{"id":"W4413238470","doi":"10.1007/s00521-025-11515-9","title":"A lightweight convolutional neural network based on U shape structure and attention mechanism for anterior mediastinum segmentation","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Computational Science and Engineering; Computer science; Mechanism (biology); Segmentation; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Anterior mediastinum; Anatomy; Mediastinum; Machine learning; Physics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008728046,0.0001399292,0.0001813834,0.00009764405,0.0003967677,0.00005165681,0.0000473313,0.00006935307,0.000006784379],"category_scores_gemma":[0.00004516302,0.0001301461,0.00004834431,0.0002120791,0.00005521663,0.00003135828,0.00003623908,0.0001328173,6.41798e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004520698,"about_ca_system_score_gemma":0.00004358647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007523896,"about_ca_topic_score_gemma":0.000004381041,"domain_scores_codex":[0.9990889,0.00002961838,0.0002206519,0.0003609897,0.0001194888,0.0001802832],"domain_scores_gemma":[0.9991465,0.0004389458,0.00009201788,0.0001340553,0.0001155812,0.00007293342],"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":[0.001348425,0.0008985488,0.0945073,0.002749692,0.0003116136,0.00001194192,0.0004041974,0.01872206,0.1502329,0.08852591,0.01818395,0.6241034],"study_design_scores_gemma":[0.001454163,0.0001646624,0.04952285,0.0002401981,0.0001331887,0.00001127055,0.00001827887,0.9435734,0.00107898,0.002053374,0.001626837,0.0001228635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8830196,0.0002356404,0.0850446,0.02937463,0.0002862775,0.001751346,0.00007619735,0.0001838342,0.00002788708],"genre_scores_gemma":[0.9829575,0.000007099035,0.004749916,0.01161963,0.0003622419,0.0001139728,0.0001422111,0.00001273082,0.00003466745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9248512,"threshold_uncertainty_score":0.5307202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01573842321050209,"score_gpt":0.3075060407824098,"score_spread":0.2917676175719077,"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."}}