{"id":"W2793498597","doi":"10.1117/12.2292479","title":"Comparison of Gaussian filter versus wavelet-based denoising on graph-based segmentation of retinal OCT images","year":2018,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Noise reduction; Wavelet; Pattern recognition (psychology); Computer vision; Image denoising; Segmentation; Wavelet transform; Gaussian; Graph; Filter (signal processing); Physics; Theoretical computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001913702,0.0001217798,0.0003461035,0.0002609718,0.00004920958,0.00001037299,0.00006030163,0.00003798943,0.0002222483],"category_scores_gemma":[0.0000797078,0.00009379611,0.0001596806,0.0002989417,0.0002309339,0.0000321974,0.000006973045,0.00009196767,0.00001876564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003098192,"about_ca_system_score_gemma":0.0000520329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000165783,"about_ca_topic_score_gemma":0.00001025534,"domain_scores_codex":[0.9988841,0.00006166201,0.0003579869,0.0001931001,0.0003538092,0.0001492953],"domain_scores_gemma":[0.999144,0.0001233289,0.0002075473,0.0002510549,0.0002074066,0.00006662041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.008058914,0.001349767,0.2535188,0.0005810367,0.0003441488,0.00002198922,0.0004545498,0.0001581872,0.6994568,0.000119199,0.009488055,0.02644852],"study_design_scores_gemma":[0.002604609,0.001876482,0.02992982,0.0003196569,0.0003177191,8.551697e-7,0.0004049376,0.0106067,0.9537798,0.000008239703,0.00005256857,0.0000986157],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748601,0.00003310863,0.01824034,0.001306207,0.00007944023,0.000122558,0.000007191542,0.00007742616,0.005273649],"genre_scores_gemma":[0.9806957,0.000001152313,0.01883681,0.0002079795,0.00006372355,0.000001924514,0.00004192175,0.00001975331,0.0001310872],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.254323,"threshold_uncertainty_score":0.3824894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04616463342124388,"score_gpt":0.378560831617731,"score_spread":0.3323961981964871,"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."}}