{"id":"W4285087688","doi":"10.1038/s41598-022-16089-3","title":"Fractal dimension of retinal vasculature as an image quality metric for automated fundus image analysis systems","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China","keywords":"Computer science; Fractal dimension; Artificial intelligence; Retinal; Computer vision; Metric (unit); Image quality; Fractal analysis; Box counting; Fundus (uterus); Segmentation; Image processing; Dimension (graph theory); Pipeline (software); Pattern recognition (psychology); Fractal; Image (mathematics); Ophthalmology; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009517985,0.0004311779,0.0004648545,0.003433356,0.0002195618,0.0008938245,0.0003424501,0.0005139658,0.0006681004],"category_scores_gemma":[0.003540035,0.0001393081,0.0004413043,0.001163766,0.0003095681,0.0007972186,0.0004347714,0.0003138111,0.0002107538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005720126,"about_ca_system_score_gemma":0.0002986703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001444769,"about_ca_topic_score_gemma":0.001395349,"domain_scores_codex":[0.9993224,0.0001161197,0.00006462276,0.0001354867,0.0003094887,0.00005191768],"domain_scores_gemma":[0.9975187,0.0009293117,0.0004926957,0.0002329523,0.0007446787,0.00008186518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008952784,0.0003367325,0.12986,0.0005295657,0.0004109454,0.0006182598,0.0004352204,0.07738507,0.13187,0.005170877,0.008715153,0.643773],"study_design_scores_gemma":[0.00003320813,0.0003963927,0.1511713,0.00008549316,0.0001925127,0.001279613,0.0001826874,0.7919187,0.04623526,0.004158718,0.004231161,0.0001148843],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5755881,0.002920245,0.4142032,0.0004281094,0.00009539067,0.0001293542,0.001518839,0.00201487,0.003101874],"genre_scores_gemma":[0.9201261,0.000528969,0.07773691,0.00004109175,0.00005819705,0.00004851054,0.0008843082,0.00005159495,0.0005242837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003433356,"threshold_uncertainty_score":0.005033672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01866619935799438,"score_gpt":0.3429942665983713,"score_spread":0.3243280672403769,"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."}}