{"id":"W4408061740","doi":"10.18280/ts.420145","title":"MSF-TransUNet: A Multi-Scale Feature Fusion Transformer-Based U-Net for Medical Image Segmentation with Uniform Attention","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Science Foundation of Zhejiang Province","keywords":"Artificial intelligence; Segmentation; Computer science; Computer vision; Image segmentation; Transformer; Pattern recognition (psychology); Feature (linguistics); Scale (ratio); Cartography; Geography; Engineering; Electrical engineering; Voltage","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005564507,0.000848996,0.001025528,0.001226319,0.0004261078,0.0007384293,0.001239807,0.0009968949,0.00411685],"category_scores_gemma":[0.0007693842,0.0003591441,0.0008242591,0.0009934395,0.0003513776,0.001088032,0.001022296,0.0006644207,0.001433293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005424323,"about_ca_system_score_gemma":0.0007868591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004667224,"about_ca_topic_score_gemma":0.006512094,"domain_scores_codex":[0.9997445,0.00003432056,0.0000126799,0.00007221726,0.0001002426,0.0000361319],"domain_scores_gemma":[0.9998147,0.00005030328,0.00001596812,0.00002968932,0.0000680822,0.00002126865],"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":[0.0005745688,0.0001395202,0.0006595054,0.0001394765,0.0001119232,0.0001542093,0.00005277454,0.02602961,0.06390918,0.004327595,0.006184102,0.8977177],"study_design_scores_gemma":[0.00002839581,0.0002113149,0.0009621513,0.000019353,0.00007638137,0.0003867349,0.00002702401,0.9288051,0.05953693,0.00396815,0.005948168,0.00003039672],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008290567,0.0003941746,0.9870028,0.00006155512,0.00005387243,0.00004836384,0.0001396167,0.002943779,0.001065163],"genre_scores_gemma":[0.2131034,0.000528979,0.7776138,0.0002756109,0.00008894205,0.0001273758,0.0007653298,0.000532611,0.006963979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004667224,"threshold_uncertainty_score":0.01377225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009767675175327109,"score_gpt":0.2819626240038401,"score_spread":0.272194948828513,"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."}}