{"id":"W2051453269","doi":"10.1117/12.2043325","title":"Retinal image quality assessment using generic features","year":2014,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Image quality; Robustness (evolution); Pixel; Support vector machine; Pattern recognition (psychology); Segmentation; Image segmentation; Classifier (UML); Computer vision; Image (mathematics)","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":[0.002329151,0.0004706914,0.0006208447,0.003639117,0.0001828817,0.0009799742,0.0004970512,0.0007140403,0.001052923],"category_scores_gemma":[0.007467256,0.0001757287,0.0007679328,0.001279494,0.0003703566,0.0008862764,0.0006568262,0.0003599392,0.0002836688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004609936,"about_ca_system_score_gemma":0.0002260039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001068151,"about_ca_topic_score_gemma":0.001178208,"domain_scores_codex":[0.9985813,0.0002685151,0.0001649138,0.0002850597,0.0006192168,0.00008099986],"domain_scores_gemma":[0.9959062,0.0009285393,0.0009207231,0.0004872483,0.001647589,0.0001096753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001279237,0.0002295159,0.07581794,0.0008465835,0.0004448071,0.0004860803,0.0002932009,0.04243968,0.2582038,0.001569708,0.001880057,0.6165094],"study_design_scores_gemma":[0.00008082723,0.001644964,0.3163228,0.0001305325,0.0004553495,0.003347646,0.000216308,0.4905704,0.1809625,0.00227258,0.003782637,0.000213364],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.45362,0.001687387,0.5393271,0.000122145,0.00004542659,0.0003605521,0.0007352731,0.001590632,0.0025115],"genre_scores_gemma":[0.8007242,0.0004410026,0.197545,0.00004560213,0.00003473687,0.00007741545,0.0005225033,0.00008369952,0.0005257315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003639117,"threshold_uncertainty_score":0.0123179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02039658983193441,"score_gpt":0.2989988568229384,"score_spread":0.2786022669910039,"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."}}