Share：
Share this content in WeChat
X
[Chinese] [PDF] 27 1
• Clinical Article •
Utility of an MRI-based radiomics intratumoral heterogeneity scoring model for malignancy risk assessment of ovarian neoplasms
GUO Mingjun  ZHANG Di  FAN Hua  TAN Shuyu  SUN Siyu  ZHANG Chuanchen 

Cite this article as: GUO M J, ZHANG D, FAN H, et al. Utility of an MRI-based radiomics intratumoral heterogeneity scoring model for malignancy risk assessment of ovarian neoplasms[J]. Chin J Magn Reson Imaging, 2026, 17(4): 79-87. DOI:10.12015/issn.1674-8034.2026.04.011.


[Abstract] Objective To calculate an intratumoral heterogeneity (ITH) score using a magnetic resonance imaging (MRI)-based radiomics approach, to construct a preoperative malignancy risk assessment model for ovarian neoplasms by integrating clinical variables and conventional MRI features, and to evaluate its adjunctive value for risk stratification of Ovarian-Adnexal Reporting and Data System (O-RADS) MRI category 4 lesions and for diagnosis by junior physicians.Materials and Methods This retrospective study included 120 patients with pathologically confirmed ovarian neoplasms, including 52 benign and 68 malignant tumors, the latter including borderline tumors. The patients were randomly assigned to a training set (n = 84) and a test set (n = 36) in a 7∶3 ratio. After preprocessing T2-weighted images with spectral attenuated inversion recovery fat suppression, intratumoral and 3-mm peritumoral regions of interest were delineated. Radiomics features were extracted using a sliding-window approach, and K-means clustering was used to calculate the ITH score and the combined ITH score. Clinical features, conventional MRI features, and ITH scores were integrated. After screening by univariable analysis and least absolute shrinkage and selection operator regression, independent predictors were identified by multivariable logistic regression to construct a clinical model, an intratumoral model, and a combined model, respectively. All lesions were scored according to O-RADS MRI, and O-RADS MRI category 4 lesions were further analyzed for risk stratification; the adjunctive value of the model for diagnosis by junior physicians was also evaluated.Results The ITH score showed good intra- and interobserver agreement, with intra-class correlation coefficients of 0.86 and 0.84, respectively. Among the three models, the combined model based on the risk of ovarian malignancy algorithm (ROMA) index, tumor composition, and the combined ITH score achieved the highest diagnostic performance. In the test set, the areas under the receiver operating characteristic curve were 0.805 [95% confidence interval (CI): 0.662 to 0.948], 0.867 (95% CI: 0.750 to 0.984), and 0.923 (95% CI: 0.827 to 0.994) for the clinical, intratumoral, and combined models, respectively. The overall diagnostic performance of the O-RADS MRI score was comparable to that of the combined model. In the subgroup analysis of category 4 lesions, the combined model showed potential for further risk stratification, with relatively high diagnostic accuracy and specificity.Conclusion The combined model based on the ROMA index, tumor composition, and the combined ITH score showed the highest diagnostic performance for preoperative malignancy risk assessment of ovarian neoplasms. It also has the potential to stratify O-RADS MRI category 4 lesions and may assist clinicians in diagnosis.
[Keywords] ovarian neoplasms；tumor heterogeneity；radiomics；nomogram；magnetic resonance imaging；Ovarian-Adnexal Reporting and Data System；risk stratification

GUO Mingjun1, 2   ZHANG Di2   FAN Hua2   TAN Shuyu1, 2   SUN Siyu1, 2   ZHANG Chuanchen2*  

1 Graduate School of Shandong First Medical University, Shandong Academy of Medical Sciences, Jinan 250117, China

2 Medical Imaging Center, Liaocheng People's Hospital, Liaocheng 252000, China

Corresponding author: ZHANG C C, E-mail: zhangchuanchen666@163.com

Conflicts of interest   None.

Received  2025-12-05
Accepted  2026-03-27
DOI: 10.12015/issn.1674-8034.2026.04.011
Cite this article as: GUO M J, ZHANG D, FAN H, et al. Utility of an MRI-based radiomics intratumoral heterogeneity scoring model for malignancy risk assessment of ovarian neoplasms[J]. Chin J Magn Reson Imaging, 2026, 17(4): 79-87. DOI:10.12015/issn.1674-8034.2026.04.011.

[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]
GHOSE A, MCCANN L, MAKKER S, et al. Diagnostic biomarkers in ovarian cancer: advances beyond CA125 and HE4[J/OL]. Ther Adv Med Oncol, 2024, 16: 17588359241233225 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/38435431/. DOI: 10.1177/17588359241233225.
[3]
AVESANI G, PANICO C, NOUGARET S, et al. ESR Essentials: characterisation and staging of adnexal masses with MRI and CT-practice recommendations by ESUR[J]. Eur Radiol, 2024, 34(12): 7673-7689. DOI: 10.1007/s00330-024-10817-1.
[4]
THOMASSIN-NAGGARA I, PONCELET E, JALAGUIER-COUDRAY A, et al. Ovarian-adnexal reporting data system magnetic resonance imaging (O-RADS MRI) score for risk stratification of sonographically indeterminate adnexal masses[J/OL]. JAMA Netw Open, 2020, 3(1): e1919896 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/31977064/. DOI: 10.1001/jamanetworkopen.2019.19896.
[5]
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 [2026-03-20]. https://pubmed.ncbi.nlm.nih.gov/37806193/. DOI: 10.1016/j.ejrad.2023.111122.
[6]
BLAGDEN S P. Harnessing pandemonium: the clinical implications of tumor heterogeneity in ovarian cancer[J/OL]. Front Oncol, 2015, 5: 149 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/26175968/. DOI: 10.3389/fonc.2015.00149.
[7]
YU T, GAO X, ZHENG Z C, et al. Intratumor heterogeneity as a prognostic factor in solid tumors: a systematic review and meta-analysis[J/OL]. Front Oncol, 2021, 11: 744064 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/34722299/. DOI: 10.3389/fonc.2021.744064.
[8]
SHAN N L, KAHN A, PUSZTAI L. Intratumour heterogeneity, from hypothesis to the clinic[J]. Br J Cancer, 2023, 128(3): 459-460. DOI: 10.1038/s41416-022-02008-w.
[9]
GOYETTE M A, LIPSYC-SHARF M, POLYAK K. Clinical and translational relevance of intratumor heterogeneity[J]. Trends Cancer, 2023, 9(9): 726-737. DOI: 10.1016/j.trecan.2023.05.001.
[10]
ZHAO B, JU S H. Habitat imaging: exploring tumor heterogeneity[J]. Chin J Radiol, 2025, 59(4): 355-357. DOI: 10.3760/cma.j.cn112149-20241230-00767.
[11]
GUIOT J, VAIDYANATHAN A, DEPREZ L, et al. A review in radiomics: Making personalized medicine a reality via routine imaging[J]. Med Res Rev, 2022, 42(1): 426-440. DOI: 10.1002/med.21846.
[12]
SU G H, XIAO Y, YOU C, et al. Radiogenomic-based multiomic analysis reveals imaging intratumor heterogeneity phenotypes and therapeutic targets[J/OL]. Sci Adv, 2023, 9(40): eadf0837 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/37801493/. DOI: 10.1126/sciadv.adf0837.
[13]
LI J Q, QIU Z B, ZHANG C, et al. ITHscore: comprehensive quantification of intra-tumor heterogeneity in NSCLC by multi-scale radiomic features[J]. Eur Radiol, 2023, 33(2): 893-903. DOI: 10.1007/s00330-022-09055-0.
[14]
SHI Z W, HUANG X M, CHENG Z L, et al. MRI-based quantification of intratumoral heterogeneity for predicting treatment response to neoadjuvant chemotherapy in breast cancer[J/OL]. Radiology, 2023, 308(1): e222830 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/37432083/. DOI: 10.1148/radiol.222830.
[15]
HUANG Y, WANG X X, CAO Y, et al. Nomogram for predicting neoadjuvant chemotherapy response in breast cancer using MRI-based intratumoral heterogeneity quantification[J/OL]. Radiology, 2025, 315(1): e241805 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/40232145/. DOI: 10.1148/radiol.241805.
[16]
LI S L, DAI Y M, CHEN J Y, et al. MRI-based habitat imaging in cancer treatment: current technology, applications, and challenges[J/OL]. Cancer Imaging, 2024, 24(1): 107 [2025-12-23]. https://pubmed.ncbi.nlm.nih.gov/39148139/. DOI: 10.1186/s40644-024-00758-9.
[17]
HAUPTMANN S, FRIEDRICH K, REDLINE R, et al. Ovarian borderline tumors in the 2014 WHO classification: evolving concepts and diagnostic criteria[J]. Virchows Arch, 2017, 470(2): 125-142. DOI: 10.1007/s00428-016-2040-8.
[18]
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.
[19]
CHEN S Y, HUANG L, LIANG M L, et al. Advances in understanding the molecular mechanisms of borderline ovarian tumors[J/OL]. Front Mol Biosci, 2024, 11: 1429852 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/39281319/. DOI: 10.3389/fmolb.2024.1429852.
[20]
SURI A, PERUMAL V, AMMALLI P, et al. Diagnostic measures comparison for ovarian malignancy risk in Epithelial ovarian cancer patients: a meta-analysis[J/OL]. Sci Rep, 2021, 11(1): 17308 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/34453074/. DOI: 10.1038/s41598-021-96552-9.
[21]
GIAMOUGIANNIS P, MARTIN-HIRSCH P L, MARTIN F L. The evolving role of MUC16 (CA125) in the transformation of ovarian cells and the progression of neoplasia[J]. Carcinogenesis, 2021, 42(3): 327-343. DOI: 10.1093/carcin/bgab010.
[22]
ANASTASI E, FARINA A, GRANATO T, et al. Recent insight about HE4 role in ovarian cancer oncogenesis[J/OL]. Int J Mol Sci, 2023, 24(13): 10479 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/37445657/. DOI: 10.3390/ijms241310479.
[23]
KIM K, KHAZAN N, MCDOWELL J L, et al. The NF-κB-HE4 axis: a novel regulator of HE4 secretion in ovarian cancer[J/OL]. PLoS One, 2024, 19(12): e0314564 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/39621651/. DOI: 10.1371/journal.pone.0314564.
[24]
THOMASSIN-NAGGARA I, DABI Y, FLORIN M, et al. O-RADS MRI SCORE: an essential first-step tool for the characterization of adnexal masses[J]. J Magn Reson Imaging, 2024, 59(3): 720-736. DOI: 10.1002/jmri.28947.
[25]
SADOWSKI E A, THOMASSIN-NAGGARA I, ROCKALL A, et al. O-RADS MRI risk stratification system: guide for assessing adnexal lesions from the ACR O-RADS committee[J]. Radiology, 2022, 303(1): 35-47. DOI: 10.1148/radiol.204371.
[26]
LINDGREN A, ANTTILA M, ARPONEN O, et al. Dynamic contrast-enhanced MRI to characterize angiogenesis in primary epithelial ovarian cancer: an exploratory study[J/OL]. Eur J Radiol, 2023, 165: 110925 [2026-03-20]. https://pubmed.ncbi.nlm.nih.gov/37320880/. DOI: 10.1016/j.ejrad.2023.110925.
[27]
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.
[28]
BEER L, SAHIN H, BATEMAN N W, et al. Integration of proteomics with CT-based qualitative and radiomic features in high-grade serous ovarian cancer patients: an exploratory analysis[J]. Eur Radiol, 2020, 30(8): 4306-4316. DOI: 10.1007/s00330-020-06755-3.
[29]
MARUSYK A, ALMENDRO V, POLYAK K. Intra-tumour heterogeneity: a looking glass for cancer?[J]. Nat Rev Cancer, 2012, 12(5): 323-334. DOI: 10.1038/nrc3261.
[30]
ZHANG S E, REGAN K, NAJERA J, et al. The peritumor microenvironment: physics and immunity[J]. Trends Cancer, 2023, 9(8): 609-623. DOI: 10.1016/j.trecan.2023.04.004.
[31]
HOU J, LIU W Y. Advance of peritumoral radiomics research[J]. Chin J Magn Reson Imaging, 2024, 15(3): 230-234. DOI: 10.12015/issn.1674-8034.2024.03.038.
[32]
WU Y J, JIANG W Y, FU L Y, et al. Intra- and peritumoral radiomics for predicting early recurrence in patients with high-grade serous ovarian cancer[J]. Abdom Radiol (NY), 2023, 48(2): 733-743. DOI: 10.1007/s00261-022-03717-9.
[33]
LI Y A, JIAN J M, GE H J, et al. Peritumoral MRI radiomics features increase the evaluation efficiency for response to chemotherapy in patients with epithelial ovarian cancer[J]. J Magn Reson Imaging, 2024, 60(6): 2718-2727. DOI: 10.1002/jmri.29359.
[34]
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 [2026-03-20]. https://pubmed.ncbi.nlm.nih.gov/39576435/. DOI: 10.1186/s13244-024-01855-w.
[35]
BI Q, MIAO K, LIU Y, et al. mpMRI-based habitat analysis for predicting prognoses in patients with high-grade serous ovarian cancer: a multicenter study[J]. Abdom Radiol (NY), 2025, 50(12): 6039-6051. DOI: 10.1007/s00261-025-05004-9.
[36]
BI Q, MIAO K, XU N, et al. Habitat radiomics based on MRI for predicting platinum resistance in patients with high-grade serous ovarian carcinoma: a multicenter study[J]. Acad Radiol, 2024, 31(6): 2367-2380. DOI: 10.1016/j.acra.2023.11.038.
[37]
LIU Z N, MOUNI D, ZHANG S M, et al. Predicting the early response to neoadjuvant chemotherapy in high-grade serous ovarian cancer by intratumoral habitat heterogeneity based on 18F-FDG PET/CT[J]. Eur J Nucl Med Mol Imaging, 2026, 53(2): 979-991. DOI: 10.1007/s00259-025-07480-z.
[38]
YU X P, ZOU Y W, WANG C, et al. Habitat-based radiomics for preoperative differentiation between early-stage serous borderline ovarian tumors and malignant ovarian tumors[J/OL]. Front Oncol, 2025, 15: 1559398 [2025-12-23]. https://pubmed.ncbi.nlm.nih.gov/40463871/. DOI: 10.3389/fonc.2025.1559398.
[39]
JIN J J, DENG X J, LONG L, et al. The value of a radiomics model in predicting ovarian malignancy: a retrospective multi-center comparison with O-RADS and radiologists[J/OL]. Insights Imaging, 2025, 16(1): 163 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/40745233/. DOI: 10.1186/s13244-025-02047-w.
[40]
ADUSUMILLI P, RAVIKUMAR N, HALL G, et al. Radiomics in the evaluation of ovarian masses - a systematic review[J/OL]. Insights Imaging, 2023, 14(1): 165 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/37782375/. DOI: 10.1186/s13244-023-01500-y.
[41]
SONG X L, REN J L, ZHAO D, et al. Radiomics derived from dynamic contrast-enhanced MRI pharmacokinetic protocol features: the value of precision diagnosis ovarian neoplasms[J]. Eur Radiol, 2021, 31(1): 368-378. DOI: 10.1007/s00330-020-07112-0.
[42]
IBRAHIM A, PRIMAKOV S, BEUQUE M, et al. Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework[J]. Methods, 2021, 188: 20-29. DOI: 10.1016/j.ymeth.2020.05.022.
[43]
CHEN H M, GOMEZ C, HUANG C M, et al. Explainable medical imaging AI needs human-centered design: guidelines and evidence from a systematic review[J/OL]. NPJ Digit Med, 2022, 5(1): 156 [2025-12-01]. https://pubmed.ncbi.nlm.nih.gov/36261476/. DOI: 10.1038/s41746-022-00699-2.
[44]
WU M R, TANG Q Y, CAI S Q, et al. Accuracy and reproducibility of the o-rads MRI risk stratification system based on enhanced non-dce MRI in the assessment of adnexal masses[J/OL]. Eur J Radiol, 2023, 159: 110670 [2026-03-20]. https://pubmed.ncbi.nlm.nih.gov/36584564/. DOI: 10.1016/j.ejrad.2022.110670.
[45]
BOUROUROU R, NOUGARET S, ROCKALL A, et al. Apparent diffusion coefficient analysis of solid tissue helps distinguish borderline from invasive malignant adnexal masses rated O-RADS MRI 4[J]. Diagn Interv Imaging, 2024, 105(10): 386-394. DOI: 10.1016/j.diii.2024.05.004.

PREV Prediction of the primary lesion origin of hepatic hypervascular metastases based on MRI multi-lesion habitat radiomics
NEXT A comparative study on acquisition time and image quality of three different diffusion imaging sequences in the examination of acute cerebral infarction
  


LINK


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