{"id":"W2601810895","doi":"10.15353/vsnl.v2i1.117","title":"Improved OCT Human Corneal segmentation Using Bayesian Residual Transform","year":2016,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Segmentation; Speckle noise; Residual; Computer vision; Computer science; Speckle pattern; Optical coherence tomography; Noise (video); Optics; Image (mathematics); Algorithm; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0002642853,0.0001080593,0.0001675888,0.0001971509,0.0001006006,0.0001010295,0.00007816516,0.00002829774,0.00001187219],"category_scores_gemma":[0.000007732411,0.00007594985,0.00005619582,0.0001256746,0.00005462484,0.0004135953,0.000006699654,0.00008971663,0.000001546973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006771791,"about_ca_system_score_gemma":0.00002657598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006187842,"about_ca_topic_score_gemma":6.5489e-7,"domain_scores_codex":[0.9990209,0.00003301637,0.0004979881,0.00007766537,0.000246156,0.0001242866],"domain_scores_gemma":[0.9994051,0.0001162672,0.0001350428,0.00005568645,0.000184026,0.000103864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008457877,0.0001565052,0.00747372,0.000342932,0.0002768849,0.00002251224,0.0009823919,0.119992,0.7400026,0.007514474,0.00237459,0.1207768],"study_design_scores_gemma":[0.002654292,0.0002359754,0.02105918,0.0007078172,0.00008623033,0.0005876209,0.0005791308,0.9645466,0.002027311,0.006553341,0.0005634284,0.0003991026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3208851,0.0002925647,0.6778851,0.0002740927,0.0002078481,0.0001536657,0.00001108355,0.0000431979,0.0002473953],"genre_scores_gemma":[0.9932886,0.00001126701,0.00651497,0.00001474141,0.0001381579,0.000002611724,0.000002741886,0.00001578494,0.00001113063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8445546,"threshold_uncertainty_score":0.3097145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01134311744889573,"score_gpt":0.2761726767459537,"score_spread":0.264829559297058,"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."}}