Share：
Share this content in WeChat
X
[Chinese] [PDF] 32 1
• Clinical Article •
The value of radiomics nomogram based on multiparametric MRI in differentiating benign and malignant ovarian O-RADS 4 masses
WANG Zitang  ZHANG Lingxia  BAI Tianjun  CHEN Chao  ZENG Qingshi 

Cite this article as: WANG Z T, ZHANG L X, BAI T J, et al. The value of radiomics nomogram based on multiparametric MRI in differentiating benign and malignant ovarian O-RADS 4 masses[J]. Chin J Magn Reson Imaging, 2026, 17(10): 125-133. DOI:10.12015/issn.1674-8034.2026.10.015.


[Abstract] Objective To develop a radiomics nomogram based on multi-parameter magnetic resonance imaging (mpMRI) and evaluate its performance in distinguishing benign from malignant ovarian-adnexal reporting and data system (O-RADS) 4 ovarian lesions.Materials and Methods This is a retrospective, single-center study on developing a diagnostic prediction model. This study included 178 O-RADS 4 ovarian masses from 178 patients with ovarian space occupying lesions, with 69 benign and 109 malignant. All lesions were randomly divided into a training set and a validation set at a 7∶3 ratio. Radiomics features were extracted from axial T2-weighted imaging (T2WI), T1-weighted imaging (T1WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1WI (CE-T1WI) sequences for each lesion. Relevant features were selected using minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) regression to build a radiomics model. A radiomics nomogram was then constructed by combining radiomics features with clinical characteristics through multivariate logistic regression. The nomogram's performance was assessed using receiver operating characteristic (ROC) curve analysis, with comparisons performed by DeLong test. Calibration curves and decision curve analysis were used to evaluate the nomogram's goodness-of-fit and clinical usefulness.Results After feature selection, 16 radiomics features were retained. The radiomics nomogram combining human epididymis protein 4 (HE4) and radiomics score (Radscore) achieved area under the curve (AUC) values of 0.885 [95% confidence interval (CI): 0.824 to 0.946] in the training set and 0.877 (95% CI: 0.782 to 0.971) in the validation set, with accuracies of 85.7% and 84.6%, respectively. ROC and decision curve analyses showed that the radiomics nomogram outperformed both the clinical model and the radiomics-only model.Conclusions The radiomics nomogram integrating mpMRI-based radiomics features with clinical factors can accurately and intuitively differentiate benign from malignant O-RADS 4 ovarian lesions. It can provide a non-invasive imaging reference for individualized preoperative risk assessment.
[Keywords] ovarian mass；radiomics；nomogram；magnetic resonance imaging；ovarian-adnexal reporting and date system

WANG Zitang1, 2   ZHANG Lingxia2   BAI Tianjun2   CHEN Chao3   ZENG Qingshi1, 4*  

1 Department of Radiology, Shandong Provincial Qianfoshan Hospital, Shandong University, Jinan 250014, China

2 Department of Radiology, The Second People's Hospital of Liaocheng, Liaocheng 252600, China

3 Qilu University of Technology (Shandong Academy of Sciences) / Shandong Artificial Intelligence Institute, Jinan 250014, China

4 Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan 250014, China

Corresponding author: ZENG Q S, E-mail: zengqingshi@sina.com

Conflicts of interest   None.

Received  2026-04-10
Accepted  2026-09-10
DOI: 10.12015/issn.1674-8034.2026.10.015
Cite this article as: WANG Z T, ZHANG L X, BAI T J, et al. The value of radiomics nomogram based on multiparametric MRI in differentiating benign and malignant ovarian O-RADS 4 masses[J]. Chin J Magn Reson Imaging, 2026, 17(10): 125-133. DOI:10.12015/issn.1674-8034.2026.10.015.

[1]
BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.
[2]
NOUGARET S, LAKHMAN Y, BAHADIR S, et al. Ovarian-adnexal reporting and data system for magnetic resonance imaging (O-RADS MRI): genesis and future directions[J]. Can Assoc Radiol J, 2023, 74(2): 370-381. DOI: 10.1177/08465371221121738.
[3]
CHEN J, YANG F, LIU C Z, et al. Diagnostic value of a CT-based radiomics nomogram for discrimination of benign and early stage malignant ovarian tumors[J]. Eur J Med Res, 2023, 28(1): 609. DOI: 10.1186/s40001-023-01561-1.
[4]
WANG W H, ZHENG C B, GAO J N, et al. Systematic review and meta-analysis of imaging differential diagnosis of benign and malignant ovarian tumors[J]. Gland Surg, 2022, 11(2): 330-340. DOI: 10.21037/gs-21-889.
[5]
HASSAN R M A, ABDEL MONEM EBRAHIM S, AHMAD KAMAL M R, et al. The impact of using ovarian-adnexal reporting data system magnetic resonance imaging (O-RADS MRI) score on risk stratification of sonographically indeterminate adnexal masses[J/OL]. Egypt J Radiol Nucl Med, 2024, 55(1): 82 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/31977064/. DOI: 10.1186/s43055-024-01252-9.
[6]
RIZZO S, COZZI A, DOLCIAMI M, et al. O-RADS MRI: A systematic review and meta-analysis of diagnostic performance and category-wise malignancy rates[J/OL]. Radiology, 2023, 307: e220795 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/36413127/. DOI: 10.1148/radiol.220795.
[7]
BUYS S S, PARTRIDGE E, BLACK A, et al. Effect of screening on ovarian cancer mortality: the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Randomized Controlled Trial[J]. JAMA, 2011, 305(22): 2295-2303. DOI: 10.1001/jama.2011.766.
[8]
JACOBS I J, MENON U, RYAN A, et al. Ovarian cancer screening and mortality in the UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS): a randomised controlled trial[J]. Lancet, 2016, 387(10022): 945-956. DOI: 10.1016/S0140-6736(15)01224-6.
[9]
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[10]
YANG Z T, WU H, GAO H Y, et al. Advances in deep learning and radiomics on ovarian cancer[J]. Chin J Magn Reson Imaging, 2025, 16(9): 223-228. DOI: 10.12015/issn.1674-8034.2025.09.034.
[11]
QIAN L D, REN J L, LIU A S, et al. MR imaging of epithelial ovarian cancer: a combined model to predict histologic subtypes[J]. Eur Radiol, 2020, 30(11): 5815-5825. DOI: 10.1007/s00330-020-06993-5.
[12]
WANG X Y, WEI M X, CHEN Y, et al. Intratumoral and peritumoral MRI-based radiomics for predicting extrapelvic peritoneal metastasis in epithelial ovarian cancer[J/OL]. Insights Imaging, 2024, 15(1): 281 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/39576435/. DOI: 10.1186/s13244-024-01855-w.
[13]
LI H M, CAI S Q, DENG L, et al. Prediction of platinum resistance for advanced high-grade serous ovarian carcinoma using MRI-based radiomics nomogram[J]. Eur Radiol, 2023, 33(8): 5298-5308. DOI: 10.1007/s00330-023-09552-w.
[14]
LEI Y, TANG H Z, LIU L L, et al. The value of texture analysis of multi-parameter MRI images in distinguishing benign and malignant lesions of O-RADS MRI 4 lesions[J]. Int J Med Sci, 2025, 22(6): 1425-1436. DOI: 10.7150/ijms.107452.
[15]
WHO Classification of Tumours Editorial Board. WHO Classification of Tumours: Female Genital Tumours [M]. 5th ed. Vol.4. Lyon: IARC Press, 2020.
[16]
ASSOULINE V, DABI Y, JALAGUIER-COUDRAY A, et al. How to improve O-RADS MRI score for rating adnexal masses with cystic component [J]. Eur Radiol, 2022, 32(9): 5943-5953. DOI: 10.1007/s00330-022-08644-3.
[17]
WONG B Z Y, CAUSA ANDRIEU P I, SONODA Y, et al. Improving risk stratification of indeterminate adnexal masses on MRI: What imaging features help predict malignancy in O-RADS MRI 4 lesions [J/OL]. Eur J Radiol, 2023, 168: 111122 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/37806193/. DOI: 10.1016/j.ejrad.2023.111122.
[18]
LIU L, CAI W J, TIAN H Y, et al. Ultrasound image-based nomogram combining clinical, radiomics, and deep transfer learning features for automatic classification of ovarian masses according to O-RADS[J/OL]. Front Oncol, 2024, 14: 1377489 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/38812784/. DOI: 10.3389/fonc.2024.1377489.
[19]
MUINAO T, DEKA BORUAH H P, PAL M. Multi-biomarker panel signature as the key to diagnosis of ovarian cancer[J/OL]. Heliyon, 2019, 5(12): e02826 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/31867451/. DOI: 10.1016/j.heliyon.2019.e02826.
[20]
VERMA N, TIWARI V, SHARMA S P, et al. Clinico-pathological correlation of ovarian tumors and tumor like lesions with role of CA125 and HE4 as biomarkers for discrimination of benign and malignant ovarian tumors[J/OL]. Int J Res Med Sci, 2018, 6(7): 2238 [2026-04-09]. https://www.msjonline.org/index.php/ijrms/article/view/4923. DOI: 10.18203/2320-6012.ijrms20182426.
[21]
ZHANG X Q, LIN S H, LIN Z L, et al. The value of a clinical-multiparametric MRI prediction model based on O-RADS MRI scoring system in differentiating between benign and malignant adnexal masses of the uterus[J]. Chin J Magn Reson Imaging, 2025, 16(7): 39-46. DOI: 10.12015/issn.1674-8034.2025.07.006.
[22]
DING C, WEI M X, JIA J Y, et al. Differentiation of borderline and malignant epithelial tumors based on MRI-T2WI radiomics nomogram[J]. Chin J Magn Reson Imaging, 2022, 13(7): 55-60. DOI: 10.12015/issn.1674-8034.2022.07.010.
[23]
TOMASZEWSKI M R, GILLIES R J. The biological meaning of radiomic features[J]. Radiology, 2021, 298(3): 505-516. DOI: 10.1148/radiol.2021202553.
[24]
KOAY E J, LEE Y, CRISTINI V, et al. A visually apparent and quantifiable CT imaging feature identifies biophysical subtypes of pancreatic ductal adenocarcinoma[J]. Clin Cancer Res, 2018, 24(23): 5883-5894. DOI: 10.1158/1078-0432.ccr-17-3668.
[25]
LIANG J, DU X, WANG X L, et al. Application value of MRI texture analysis based on GLCM in differential diagnosis of intraspinal meningioma and schwannoma[J]. Chin J Magn Reson Imaging, 2022, 13(8): 84-87. DOI: 10.12015/issn.1674-8034.2022.08.016.2026.04.003.
[26]
GROSSMANN P, STRINGFIELD O, EL-HACHEM N, et al. Defining the biological basis of radiomic phenotypes in lung cancer[J/OL]. eLife, 2017, 6: e23421 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/28731408/. DOI: 10.7554/elife.23421.
[27]
MANGANARO L, CIULLA S, CELLI V, et al. Impact of DWI and ADC values in ovarian-adnexal reporting and data system (O-RADS) MRI score[J]. La Radiol Med, 2023, 128(5): 565-577. DOI: 10.1007/s11547-023-01628-3.
[28]
HOTTAT N A, VAN PACHTERBEKE C, VANDEN HOUTE K, et al. Magnetic resonance scoring system for assessment of adnexal masses: added value of diffusion-weighted imaging including apparent diffusion coefficient map[J]. Ultrasound Obstet & Gyne, 2021, 57(3): 478-487. DOI: 10.1002/uog.22090.
[29]
MOSKOWITZ C S, WELCH M L, JACOBS M A, et al. Radiomic analysis: study design, statistical analysis, and other bias mitigation strategies[J]. Radiology, 2022, 304(2): 265-273. DOI: 10.1148/radiol.211597.
[30]
LIU L, CAI W J, ZHENG F B, et al. Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses[J/OL]. Insights Imaging, 2025, 16(1): 14 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/39804536/. DOI: 10.1186/s13244-024-01874-7.
[31]
ZHU H Y, AI Y, ZHANG J D, et al. Preoperative nomogram for differentiation of histological subtypes in ovarian cancer based on computer tomography radiomics[J/OL]. Front Oncol, 2021, 11: 642892 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/33842352/. DOI: 10.3389/fonc.2021.642892.
[32]
YU X P, WANG L, YU H Y, et al. MDCT-based radiomics features for the differentiation of serous borderline ovarian tumors and serous malignant ovarian tumors[J]. Cancer Manag Res, 2021, 13: 329-336. DOI: 10.2147/CMAR.S284220.
[33]
LI S Y, LIU J Q, XIONG Y H, et al. A radiomics approach for automated diagnosis of ovarian neoplasm malignancy in computed tomography[J/OL]. Sci Rep, 2021, 11: 8730 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/33888749/. DOI: 10.1038/s41598-021-87775-x.
[34]
WEI M X, ZHANG Y, BAI G J, et al. T2-weighted MRI-based radiomics for discriminating between benign and borderline epithelial ovarian tumors: a multicenter study[J/OL]. Insights Imaging, 2022, 13(1): 130 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/35943620/. DOI: 10.1186/s13244-022-01264-x.
[35]
HU Y M, WENG Q Y, XIA H H, et al. A radiomic nomogram based on arterial phase of CT for differential diagnosis of ovarian cancer[J]. Abdom Radiol, 2021, 46(6): 2384-2392. DOI: 10.1007/s00261-021-03120-w.
[36]
ZHAO L, ZHANG M W, GUO H D, et al. Construction of mammography-based nomogram models for predicting HR and HER2 expression in breast cancer[J/OL]. Chin J Clin Electron Ed, 2025, 19(10): 747-757 [2026-04-09]. https://rs.yiigle.com/cmaid/1663713. DOI: 10.3877/cma.j.issn.1674-0785.2025.10.004.
[37]
HOU X X, GUO J S, CHEN X Y. Diagnostic value of four types of breast BI-RADS nodules by constructing a nomogram based on multi-modal ultrasound features combined with inflammatory complex indicators[J]. Chin J Endocr Surg, 2024, 18(6): 859-864. DOI: 10.3760/cma.j.cn115807-20240423-00132.
[38]
ZHANG H, MAO Y F, CHEN X J, et al. Magnetic resonance imaging radiomics in categorizing ovarian masses and predicting clinical outcome: a preliminary study[J]. Eur Radiol, 2019, 29(7): 3358-3371. DOI: 10.1007/s00330-019-06124-9.
[39]
ZHANG X H, WANG J J, WU Z F, et al. A joint model based on multi-sequence MRI imaging radiomics for prediction of benign and malignant ovarian tumors[J]. Chin J Anat Clin, 2024, 29(6): 371-378. DOI: 10.3760/cma.j.cn101202-20230928-00096.
[40]
NAGAWA K, KISHIGAMI T, YOKOYAMA F, et al. Diagnostic utility of a conventional MRI-based analysis and texture analysis for discriminating between ovarian thecoma-fibroma groups and ovarian granulosa cell tumors[J/OL]. J Ovarian Res, 2022, 15(1): 65 [2026-04-09]. https://pubmed.ncbi.nlm.nih.gov/35610706/. DOI: 10.1186/s13048-022-00989-z.

PREV Preoperative prediction of extra-pelvic peritoneal metastasis in epithelial ovarian cancer using habitat radiomics from T2-weighted MRI
NEXT Quantitative assessment of myocardial tissue characteristics using intravoxel incoherent motion in a minipig model of acute myocardial infarction induced by transcatheter embolization
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn