{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002208817,0.0003723462,0.0009663807,0.0002531355,0.0001414861,0.00004525477,0.0001197519,0.0003415933,0.0003743744],"category_scores_gemma":[0.0001024025,0.0003464783,0.0007887869,0.00003179992,0.0002308422,0.00001734302,0.00008049305,0.000744437,0.00002325226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005794003,"about_ca_system_score_gemma":0.0001325585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.961698e-7,"about_ca_topic_score_gemma":8.177761e-7,"domain_scores_codex":[0.9983088,0.00003137829,0.0004330488,0.0005885327,0.0002768406,0.0003613766],"domain_scores_gemma":[0.9987546,0.0001486609,0.0002033638,0.0003804693,0.0003159287,0.0001970421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006853566,0.00002004882,0.0006203826,0.0004099996,0.00073665,0.00102968,0.00005682213,0.00001969592,0.0008724175,0.001168127,0.00001084418,0.9949868],"study_design_scores_gemma":[0.001670916,0.0009195465,0.0001824567,0.004282345,0.006596501,0.006137085,0.0001116187,0.004474944,0.0006452109,0.003790211,0.9697951,0.001394047],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.001354504,0.003430762,0.0004934134,0.00008866115,0.0001600294,0.0003758387,0.000003060114,0.00005569068,0.994038],"genre_scores_gemma":[0.01165567,0.0000449943,0.0109568,0.0001675597,0.0004701692,0.00002552365,0.00008632764,0.0001046804,0.9764883],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9935927,"threshold_uncertainty_score":0.9998987,"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."}}