{"id":"W4412558155","doi":"10.1016/j.compbiomed.2025.110716","title":"DualSwinUnet++: An enhanced Swin-Unet architecture with dual decoders for PTMC segmentation","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dual (grammatical number); Architecture; Computer science; Computer architecture; Segmentation; Dual purpose; Artificial intelligence; Embedded system; Engineering; Geography","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":[0.00008737362,0.00009141791,0.0001773124,0.000179749,0.00003255716,0.000003667703,0.00003660158,0.00006243544,0.00001097432],"category_scores_gemma":[0.000009338588,0.00006712256,0.00001276215,0.000136296,0.00008761037,0.00002203083,0.000007129336,0.00007773977,2.947007e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001235904,"about_ca_system_score_gemma":0.000006835768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007166996,"about_ca_topic_score_gemma":0.0001153371,"domain_scores_codex":[0.9995676,0.00002213081,0.000127275,0.0001436092,0.00002116485,0.0001181916],"domain_scores_gemma":[0.9997798,0.00009201394,0.00001541728,0.0000598507,0.00001682212,0.00003616441],"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":[0.0007327882,0.0001105576,0.01009606,0.000418359,0.0007161166,0.0000133223,0.005082985,0.0382196,0.07198934,0.003559013,0.004565312,0.8644965],"study_design_scores_gemma":[0.07687849,0.008142154,0.07553396,0.00310102,0.001230658,0.000106321,0.009449444,0.688151,0.04903278,0.05961835,0.02609687,0.00265898],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4519971,0.000231088,0.5463603,0.0005170224,0.0002450003,0.0001453442,0.000003192709,0.00005355772,0.0004473266],"genre_scores_gemma":[0.9863188,0.0001053402,0.01244703,0.0007994964,0.00008473571,0.00002710017,0.0001767217,0.000005550365,0.00003526768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8618376,"threshold_uncertainty_score":0.2737178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00783238459679488,"score_gpt":0.2872051836554893,"score_spread":0.2793727990586944,"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."}}