Integrating O-RADS，Contrast-enhanced Ultrasound and ROMA z-score for Three-category Prediction of Ovarian Epithelial Tumors
10.11714/jsysu.med.YX20260009
- VernacularTitle:O-RADS联合超声造影与ROMA z-score三分类预测卵巢上皮肿瘤
- Author:
Kun YUAN
1
;
Xiaomin ZHU
1
;
Huanyu ZHANG
2
;
Yujun HUANG
1
;
Qingying LI
1
;
Yan OU
1
;
Yunxiao ZHU
1
Author Information
1. Department of Medical Ultrasonics， The Seventh Affiliated Hospital of Sun Yat-sen University ， Shenzhen 518107， China
2. Department of Clinical Big Data Research Center， The Seventh Affiliated Hospital of Sun Yat-sen University， Shenzhen 518107， China
- Publication Type:Journal Article
- Keywords:
ovarian epithelial tumors;
O-RADS;
contrast-enhanced ultrasound;
the risk of ovarian malignancy algorithm;
carbonhydrate antigen 125;
human epididymis 4
- From:
Journal of Sun Yat-sen University(Medical Sciences)
2026;47(2):336-345
- CountryChina
- Language:Chinese
-
Abstract:
ObjectiveTo develop and evaluate an O-RADSbased multiparametric model integratingcontrast-enhanced US （CEUS） and the z-score standardized risk of ovarian malignancy algorithm （ROMA z-score） to improve the diagnostic accuracy for differentiating benign， borderline， and malignant ovarian epithelial tumors （OETs）. MethodsThis retrospective study included 129 patients with pathologically confirmed OETs between May 2018 and December 2024. Clinical variables （age， menopausal status， BMI， HE4， CA125） and sonographic features （conventional US and CEUS） were collected. Tumors were classified as benign， borderline， or malignant according to pathological findings. A random forest algorithm was used to contruct the predictive model. Receiver operating characteristic （ROC） curves were generated tocompare the diagnostic performance of O-RADS， O-RADS+CEUS， O-RADS+ROMA z-score， and O-RADS+ CEUS+ROMA z-score. ResultsAmong the 129 patients， 63 had benign tumors， 25 had borderline tumors， and 41 had malignant tumors. Compared with O-RADS alone， the combined O-RADS+CEUS+ROMA z-score model demonstrated superior diagnostic performance， with an AUC of 0.87 （95% CI： 0.79-0.95） vs. 0.64 （95% CI： 0.51-0.76）， P＜0.001， for differentiating benign from borderline tumors， and 0.90 （95% CI： 0.83-0.97） vs. 0.64 （95% CI： 0.50-0.78）， P＜0.001， for differentiating borderline from malignant tumors. The random forest analysis identified HE4， CA125 and CEUS features as the most important predictors，contributing 11.02， 8.82， 18.1 points， respectively， to the total importance score of 51.94. In the test cohort， the model achieved an overall diagnostic accuracy of 72.97%， with an AUC of 0.89（95%CI：0.77-1.00）， sensitivity of 67.06%， and specificity of 85.01%. ConclusionsO-RADS+CEUS+ROMA z-score multiparametric model demonstrated the highest diagnostic performance for in differentiating benign from borderline and borderline from malignant OETs. HE4， CA125 and CEUS features were identified as key predictive risk factors， supporting the role of this model in improving preoperative risk stratification of OETs.
