{"id":"W4388760984","doi":"10.1364/boe.506205","title":"ESDiff: a joint model for low-quality retinal image enhancement and vessel segmentation using a diffusion model","year":2023,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Shandong Province; Natural Sciences and Engineering Research Council of Canada; Taishan Scholar Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Computer science; Fundus (uterus); Artificial intelligence; Computer vision; Segmentation; Image quality; Process (computing); Diffusion; Pattern recognition (psychology); Image (mathematics); Ophthalmology; Medicine","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":[0.0005815484,0.0001767536,0.0003744279,0.0001816466,0.0001452546,0.00005216925,0.00007032075,0.00009651506,0.000009203994],"category_scores_gemma":[0.0002025597,0.0001468933,0.0001263043,0.0002378126,0.0002053848,0.00008249113,0.0001215069,0.000134148,0.000005003065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007240041,"about_ca_system_score_gemma":0.00008385986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001790305,"about_ca_topic_score_gemma":1.505973e-7,"domain_scores_codex":[0.9981833,0.00003536548,0.000478523,0.0003962021,0.0005671994,0.0003394661],"domain_scores_gemma":[0.9991303,0.00006939877,0.0001349311,0.0002340615,0.0001434034,0.0002879039],"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":[0.0001665952,0.0002591853,0.00005313624,0.0005071548,0.00004987787,0.00001312769,0.0007100589,0.0006520501,0.9945294,0.00008529334,0.0009426148,0.002031566],"study_design_scores_gemma":[0.00152519,0.00009585482,0.0001347947,0.000312022,0.000200997,0.000006789718,0.0002657667,0.9796461,0.01704057,0.0005764203,0.00003315402,0.0001623748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4986118,0.00002717944,0.5001918,0.0008189509,0.00003193765,0.000208561,0.00003178601,0.00004552601,0.00003246526],"genre_scores_gemma":[0.772413,0.0002615605,0.2253688,0.0003170715,0.0001569638,0.00007678062,0.0003365862,0.00003629123,0.001032902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.978994,"threshold_uncertainty_score":0.5990133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0669678639794797,"score_gpt":0.3698821402856993,"score_spread":0.3029142763062196,"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."}}