{"id":"W4407170397","doi":"10.3389/fonc.2025.1456563","title":"Improving diagnostic precision in thyroid nodule segmentation from ultrasound images with a self-attention mechanism-based Swin U-Net model","year":2025,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Thyroid Cancer Diagnosis and Treatment","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Nodule (geology); Segmentation; Thyroid nodules; Ultrasound; Mechanism (biology); Thyroid; Medicine; Computer science; Artificial intelligence; Radiology; Computer vision; Internal medicine; Biology; Physics","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":[0.0009226223,0.001075029,0.0007206526,0.0009146756,0.0003914327,0.001062326,0.00167154,0.001567545,0.001638944],"category_scores_gemma":[0.00169174,0.0004308905,0.0008502517,0.0004423753,0.0005772637,0.001018714,0.0008909825,0.0008615875,0.0005361785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00160064,"about_ca_system_score_gemma":0.001353986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01142624,"about_ca_topic_score_gemma":0.01297961,"domain_scores_codex":[0.9997465,0.00003995419,0.00001565808,0.00009605119,0.00005787754,0.00004398718],"domain_scores_gemma":[0.9995589,0.0001589475,0.00006067222,0.00004393759,0.0001423644,0.00003514159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006080188,0.0001821432,0.003778877,0.0001461231,0.0001471688,0.0002777946,0.0001062078,0.7186265,0.0160359,0.003629471,0.004021299,0.2524406],"study_design_scores_gemma":[0.000004396951,0.00003596435,0.0002015419,0.000006389393,0.00001597797,0.00003165832,0.000003968036,0.9963289,0.002510386,0.0006175081,0.0002389255,0.000004417622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1799978,0.002384509,0.8046157,0.000920659,0.0002294043,0.0002133181,0.0004193877,0.003837218,0.007382061],"genre_scores_gemma":[0.8593272,0.0006739885,0.1299887,0.0005899991,0.00009373734,0.000137192,0.0007104698,0.0002042809,0.008274355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01142624,"threshold_uncertainty_score":0.02271944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005160837039135114,"score_gpt":0.259532120545762,"score_spread":0.2543712835066269,"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."}}