scores_codex":[0.9991304,0.00001075243,0.0003329898,0.0001360166,0.0001974584,0.0001923323],"domain_scores_gemma":[0.999244,0.0001126698,0.0002148293,0.00009220051,0.0001799722,0.0001563747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002312295,0.0002358016,0.2593276,0.0004031619,0.0000941447,0.0001411528,0.0007113739,0.0001664684,0.4204968,0.00008409597,0.0002433527,0.3178649],"study_design_scores_gemma":[0.01413424,0.001744041,0.05570513,0.004850771,0.001189418,0.0449296,0.006124403,0.7354925,0.08923815,0.004344167,0.04070143,0.001546199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8752632,0.0001901238,0.1234825,0.0005718116,0.000084602,0.0001832386,8.082436e-7,0.00003154838,0.0001921086],"genre_scores_gemma":[0.9917599,0.00001576146,0.007669592,0.0001629513,0.0002520185,0.000001859293,0.000002652901,0.00002759051,0.0001076502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.735326,"threshold_uncertainty_score":0.3718368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02221774624942191,"score_gpt":0.3154127551501326,"score_spread":0.2931950089007107,"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."}}