Objective To evaluate the diagnostic value of the nine Morphological Uterus Sonographic Assessment (MUSA)‐defined ultrasonographic features for adenomyosis and develop an ultrasound scoring system to improve diagnostic accuracy. Methods This retrospective study analyzed ultrasound images from patients who underwent total hysterectomy between May 2023 and December 2024, in accordance with the MUSA consensus. The cohort was split into training and testing sets. Ridge regression was applied to the training set to develop an ultrasound scoring system based on the regression coefficients of each sign, which was subsequently validated in the test set. Correlations between the ultrasound score and preoperative hemoglobin, dysmenorrhea were evaluated. Results Interrupted junctional zone and myometrial cysts showed highest specificity (89.0%, 88.5%), hyperechoic islands highest sensitivity (69.2%). In the training set, the scoring system achieved an area under the curve (AUC) of 0.948 (95% CI 0.901–0.990), sensitivity 86.3%, specificity 87.3%, accuracy 86.8%. In the testing set, AUC was 0.894 (95% CI 0.856–0.931), sensitivity 79.4%, specificity 83.9%, accuracy 81.7%. No significant correlation existed between ultrasound score and hemoglobin ( ρ = 0.017, P = .824), but a weak positive correlation was found with Visual Analogue Scale (VAS) scores ( ρ = 0.178, P = .016). Conclusion All nine MUSA features contribute to adenomyosis diagnosis, but no single sign is sufficiently accurate alone. The ultrasound scoring system significantly enhances transvaginal ultrasound diagnostic performance and shows strong clinical potential. Higher scores correlate modestly with greater dysmenorrhea severity.
Hu et al. (Thu,) studied this question.