{"id":"W4387057829","doi":"10.21203/rs.3.rs-3348299/v1","title":"DeepRetNet: Retinal Disease Classification using Attention UNet++ based Segmentation and Optimized Deep Learning Technique","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Segmentation; Artificial intelligence; Weighting; Retinal; Computer science; Pattern recognition (psychology); Convergence (economics); Medicine; Ophthalmology; Radiology","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":[0.0004273763,0.0009885404,0.0006248564,0.0007677912,0.0002979977,0.000727322,0.001268878,0.001099297,0.003460732],"category_scores_gemma":[0.0009741473,0.0003362092,0.0006926605,0.00050814,0.0002530618,0.0007250994,0.0007542289,0.0008280697,0.0008364923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001087655,"about_ca_system_score_gemma":0.001176591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01407965,"about_ca_topic_score_gemma":0.01471409,"domain_scores_codex":[0.9997705,0.0000278009,0.0000153611,0.00008784061,0.00005180723,0.00004673868],"domain_scores_gemma":[0.9997852,0.00004741785,0.00002827728,0.00003284645,0.00008690152,0.00001936415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005403251,0.0003651411,0.00796703,0.0002491904,0.0002047689,0.0004583896,0.00009321008,0.2734438,0.03494075,0.004199427,0.02416648,0.6533716],"study_design_scores_gemma":[0.00001674469,0.00007233394,0.0009259785,0.00001714737,0.00002231164,0.000118892,0.00001071401,0.9849733,0.01093762,0.001359082,0.001535547,0.00001029927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.252966,0.003826808,0.7142761,0.001554353,0.0005124413,0.0003016739,0.002914585,0.01540662,0.008241358],"genre_scores_gemma":[0.7754436,0.0007915695,0.2023236,0.0006989802,0.0001363273,0.0002190983,0.005019093,0.000270655,0.01509713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01407965,"threshold_uncertainty_score":0.02799541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1294912519747025,"score_gpt":0.450450337261219,"score_spread":0.3209590852865165,"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."}}