{"id":"W7114779469","doi":"10.48550/arxiv.2512.08243","title":"Residual-SwinCA-Net: A Channel-Aware Integrated Residual CNN-Swin Transformer for Malignant Lesion Segmentation in BUSI","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Discriminative model; Robustness (evolution); Encoder; Residual; Pattern recognition (psychology); Pixel","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":[0.0004252959,0.00120112,0.00064152,0.0007279914,0.0002561507,0.0007794775,0.001948472,0.0008144753,0.003181883],"category_scores_gemma":[0.0007236235,0.0004460853,0.0005321907,0.0004309018,0.0002956474,0.0007670602,0.0008475246,0.0007747451,0.001222927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007903851,"about_ca_system_score_gemma":0.001242536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007197218,"about_ca_topic_score_gemma":0.01957077,"domain_scores_codex":[0.9998499,0.00001366676,0.00000631165,0.00004500723,0.00004909097,0.00003592813],"domain_scores_gemma":[0.999858,0.00002848505,0.00001636931,0.00002732005,0.00004657693,0.00002326468],"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":[0.0008102737,0.0002756767,0.006071544,0.000424618,0.0003320492,0.0004260393,0.0001236538,0.1366529,0.08874658,0.00482895,0.02247785,0.7388298],"study_design_scores_gemma":[0.00003172025,0.0002029749,0.001456628,0.00002608655,0.00007436385,0.0003231593,0.00003204835,0.9516128,0.03772905,0.001819441,0.006663616,0.00002798251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.141248,0.002829214,0.8208392,0.000635786,0.000283529,0.0003726981,0.00245707,0.02005193,0.01128269],"genre_scores_gemma":[0.5792458,0.0009868522,0.3902059,0.0008359115,0.0001020495,0.0002467488,0.008115563,0.001095442,0.01916567],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007197218,"threshold_uncertainty_score":0.01431066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08994713190645673,"score_gpt":0.2291300551007074,"score_spread":0.1391829231942507,"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."}}