{"id":"W2896311095","doi":"10.1364/boe.9.005353","title":"Automated identification of cone photoreceptors in adaptive optics optical coherence tomography images using transfer learning","year":2018,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Alzheimer Society; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Adaptive optics; Computer vision; Optics; Convolutional neural network; Cone (formal languages); Image processing; Physics; Image (mathematics); Algorithm","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":[0.0005048207,0.0001953026,0.0004997068,0.0004391362,0.0000694069,0.00003322217,0.0001667363,0.0001809851,0.00007247458],"category_scores_gemma":[0.0003186777,0.0001720068,0.0001489415,0.000965798,0.001344085,0.0001006122,0.00004410237,0.0003263423,0.00001111717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004806659,"about_ca_system_score_gemma":0.00009514508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006798293,"about_ca_topic_score_gemma":8.875136e-7,"domain_scores_codex":[0.9978406,0.00009993178,0.0007364868,0.0003672313,0.0006156981,0.0003400934],"domain_scores_gemma":[0.9988521,0.0001423571,0.000120367,0.000245322,0.0003933947,0.0002464459],"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":[0.0002138263,0.0004686542,0.004827769,0.0001135037,0.0001377038,0.00003961989,0.0005836102,0.00007834798,0.9921497,0.0001622457,0.00007384347,0.001151189],"study_design_scores_gemma":[0.001895479,0.000887435,0.007511398,0.0008453727,0.0004598241,0.00003985356,0.001020988,0.453906,0.5328734,0.00005365913,0.0001574025,0.0003491962],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9539077,0.000107957,0.04488572,0.0001393459,0.0001493403,0.0002176476,0.0000165886,0.0001443869,0.00043126],"genre_scores_gemma":[0.9749075,0.0000434931,0.02471979,0.00002942913,0.0001402226,0.000009443619,0.00004113156,0.00002543293,0.00008358007],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4592763,"threshold_uncertainty_score":0.7014232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02141198949881101,"score_gpt":0.302981088945388,"score_spread":0.281569099446577,"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."}}