{"id":"W3133139577","doi":"10.1117/12.2581110","title":"EdgeWaveNet: edge aware residual wavelet GAN for OCT image denoising","year":2021,"lang":"en","type":"article","venue":"","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Speckle noise; Computer vision; Smoothing; Sobel operator; Optical coherence tomography; Pattern recognition (psychology); Residual; Enhanced Data Rates for GSM Evolution; Wavelet transform; Noise reduction; Noise (video); Wavelet; Edge detection; Speckle pattern; Image (mathematics); Image processing; Algorithm; Optics","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":[0.0004402286,0.0005359113,0.0003738177,0.0003394267,0.0001003783,0.0003420796,0.0006085975,0.0004446418,0.001622622],"category_scores_gemma":[0.0006175525,0.0001593024,0.000401261,0.000298917,0.0002072597,0.0004866792,0.0004484695,0.0008375125,0.0005827076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000270661,"about_ca_system_score_gemma":0.000368836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001713461,"about_ca_topic_score_gemma":0.004202487,"domain_scores_codex":[0.9998909,0.00002463948,0.0000047551,0.00001994198,0.00004473042,0.00001496298],"domain_scores_gemma":[0.9998838,0.00003540116,0.0000129218,0.00001927711,0.00003881707,0.000009800443],"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":[0.0004381244,0.0002322003,0.001635864,0.000184308,0.0001572584,0.0002385244,0.00006836648,0.3510077,0.06618413,0.01824945,0.01304916,0.548555],"study_design_scores_gemma":[0.0000068012,0.00003941174,0.0002338785,0.000006943362,0.000008099294,0.00004504423,0.000005996883,0.9895043,0.007186785,0.001437605,0.001520119,0.000005082542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01962223,0.0003660182,0.9763591,0.0001376849,0.00005061787,0.00003540761,0.0002034587,0.001158695,0.00206675],"genre_scores_gemma":[0.4603211,0.001008553,0.5233549,0.0004131367,0.00006986018,0.0001425455,0.001735924,0.0004634691,0.01249042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001713461,"threshold_uncertainty_score":0.005428195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01346370583394104,"score_gpt":0.2442385987734404,"score_spread":0.2307748929394994,"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."}}