{"id":"W2884526620","doi":"10.1364/boe.9.003740","title":"Deep learning based detection of cone photoreceptors with multimodal adaptive optics scanning light ophthalmoscope images of achromatopsia","year":2018,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Eye Institute; National Institutes of Health; Foundation Fighting Blindness; Research to Prevent Blindness","keywords":"Achromatopsia; Adaptive optics; Artificial intelligence; Scanning laser ophthalmoscopy; Computer science; Deep learning; Retina; Computer vision; Retinal; Optics; Ophthalmology; Medicine; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291699,0.0002261395,0.0006001037,0.0002729075,0.00009789967,0.00001692367,0.0001536616,0.0001509427,0.00009404826],"category_scores_gemma":[0.0003122473,0.000171974,0.0001312979,0.0005489068,0.001045049,0.00008160173,0.00005847583,0.0002907965,0.000006693398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004532304,"about_ca_system_score_gemma":0.0001044767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008411711,"about_ca_topic_score_gemma":7.418192e-7,"domain_scores_codex":[0.9980872,0.00008925437,0.0004871652,0.000330868,0.000700101,0.0003054686],"domain_scores_gemma":[0.9983555,0.0001484066,0.0003534869,0.0002810673,0.0005900592,0.0002714449],"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":[0.0007872364,0.0004128196,0.003220205,0.0002372866,0.0002732123,0.00005746841,0.0005253358,0.0001974434,0.9918658,0.000008183759,0.00002649027,0.002388568],"study_design_scores_gemma":[0.001784345,0.002758791,0.001617222,0.0008471972,0.0003914068,0.00004950613,0.0009144172,0.2072887,0.7839562,0.000002987526,0.0001940998,0.0001951589],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8734377,0.0001559791,0.124843,0.0001253842,0.0001255807,0.0002057234,0.000008133376,0.00006350153,0.001034981],"genre_scores_gemma":[0.9359269,0.00001378552,0.06364574,0.00002057668,0.0001962926,0.0000106123,0.00002268768,0.000036662,0.0001268094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2079096,"threshold_uncertainty_score":0.7012894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01017426155522647,"score_gpt":0.2656527865893243,"score_spread":0.2554785250340978,"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."}}