{"id":"W3036782889","doi":"10.1364/boe.395279","title":"Real-time retinal layer segmentation of OCT volumes with GPU accelerated inferencing using a compressed, low-latency neural network","year":2020,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Eye Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC; Research to Prevent Blindness","keywords":"Computer science; Optical coherence tomography; Artificial intelligence; Artificial neural network; Segmentation; Computer vision; Wavefront; Optics","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":[0.0001587212,0.0002183116,0.0005610015,0.00008821531,0.00008654607,0.00004763281,0.0001505654,0.0001068439,0.0001529709],"category_scores_gemma":[0.00009715247,0.0001663011,0.0001036137,0.0006698873,0.0002445509,0.0001145311,0.00008462895,0.0002583407,0.000008777906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003459652,"about_ca_system_score_gemma":0.0001273269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001566909,"about_ca_topic_score_gemma":4.352749e-7,"domain_scores_codex":[0.998052,0.00009210724,0.0005296076,0.0003412907,0.0006342793,0.0003507276],"domain_scores_gemma":[0.9987952,0.00008932141,0.0002528152,0.000212707,0.0002655302,0.0003844553],"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":[0.0007681497,0.0002160091,0.01680268,0.0004157215,0.0002843817,0.0002136763,0.0007306127,0.004697234,0.9731748,0.00001462212,0.001468318,0.001213755],"study_design_scores_gemma":[0.002078397,0.000722546,0.002635451,0.0008942873,0.0006303404,0.0000500144,0.0002892957,0.9742677,0.018016,0.000009883176,0.0001278414,0.0002781979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881437,0.00007708267,0.01008735,0.0008947482,0.0000516557,0.0002073949,0.00001233111,0.00009430806,0.0004314801],"genre_scores_gemma":[0.963344,0.00005058926,0.03571527,0.0002239098,0.0004006574,0.000004953703,0.0001418558,0.00003291485,0.0000859026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9695705,"threshold_uncertainty_score":0.6781564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04088598449413583,"score_gpt":0.2991106168544779,"score_spread":0.2582246323603421,"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."}}