{"id":"W4407731058","doi":"10.2139/ssrn.5137786","title":"Customized Cyclegan with Balanced Skip Networked Residual Layer (Ccgan-Bsnrl) to Enhance Colonoscopy Image by Nbi Translation","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Residual; Translation (biology); Colonoscopy; Layer (electronics); Computer science; Image (mathematics); Artificial intelligence; Image translation; Computer vision; Algorithm; Materials science; Medicine; Chemistry; Internal medicine; Nanotechnology; Colorectal cancer","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":[0.0003793395,0.0009231934,0.0004489992,0.0005790927,0.0002102552,0.000458055,0.0005899435,0.0006860269,0.00628865],"category_scores_gemma":[0.0008887892,0.0002465434,0.0004615324,0.0003696569,0.0002541019,0.0007069497,0.0009806808,0.0006869929,0.002306745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002997609,"about_ca_system_score_gemma":0.0006570491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003684308,"about_ca_topic_score_gemma":0.01155691,"domain_scores_codex":[0.999842,0.0000284894,0.000007195992,0.00004241667,0.00004624975,0.00003362543],"domain_scores_gemma":[0.9998329,0.00003862672,0.00001173764,0.0000457989,0.00005450323,0.00001650537],"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":[0.0009029058,0.000171987,0.001284658,0.0004824745,0.0001607374,0.0003034242,0.0001123495,0.03347897,0.2073746,0.005604979,0.02322038,0.7269026],"study_design_scores_gemma":[0.00008616233,0.0003846062,0.00282783,0.0001206621,0.0001870534,0.0006738768,0.00007842731,0.7965896,0.1647221,0.005636503,0.02861107,0.00008206181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09963033,0.002598221,0.8657266,0.0007882841,0.0007365935,0.0003416102,0.002672357,0.01158716,0.01591881],"genre_scores_gemma":[0.373426,0.001490298,0.5912345,0.001058827,0.0001653086,0.0002987771,0.005854977,0.001362923,0.02510838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00628865,"threshold_uncertainty_score":0.02103764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007730478597447563,"score_gpt":0.2972573956430676,"score_spread":0.28952691704562,"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."}}