{"id":"W2793314794","doi":"10.1117/12.2292095","title":"Intra-retinal segmentation of optical coherence tomography images using active contours with a dynamic programming initialization and an adaptive weighting strategy","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":"Active contour model; Artificial intelligence; Computer science; Computer vision; Optical coherence tomography; Weighting; Level set (data structures); Initialization; Segmentation; Retinal; Robustness (evolution); Pattern recognition (psychology); Image segmentation; Speckle noise; Level set method; Speckle pattern; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001314891,0.0001172352,0.000211707,0.000144593,0.00008367292,0.00004110108,0.00002852668,0.00003475637,0.00002461904],"category_scores_gemma":[0.00002168703,0.00008706153,0.00002898905,0.0003255978,0.0004335978,0.0002682552,0.00001058228,0.00008393593,2.797184e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002656109,"about_ca_system_score_gemma":0.00005948418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002802194,"about_ca_topic_score_gemma":0.00007172723,"domain_scores_codex":[0.9991819,0.00005442484,0.0001880025,0.0002275345,0.0001934708,0.0001546437],"domain_scores_gemma":[0.9992625,0.00003243779,0.0001391278,0.00008100102,0.0003964092,0.00008850443],"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":[0.003042302,0.0004975484,0.1347694,0.0002103316,0.0006181519,0.00006549423,0.003597638,0.00006565105,0.546338,0.00109727,0.000003573589,0.3096946],"study_design_scores_gemma":[0.004385191,0.01491491,0.09961417,0.001722259,0.002472055,0.0004216412,0.05494353,0.2745341,0.5458223,0.0004512475,0.000003614875,0.0007149708],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8712122,0.00002380803,0.1274642,0.0000404023,0.000007319799,0.0002008901,0.000002539981,0.00003105492,0.001017647],"genre_scores_gemma":[0.9187747,0.000004268933,0.08110469,0.000021984,0.00004354038,0.000005219591,0.00002265177,0.00001051741,0.00001241893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3089797,"threshold_uncertainty_score":0.3550266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02085201564779392,"score_gpt":0.3274686290758048,"score_spread":0.3066166134280108,"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."}}