{"id":"W2800771112","doi":"10.1364/boe.9.002394","title":"Enhancement of morphological and vascular features in OCT images using a modified Bayesian residual transform","year":2018,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Optical coherence tomography; Residual; Artificial intelligence; Speckle pattern; Speckle noise; Computer vision; Computer science; Image processing; Contrast (vision); Pattern recognition (psychology); Optics; Image (mathematics); Physics; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001874161,0.0001525195,0.0002417341,0.0001552743,0.00003742363,0.00002096576,0.00018903,0.0001811161,0.00005892738],"category_scores_gemma":[0.00003171021,0.000133717,0.00004860848,0.000337725,0.0006520003,0.00006670114,0.00004444673,0.0001832534,0.000001751121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002052468,"about_ca_system_score_gemma":0.00001581033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002394978,"about_ca_topic_score_gemma":0.000004113261,"domain_scores_codex":[0.9988464,0.00002356272,0.0003231826,0.0002230367,0.0002890477,0.0002948329],"domain_scores_gemma":[0.9994767,0.00007123742,0.00002410637,0.0002273435,0.00004189329,0.0001586671],"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":[0.00007227817,0.0005951564,0.0002616999,0.0003679087,0.0001608346,0.00006004602,0.001108144,0.0004590965,0.9799274,0.005316014,0.0006637012,0.01100774],"study_design_scores_gemma":[0.00656734,0.001929347,0.02070379,0.0009216887,0.00037063,0.0001237188,0.0008985215,0.2899894,0.6566762,0.0171697,0.002297155,0.002352446],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7693472,0.0003971286,0.2272221,0.0001231119,0.00007956365,0.0003735729,0.00003975831,0.00008724511,0.002330291],"genre_scores_gemma":[0.945756,0.0001185417,0.05396967,0.00001408065,0.0000745962,0.00003714718,0.000008854465,0.00001531811,0.000005824506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3232511,"threshold_uncertainty_score":0.5452821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01505463126827551,"score_gpt":0.2588844520835973,"score_spread":0.2438298208153218,"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."}}