{"id":"W4287751635","doi":"10.48550/arxiv.2006.14738","title":"Cascaded Convolutional Neural Networks with Perceptual Loss for Low Dose\\n CT Denoising","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saskatoon Medical Imaging; Toronto Metropolitan University","funders":"","keywords":"Convolutional neural network; Contrast (vision); Artificial intelligence; Noise reduction; Computer science; Ground truth; Mean squared error; Image (mathematics); Perception; Image denoising; Deep learning; Pattern recognition (psychology); Reduction (mathematics); Radiation dose; Artificial neural network; Residual neural network; Contrast enhancement; Mathematics; Nuclear medicine; Medicine; Radiology; Statistics; Magnetic resonance imaging; Psychology","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":[0.0008817944,0.0008576293,0.0006176378,0.0004390629,0.0002133358,0.0005316214,0.00110241,0.001148395,0.001419675],"category_scores_gemma":[0.001868444,0.0004087221,0.0006130612,0.0003336466,0.0005000496,0.0008175549,0.0007870335,0.001440394,0.000391509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008771581,"about_ca_system_score_gemma":0.00070517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006646466,"about_ca_topic_score_gemma":0.008300087,"domain_scores_codex":[0.9997706,0.00003948597,0.00001091336,0.00006000003,0.00007961778,0.0000393922],"domain_scores_gemma":[0.9996253,0.0001597308,0.00004311759,0.00005147455,0.00009466516,0.00002569792],"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":[0.0002435415,0.0001171893,0.001176166,0.00007818106,0.00009553399,0.0001517491,0.00004486218,0.849007,0.01662273,0.004461544,0.002116984,0.1258846],"study_design_scores_gemma":[0.000002378021,0.0000186958,0.0001209286,0.000003660296,0.000007660798,0.00001303602,0.000001472065,0.9967969,0.001982166,0.0008653051,0.000185336,0.000002522859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07047326,0.001385698,0.923081,0.0004502597,0.0001275016,0.00003904129,0.0001213314,0.001336434,0.00298549],"genre_scores_gemma":[0.8400616,0.0009137527,0.1484994,0.0002661699,0.0001112343,0.00005817959,0.0003516631,0.0001672302,0.009570751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006646466,"threshold_uncertainty_score":0.01321554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09208562480147053,"score_gpt":0.2363699963974425,"score_spread":0.144284371595972,"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."}}