Objective To assess the utility of clinical and MRI features in distinguishing ovarian clear cell carcinoma (CCC) from adnexal masses with ovarian-adnexal reporting and data system (O-RADS) MRI scores of 4–5. Methods This retrospective study included 850 patients with indeterminate adnexal masses on ultrasound. Two radiologists evaluated all preoperative MRIs using the O-RADS MRI risk stratification system. Patients with O-RADS MRI scores of 4–5 were divided into a training set (n = 135, hospital A) and a test set (n = 86, hospital B). Clinical and MRI features were compared between CCC and non-CCC patients. Analysis of variance and support vector machine were used to develop four CCC prediction models. Tenfold cross-validation was applied to determine the hyperparameters. Model performance was evaluated by the area under the curve (AUC) and decision curve. Results 221 patients were included (30 CCCs, 191 non-CCCs). CA125, HE4, CEA, ROMA, endometriosis, shape, parity, unilocular, component, the growth pattern of mural nodules, high signal on T1WI, number of nodules, the ratio of signal intensity, and the ADC value were significantly different between CCCs and non-CCCs. The kappa and interobserver correlation coefficient of each MRI feature exceeded 0.85. The comprehensive model combining clinical and MRI features had a greater AUC than the clinical model and tumour maker model (0.92 vs 0.66 and 0.78 in the test set; both p < 0.05), displaying improved net benefit. Conclusions The comprehensive model combining clinical and MRI features can effectively differentiate CCC from adnexal masses with O-RADS MRI scores of 4–5. Critical relevance statement CCC has a high incidence rate in Asians and has limited sensitivity to platinum chemotherapy. This comprehensive model improves CCC prediction ability and clinical applicability for facilitating individualised clinical decision-making. Key Points <UnorderedList Mark="Bullet"> <ItemContent> Identifying ovarian CCC preoperatively is beneficial for treatment planning. </ItemContent> <ItemContent> Ovarian CCC tends to be high-signal on T1WI, unilocular, big size, with endometriosis and low CEA. </ItemContent> <ItemContent> This model, integrating clinical and MRI features, can differentiate ovarian CCC from adnexal masses with O-RADS MRI scores 4–5. </ItemContent> </UnorderedList> Graphical Abstract

The value of MRI in differentiating ovarian clear cell carcinoma from other adnexal masses with O-RADS MRI scores of 4–5

期刊论文
出版模式：

开放获取
发表日期：

2025年1月29日

查看全文

Lingling Lin,
Le Fu,
Huawei Wu,
Saiming Cheng,
Guangquan Chen,
Lei Chen,
Jun Zhu,
Yu Wang,
Jiejun Cheng

摘要

Objective

To assess the utility of clinical and MRI features in distinguishing ovarian clear cell carcinoma (CCC) from adnexal masses with ovarian-adnexal reporting and data system (O-RADS) MRI scores of 4–5.

Methods

This retrospective study included 850 patients with indeterminate adnexal masses on ultrasound. Two radiologists evaluated all preoperative MRIs using the O-RADS MRI risk stratification system. Patients with O-RADS MRI scores of 4–5 were divided into a training set (n = 135, hospital A) and a test set (n = 86, hospital B). Clinical and MRI features were compared between CCC and non-CCC patients. Analysis of variance and support vector machine were used to develop four CCC prediction models. Tenfold cross-validation was applied to determine the hyperparameters. Model performance was evaluated by the area under the curve (AUC) and decision curve.

Results

221 patients were included (30 CCCs, 191 non-CCCs). CA125, HE4, CEA, ROMA, endometriosis, shape, parity, unilocular, component, the growth pattern of mural nodules, high signal on T1WI, number of nodules, the ratio of signal intensity, and the ADC value were significantly different between CCCs and non-CCCs. The kappa and interobserver correlation coefficient of each MRI feature exceeded 0.85. The comprehensive model combining clinical and MRI features had a greater AUC than the clinical model and tumour maker model (0.92 vs 0.66 and 0.78 in the test set; both p < 0.05), displaying improved net benefit.

Conclusions

The comprehensive model combining clinical and MRI features can effectively differentiate CCC from adnexal masses with O-RADS MRI scores of 4–5.

Critical relevance statement

CCC has a high incidence rate in Asians and has limited sensitivity to platinum chemotherapy. This comprehensive model improves CCC prediction ability and clinical applicability for facilitating individualised clinical decision-making.

Key Points

Identifying ovarian CCC preoperatively is beneficial for treatment planning.

Ovarian CCC tends to be high-signal on T1WI, unilocular, big size, with endometriosis and low CEA.

This model, integrating clinical and MRI features, can differentiate ovarian CCC from adnexal masses with O-RADS MRI scores 4–5.

Graphical Abstract