{"id":"W2606534623","doi":"10.1364/boe.8.003627","title":"ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks","year":2017,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":607,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Bayerisches Staatsministerium für Bildung und Kultus, Wissenschaft und Kunst; Nvidia","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Segmentation; Convolutional neural network; Deep learning; Pattern recognition (psychology); Benchmark (surveying); Computer vision; Ophthalmology; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0003308068,0.0001440304,0.0003463438,0.0001100815,0.0001969511,0.00006261185,0.0001520376,0.0001428597,0.00005426619],"category_scores_gemma":[0.0002006445,0.0001211932,0.000119633,0.0001065613,0.001090942,0.00009148633,0.0001153227,0.0002015466,0.000001894332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002138393,"about_ca_system_score_gemma":0.00005822775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004599236,"about_ca_topic_score_gemma":3.45037e-7,"domain_scores_codex":[0.9985459,0.00003824536,0.000357913,0.000281798,0.0005325754,0.0002436073],"domain_scores_gemma":[0.9989074,0.00007139544,0.0001970963,0.0003541276,0.0001827273,0.0002872009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007474861,0.0006772781,0.1260992,0.0004494529,0.0006999297,0.0004879469,0.0002007477,0.0003197623,0.8567908,0.002149435,0.0009457591,0.01043218],"study_design_scores_gemma":[0.006557778,0.00123292,0.1226154,0.002168659,0.002274237,0.0008251934,0.000368297,0.8229055,0.03784644,0.0005831348,0.00178162,0.0008408166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.887598,0.0007349472,0.110044,0.0007526192,0.0001409488,0.0001545684,0.00001517392,0.00002302512,0.000536733],"genre_scores_gemma":[0.9502638,0.0001014431,0.04920316,0.00008023815,0.0002246774,0.000005185116,0.00004677262,0.00001331779,0.00006139919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8225858,"threshold_uncertainty_score":0.4942116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02657593600976555,"score_gpt":0.3095475841092514,"score_spread":0.2829716480994859,"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."}}