Parotid Ultrasound Radiomics Accurately Detects Sjögren's Disease, Surpassing Radiologist Visual Assessment

A radiomics-based support vector machine (SVM) model using parotid ultrasound distinguished Sjögren's disease from healthy controls with AUC 0.99, accuracy 0.94, sensitivity 0.86, specificity 0.96, outperforming radiologists' accuracy of 0.62–0.72.

• SHAP analysis identified intensity dispersion, GLCM texture, and LBP micro-texture features as strongest predictors.
• PCA revealed substantial radiomic overlap between non-Sjögren sicca and confirmed Sjögren's patients.
• Single-center study; the authors note validation in larger multicenter cohorts is required.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.