{"id":"W3185119318","doi":"10.1016/b978-0-12-819740-0.00012-7","title":"Deep learning for ophthalmology using optical coherence tomography","year":2021,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Optical coherence tomography; Deep learning; Computer science; Artificial intelligence; Coherence (philosophical gambling strategy); Modality (human–computer interaction); Optometry; Data science; Computer vision; Medicine; Ophthalmology; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002034159,0.0007515219,0.0003094973,0.0008013483,0.0002048406,0.001280244,0.0005110538,0.0008645477,0.04628475],"category_scores_gemma":[0.0005981754,0.0003056032,0.0003058215,0.0008008662,0.0003174289,0.001663738,0.0009008325,0.001462951,0.01940777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004654897,"about_ca_system_score_gemma":0.0003909505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001246017,"about_ca_topic_score_gemma":0.003478678,"domain_scores_codex":[0.9999009,0.00001064839,0.000004402728,0.0000161203,0.00006141369,0.000006503708],"domain_scores_gemma":[0.9997756,0.000109672,0.00001090969,0.00002577596,0.000058612,0.0000193623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008763134,0.00001975166,0.00009068131,0.0002494281,0.00001339763,0.00004571883,0.00002906149,0.003026247,0.001934347,0.03788445,0.2297037,0.7269945],"study_design_scores_gemma":[0.000004181161,0.00002174648,0.0003434839,0.0002618378,0.00001262362,0.0003987353,0.00002292135,0.01980728,0.002428143,0.07362472,0.903053,0.00002120964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.002416616,0.0726056,0.5342842,0.006814316,0.006021248,0.00006295928,0.001332914,0.003981254,0.3724808],"genre_scores_gemma":[0.0139082,0.04423988,0.1454954,0.001416207,0.002522045,0.00006480078,0.000964791,0.0009050715,0.7904835],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.04628475,"threshold_uncertainty_score":0.1548378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03269651827453707,"score_gpt":0.3060420063045977,"score_spread":0.2733454880300606,"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."}}