{"id":"W4383860708","doi":"10.3390/jimaging9070140","title":"Conv-ViT: A Convolution and Vision Transformer-Based Hybrid Feature Extraction Method for Retinal Disease Detection","year":2023,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Feature extraction; Pixel; Deep learning; Computer vision; Preprocessor","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":[0.0004239387,0.0008637671,0.0007366181,0.001120296,0.000163576,0.0004935869,0.00130334,0.0005677928,0.001657251],"category_scores_gemma":[0.0006094708,0.0003362989,0.001203922,0.0005897128,0.0002218648,0.0006762114,0.0005647377,0.0006807065,0.0007187811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000691913,"about_ca_system_score_gemma":0.0007641529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007683945,"about_ca_topic_score_gemma":0.009001608,"domain_scores_codex":[0.999765,0.00002065903,0.00001346064,0.00006869547,0.00009221286,0.00003993139],"domain_scores_gemma":[0.9998584,0.00003106166,0.00001885166,0.00002513278,0.00005373155,0.00001283286],"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":[0.000377783,0.0001981322,0.003101334,0.0001774664,0.0002729094,0.0002135779,0.00004724659,0.05512879,0.05955723,0.002814393,0.009187669,0.8689235],"study_design_scores_gemma":[0.00002504354,0.0001592718,0.002100391,0.00001758692,0.00009132606,0.0004429412,0.00001283826,0.9572561,0.03444873,0.001675305,0.003745842,0.0000246848],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04250648,0.001479302,0.9469297,0.000159592,0.0001226152,0.0001276754,0.0006005796,0.005847702,0.002226376],"genre_scores_gemma":[0.5981407,0.001237261,0.386148,0.0004306522,0.0001064849,0.0001898561,0.003172783,0.0003862809,0.01018795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007683945,"threshold_uncertainty_score":0.0152784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130555059973633,"score_gpt":0.3661486892471792,"score_spread":0.3548431386474429,"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."}}