{"id":"W4411453846","doi":"10.1007/s10489-025-06629-5","title":"RA-EPNet: A novel network fusing residual axial attention and edge prediction for medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Sichuan Province Science and Technology Support Program","keywords":"Computer science; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Segmentation; Residual; Computer vision; Image (mathematics); Image segmentation; Pattern recognition (psychology); Algorithm","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006557998,0.0001651387,0.0002382278,0.0001332263,0.00019986,0.00005425935,0.0000893364,0.0001765641,0.00006057036],"category_scores_gemma":[0.0003563107,0.0001677094,0.00005454482,0.0003448696,0.0001586333,0.00008493564,0.00008112169,0.0002034795,0.0000118328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001667871,"about_ca_system_score_gemma":0.000217024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004923088,"about_ca_topic_score_gemma":0.0000265442,"domain_scores_codex":[0.9984595,0.00001881539,0.0004323074,0.0004546759,0.0003486458,0.0002860649],"domain_scores_gemma":[0.9989851,0.0004816962,0.0000965691,0.0002079845,0.0001168075,0.0001118825],"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":[0.00263997,0.001018664,0.00754056,0.001794042,0.0004090292,0.00001721236,0.00136809,0.0009921375,0.3035519,0.03124878,0.09621856,0.553201],"study_design_scores_gemma":[0.01804723,0.002333495,0.1298454,0.00850746,0.003453089,0.0002118239,0.003658081,0.2529207,0.4154163,0.0278813,0.1354245,0.002300584],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05680474,0.0002188738,0.9310103,0.00893455,0.0006813694,0.001504673,0.00001777086,0.0001681434,0.0006595765],"genre_scores_gemma":[0.9400172,0.0003886969,0.04168243,0.01487928,0.001724479,0.0005881512,0.0003036295,0.00005450955,0.0003615862],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8893279,"threshold_uncertainty_score":0.683899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02537982196075416,"score_gpt":0.3370252445486559,"score_spread":0.3116454225879017,"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."}}