The Journal of Practical Medicine >

2026 , Vol. 42 >Issue 7: 1192 - 1200

DOI: https://doi.org/10.3969/j.issn.1006-5725.2026.07.011

Oncology: Diagnosis, Treatment and Prevention

Developing an ovarian cancer diagnostic model from ultrasound radiomics， O‑RADS classification， and clinical factors

  • Jing YIN ,
  • Pingyang ZHANG ,
  • Junli WANG ,
  • Weiwei YIN ,
  • Xiaoai CHU ,
  • Wenyan ZHAO
Expand
  • 1.Department of Cardiovascular Ultrasound，Nanjing Hospital Affiliated to Nanjing Medical University，Nanjing First Hospital，Nanjing 210006，Jiangsu，China
    2.Department of Ultrasound Medicine，Wuhu Hospital Affiliated to East China Normal University，Wuhu Second People's Hospital，Wuhu 241000，Anhui，China
    3.Department of Ultrasound Medicine，First People's Hospital of Hefei，Hefei 230000，Anhui，China

Received date: 2025-12-01

  Revised date: 2025-12-26

  Accepted date: 2025-12-30

  Online published: 2026-04-13

Fold

Abstract

Objective This study aims to integrate ultrasound radiomics， the O-RADS （v2022） classification system， and clinical risk factors to develop and validate an intelligent diagnostic model for improving the accuracy of differentiating between benign and malignant ovarian tumors. Methods A multicenter， retrospective study design was adopted. A total of 596 patients who underwent surgery at our institution were enrolled and randomly split into a training set （n = 418） and an internal validation set （n = 178） at a 7：3 ratio. Additionally， 110 patients from an external hospital were recruited as an external test set. Model construction consisted of three core components： （1） extraction of 12 radiomics features from standardized ultrasound images； （2） O-RADS classification results derived from blinded assessments and consensus among three physicians； （3） clinical predictors （age， maximum tumor diameter， CA125， HE4， and menopausal status） identified through univariate and multivariate logistic regression screening. Three models were developed and compared： a standalone O-RADS model， a combined clinical-O-RADS model， and an integrated radiomics-clinical-O-RADS model. Results The integrated model exhibited the optimal diagnostic performance， with area under the curve （AUC） values of 0.95 in the training set， 0.92 in the internal validation set， and 0.89 in the external test set （P < 0.05）. Decision curve analysis （DCA） further confirmed that this model achieved a higher clinical net benefit across a wide range of threshold probabilities. Feature importance analysis revealed that radiomics features contributed the most to the model’s predictive power （approximately 60%）. Conclusions The integrated model combining ultrasound radiomics， O-RADS classification， and clinical factors significantly improves the preoperative diagnostic accuracy for distinguishing between benign and malignant ovarian lesions. It demonstrates good generalization ability and clinical utility， providing an objective and precise auxiliary tool to support clinical decision-making in ovarian tumor management.

Key words： ovarian cancer; ultrasound diagnosis; radiomics; O-RADS classification system; diagnostic model

Cite this article

Jing YIN , Pingyang ZHANG , Junli WANG , Weiwei YIN , Xiaoai CHU , Wenyan ZHAO . Developing an ovarian cancer diagnostic model from ultrasound radiomics， O‑RADS classification， and clinical factors[J]. The Journal of Practical Medicine, 2026 , 42(7) : 1192 -1200 . DOI: 10.3969/j.issn.1006-5725.2026.07.011

References

[1] WEI Y F， NING L， XU Y L， et al.Worldwide patterns and trends in ovarian cancer incidence by histological subtype： A population-based analysis from 1988 to 2017［J］. E Clin Med， 2024， 79： 102983. doi： 10.1016/j.eclinm.2024.102983 .
[2] WANG Y， WANG Z， ZHANG Z H， et al. Burden of ovarian cancer in China from 1990 to 2030： A systematic analysis and comparison with the global level［J］. Front Public Health， 2023， 11： 1136596. doi： 10.3389/fpubh.2023.1136596 .
[3] 秦绪颖， 王瑞国， 王稳， 等. 卵巢肿瘤良恶性风险评估方法学中国专家共识（2024年版）［J］.中国实用妇科与产科杂志， 2024， 40（3）： 312-320. doi： 10.19538/j.fk2024030113 .
[4] KOUTRAS A， PERROS P， PROKOPAKIS I， et al. Advantages and limitations of ultrasound as a screening test for ovarian cancer［J］. Diagnostics （Basel）， 2023， 13（12）： 2078. doi： 10.3390/diagnostics13122078 .
[5] GUO Y， PHILLIPS C H， SUAREZ-WEISS K， et al. Interreader agreement and intermodality concordance of O-RADS US and MRI for assessing large， complex ovarian-adnexal cysts［J］. Radiol Imaging Cancer， 2022， 4（5）： e220064. doi： 10.1148/rycan.220064 .
[6] AKKAYA H， DEMIREL E， DILEK O， et al. Ovarian-adnexal reporting and data system MRI scoring： Diagnostic accuracy， interobserver agreement， and applicability to machine learning［J］. Br J Radiol， 2025， 98（1166）： 254-261. doi： 10.1093/bjr/tqae221 .
[7] MATSAS A， STEFANOUDAKIS D， TROUPIS T， et al. Tumor markers and their diagnostic significance in ovarian cancer［J］. Life （Basel）， 2023， 13（8）： 1689. doi： 10.3390/life13081689 .
[8] SILVERWOOD S M， BACKER G， GALLOWAY A， et al. Assessing the rates of false-positive ovarian cancer screenings and surgical interventions associated with screening tools： A systematic review［J］. BMJ Oncol， 2024， 3（1）： e000404. doi： 10.1136/bmjonc-2024-000404 .
[9] SALIMA S， RACHMAWATI A， HARSONO A， et al. Ovarian cancer-self assessment： An innovation for early detection and risk assessment of ovarian cancer［J］. Asian Pac J Cancer Prev， 2022， 23（8）： 2643-2647. doi： 10.31557/APJCP.2022.23.8.264 .
[10] LI B， SUN M， YAO P， et al. Radiogenomics： A valuable tool for the clinical assessment and research of ovarian cancer［J］. J Comput Assist Tomogr， 2022， 46（3）： 371-378. doi： 10.1097/RCT.0000000000001279 .
[11] ZHOU J， CAO W， WANG L， et al. Application of artificial intelligence in the diagnosis and prognostic prediction of ovarian cancer［J］. Comput Biol Med， 2022， 146： 105608. doi： 10.1016/j.compbiomed.2022.105608 .
[12] 何尚鹏， 黄炜贤， 江燕辉， 等. 超声特征与超声影像组学对BethesdaⅢ类甲状腺结节良恶性再评价的价值［J］. 实用医学杂志， 2025， 41（12）： 1892-1898. doi： 10.3969/j.issn.1006-5725.2025.12.018 .
[13] HIETT A K， SONEK J D， GUY M， et al. Performance of IOTA Simple Rules， Simple Rules risk assessment， ADNEX model and O-RADS in differentiating between benign and malignant adnexal lesions in North American women［J］. Ultrasound Obstet Gynecol， 2022， 59（5）： 668-676. doi： 10.1002/uog.24777 .
[14] JHA P， GUPTA A， BARAN T M， et al. Diagnostic performance of the ovarian-adnexal reporting and data system （O-RADS） ultrasound risk score in women in the United States［J］. JAMA Netw Open， 2022， 5（6）： e2216370. doi： 10.1001/jamanetworkopen.2022.16370 .
[15] HAN J， WEN J， HU W. Comparison of O-RADS with the ADNEX model and IOTA SR for risk stratification of adnexal lesions： A systematic review and meta-analysis［J］. Front Oncol， 2024， 14： 1354837. doi： 10.3389/fonc.2024.1354837 .
[16] 苏漫婷， 吴曼丽， 张曼， 等. 超声造影提高O-RADS 4～5类附件肿块诊断准确性的多中心回顾性研究［J］. 新医学， 2025， 56（9）： 872-881. doi： 10.12464/j.issn.0253-9802.2025-0091 .
[17] GRANT E G. Adding contrast-enhanced US to O-RADS： A route to improved specificity？［J］. Radiology， 2023， 308（2）： e231483. doi： 10.1148/radiol.231483 .
[18] 刘芳欣， 王洲， 李健， 等. 超声O-RADS分类联合超声造影及血清CA125和HE4检测诊断绝经后卵巢肿物的应用价值［J］. 实用肿瘤杂志， 2023， 38（4）： 392-397. doi： 10.13267/j.cnki.syzlzz.2023.062 .
[19] 何丽英， 昌禹豪， 马强， 等. 基于超声影像组学和临床特征构建的联合模型诊断早期卵巢癌的临床价值［J］. 临床超声医学杂志， 2025， 27（1）： 39-47. doi： 10.16245/j.cnki.issn1008-6978.2025.01.016 .
[20] STRACHOWSKI L M， JHA P， PHILLIPS C H， et al. O-RADS US v2022： An update from the American College of Radiology's ovarian-adnexal reporting and data system US committee［J］. Radiology， 2023， 308（3）： e230685. doi： 10.1148/radiol.230685 .
[21] 杜阳春， 郑红雨， 陈海宁， 等. 深度学习超声影像组学列线图模型鉴别Ⅰ和Ⅱ型上皮性卵巢癌［J］. 实用医学杂志， 2025， 41（18）： 2920-2927. doi： 10.3969/j.issn.1006-5725.2025.18.020 .
[22] 王稳， 王兴国， 刘淑娟， 等. 交界性卵巢肿瘤诊治中国专家共识（2022年版）［J］. 中国实用妇科与产科杂志， 2022， 38（12）： 1185-1194. doi： 10.19538/j.fk2022120110 .
[23] POONYAKANOK V， TANMAHASAMUT P， JAISHUEN A. Prospective comparative trial comparing O-RADS， IOTA ADNEX model， and RMI score for preoperative evaluation of adnexal masses for prediction of ovarian cancer［J］. J Obstet Gynaecol Res， 2023， 49（5）： 1412-1417. doi： 10.1111/jog.15624 .
[24] LU B， LIU C， QI J， et al. Comparison of contrast-enhanced ultrasound， IOTA simple rules and O-RADS for assessing the malignant risk of sonographically appearing solid ovarian masses［J］. J Gynecol Obstet Hum Reprod， 2023， 52（4）： 102564. doi： 10.1016/j.jogoh.2023.102564 .
[25] SHANG J， LEI T， WU L， et al. Comparison of performance between O-RADS， IOTA simple rules risk assessment and ADNEX model in the discrimination of ovarian Brenner tumors［J］. Arch Gynecol Obstet， 2023， 308（3）： 961-970. doi： 10.1007/s00404-022-06903-8 .
[26] HENRY T， SUN R， LEROUSSEAU M， et al. Investigation of radiomics based intra-patient inter-tumor heterogeneity and the impact of tumor subsampling strategies［J］. Sci Rep， 2022， 12（1）： 17244. doi： 10.1038/s41598-022-20931-z .
[27] LAN W， HONG J， HUAYUN T. Advances in ovarian cancer radiomics： A bibliometric analysis from 2010 to 2024［J］. Front Oncol， 2024， 14： 1456932. doi： 10.3389/fonc.2024.1456932 .
[28] WANG D， SU N， WANG R， et al. Serous surface papillary borderline ovarian tumors： Correlation of sonographic features with clinic pathological findings［J］. Ultrasound Obstet Gynecol， 2024， 63（5）： 691-698. doi： 10.1002/uog.27454 .
[29] MASCILLINI F， MORO F， PASCIUTO T， et al. Imaging in gynecological disease （28）： Clinical and ultrasound characteristics of serous and mucinous cystadenomas in the adnexa［J］. Ultrasound Obstet Gynecol， 2025， 66（2）： 233-241. doi： 10.1002/uog.29248 .
[30] XIE X， MA S X， LUO X D， et al. Automatic recognition of adrenal incidentalomas using a two-stage cascade network： A multicenter study［J］. Ann Med， 2025， 57（1）. doi： 0.1080/07853890.2025.2540596 .
Options
Outlines

/

〈 〉