{"id":"W2751422573","doi":"10.1007/s10916-018-1074-7","title":"Adaptive Real-Time Removal of Impulse Noise in Medical Images","year":2018,"lang":"en","type":"preprint","venue":"Journal of Medical Systems","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Impulse noise; Computer science; Dark-frame subtraction; Pixel; Noise (video); Computer vision; Impulse (physics); Artificial intelligence; Gradient noise; Noise measurement; Image noise; Salt-and-pepper noise; Noise reduction; Algorithm; Median filter; Noise floor; Image (mathematics); Image processing; Physics","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":[0.0006988605,0.0005637815,0.0004235481,0.0004854778,0.0001332286,0.000635514,0.0005254198,0.001222304,0.002355686],"category_scores_gemma":[0.002998623,0.000312081,0.000450169,0.0003368068,0.0004868853,0.0006244777,0.0006634124,0.0009588594,0.000679463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001818891,"about_ca_system_score_gemma":0.0003827467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000465094,"about_ca_topic_score_gemma":0.0007002712,"domain_scores_codex":[0.9996459,0.00007929749,0.00001978131,0.00006599969,0.0001577007,0.00003127547],"domain_scores_gemma":[0.99934,0.0003565479,0.00006168773,0.00009091121,0.0001149924,0.00003585912],"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":[0.001396087,0.0002295033,0.001010154,0.0005565354,0.0001288522,0.0003984034,0.0002540531,0.07753472,0.4139041,0.008414537,0.003066393,0.4931066],"study_design_scores_gemma":[0.00004923654,0.0002063799,0.002290067,0.00003743509,0.00007162612,0.001106887,0.00005068794,0.8750194,0.1131259,0.004040569,0.003971097,0.00003076303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05359162,0.0009784984,0.9426534,0.0004627531,0.0001943403,0.00003915311,0.00007035036,0.0005171857,0.001492801],"genre_scores_gemma":[0.4847777,0.00194743,0.4979698,0.0003347995,0.0003496173,0.00008081937,0.0003140341,0.0003291879,0.01389677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002355686,"threshold_uncertainty_score":0.007880569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02622909373359003,"score_gpt":0.3240933731170113,"score_spread":0.2978642793834213,"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."}}