{"id":"W2951902350","doi":"10.1101/667865","title":"Accurate detection of non-proliferative diabetic retinopathy in optical coherence tomography images using convolutional neural networks","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Computer science; Optical coherence tomography; Preprocessor; Artificial intelligence; Deep learning; Diabetic retinopathy; Transfer of learning; Pattern recognition (psychology); Computer-aided diagnosis; Computer vision; Medicine; Radiology; Diabetes mellitus","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":[0.0003059291,0.0003655536,0.0001760945,0.0008800161,0.0001356587,0.0004312332,0.0002808285,0.0003975253,0.000723418],"category_scores_gemma":[0.0007894197,0.0001728209,0.000197603,0.0003187766,0.0001285235,0.0003541916,0.0003082094,0.0002457,0.0002432234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004665349,"about_ca_system_score_gemma":0.0003650269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005005853,"about_ca_topic_score_gemma":0.007686465,"domain_scores_codex":[0.9998358,0.0000293044,0.00000906728,0.00003686189,0.00005962644,0.00002933689],"domain_scores_gemma":[0.9997602,0.00006984922,0.00005207066,0.00002774648,0.00007583878,0.00001428684],"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":[0.0007070564,0.0002717446,0.0256171,0.0002407837,0.0001182438,0.0006244645,0.00009178451,0.03808348,0.3678296,0.001385763,0.005063542,0.5599664],"study_design_scores_gemma":[0.00001595776,0.0001063983,0.02444019,0.00003886552,0.00005212445,0.0004275145,0.00003413356,0.8570496,0.115086,0.000583916,0.002143583,0.00002172767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6089512,0.002073341,0.3795388,0.0006167662,0.00009103108,0.0001108306,0.0006225409,0.00265671,0.005338751],"genre_scores_gemma":[0.9145792,0.0006640002,0.0818299,0.0001666285,0.00002880816,0.0000302515,0.0003303812,0.00003181431,0.00233908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005005853,"threshold_uncertainty_score":0.009953439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01400664137029768,"score_gpt":0.2512062324753521,"score_spread":0.2371995911050544,"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."}}