{"id":"W3207698969","doi":"10.1016/j.compmedimag.2021.101988","title":"LF-UNet – A novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Convolutional neural network; Segmentation; Computer vision; Network architecture; Pattern recognition (psychology); Deep learning; Artificial neural network; Radiology; Medicine","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":[0.0003930298,0.000248297,0.0006757373,0.0001441349,0.0001426688,0.00008493842,0.0000912049,0.0001181089,0.00002065565],"category_scores_gemma":[0.000253458,0.0002197391,0.0002157068,0.0005210364,0.0006666934,0.0000930859,0.0001194729,0.0003623642,2.282516e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009654501,"about_ca_system_score_gemma":0.00008139338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007655573,"about_ca_topic_score_gemma":0.000006160616,"domain_scores_codex":[0.9979665,0.00009301632,0.0005145665,0.0005588342,0.0004967006,0.0003703326],"domain_scores_gemma":[0.9982865,0.0005945106,0.0001342656,0.0002308867,0.0002906525,0.000463169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00203341,0.001252869,0.4504806,0.002038545,0.002049139,0.001557998,0.001315634,0.0001030326,0.2540537,0.001583776,0.007875966,0.2756554],"study_design_scores_gemma":[0.01154954,0.0002716994,0.06087068,0.001447811,0.001421171,0.001377174,0.0005347317,0.9102804,0.008744848,0.002172985,0.0006894579,0.0006394995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.685283,0.003819086,0.3034674,0.006854308,0.0002123824,0.0002167901,0.00005531943,0.00007278656,0.00001891951],"genre_scores_gemma":[0.9271244,0.0005475522,0.06959844,0.001988498,0.000334555,0.00001819795,0.0003515739,0.00002687813,0.000009899292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9101774,"threshold_uncertainty_score":0.89607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01311444127564886,"score_gpt":0.2806330781246108,"score_spread":0.2675186368489619,"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."}}