MR image-based radiomics to differentiate type Ι and type ΙΙ epithelial ovarian cancers

Abstract

Objectives

Epithelial ovarian cancers (EOC) can be divided into type I and type II according to etiology and prognosis. Accurate subtype differentiation can substantially impact patient management. In this study, we aimed to construct an MR image–based radiomics model to differentiate between type I and type II EOC.

Methods

In this multicenter retrospective study, a total of 294 EOC patients from January 2010 to February 2019 were enrolled. Quantitative MR imaging features were extracted from the following axial sequences: T2WI FS, DWI, ADC, and CE-T1WI. A combined model was constructed based on the combination of these four MR sequences. The diagnostic performance was evaluated by ROC-AUC. In addition, an occlusion test was carried out to identify the most critical region for EOC differentiation.

Results

The combined radiomics model exhibited superior diagnostic capability over all four single-parametric radiomics models, both in internal and external validation cohorts (AUC of 0.806 and 0.847, respectively). The occlusion test revealed that the most critical region for differential diagnosis was the border zone between the solid and cystic components, or the less compact areas of solid component on direct visual inspection.

Conclusions

MR image–based radiomics modeling can differentiate between type I and type II EOC and identify the most critical region for differential diagnosis.

Key Points

• Combined radiomics models exhibited superior diagnostic capability over all four single-parametric radiomics models, both in internal and external validation cohorts (AUC of 0.834 and 0.847, respectively).

• The occlusion test revealed that the most crucial region for differentiating type Ι and type ΙΙ EOC was the border zone between the solid and cystic components, or the less compact areas of solid component on direct visual inspection on T2WI FS.

• The light-combined model (constructed by T2WI FS, DWI, and ADC sequences) can be used for patients who are not suitable for contrast agent use.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3

Abbreviations

ADC:

Apparent diffusion coefficient

CE-T1WI:

Contrast-enhanced T1-weighted imaging

DWI:

Diffusion-weighted imaging

EOC:

Epithelial ovarian cancer

MP:

Multi-parameter

T2WI FS:

Fat-suppressed T2-weighted imaging

References

  1. 1.

    Soong TR, Kolin DL, Teschan NJ, Crum CP (2018) Back to the future? The fallopian tube, precursor escape and a dualistic model of high-grade serous carcinogenesis. Cancers (Basel) 10. https://doi.org/10.3390/cancers10120468

  2. 2.

    Lheureux S, Gourley C, Vergote I, Oza AM (2019) Epithelial ovarian cancer. Lancet 393:1240–1253. https://doi.org/10.1016/S0140-6736(18)32552-2

    Article  PubMed  Google Scholar 

  3. 3.

    Kim A, Ueda Y, Naka T, Enomoto T (2012) Therapeutic strategies in epithelial ovarian cancer. J Exp Clin Cancer Res 31:14. https://doi.org/10.1186/1756-9966-31-14

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  4. 4.

    Terraneo N, Jacob F, Dubrovska A, Grünberg J (2020) Novel therapeutic strategies for ovarian cancer stem cells. Front Oncol 10. https://doi.org/10.3389/fonc.2020.00319

  5. 5.

    Kurman RJ, Shih I-M (2008) Pathogenesis of ovarian cancer: lessons from morphology and molecular biology and their clinical implications. Int J Gynecol Pathol 27:151–160. https://doi.org/10.1097/PGP.0b013e318161e4f5

    Article  PubMed  PubMed Central  Google Scholar 

  6. 6.

    Kurman RJ, Carcangiu ML, Herrington CS, Young RH (2014) WHO classification of tumours of female reproductive organs. International Agency for Research on Cancer

  7. 7.

    Lalwani N, Prasad SR, Vikram R, Shanbhogue AK, Huettner PC, Fasih N (2011) Histologic, molecular, and cytogenetic features of ovarian cancers: implications for diagnosis and treatment. Radiographics 31:625–646. https://doi.org/10.1148/rg.313105066

  8. 8.

    Despierre E, Yesilyurt BT, Lambrechts S et al (2014) Epithelial ovarian cancer: rationale for changing the one-fits-all standard treatment regimen to subtype-specific treatment. Int J Gynecol Cancer 24:468–477. https://doi.org/10.1097/IGC.0000000000000089

    Article  PubMed  Google Scholar 

  9. 9.

    Kurman RJ, Shih I-M (2010) The origin and pathogenesis of epithelial ovarian cancer: a proposed unifying theory. Am J Surg Pathol 34:433–443. https://doi.org/10.1097/PAS.0b013e3181cf3d79

    Article  PubMed  PubMed Central  Google Scholar 

  10. 10.

    Oh JW, Rha SE, Oh SN, Parka MY, Byuna JY, Lee A (2015) Diffusion-weighted MRI of epithelial ovarian cancers: correlation of apparent diffusion coefficient values with histologic grade and surgical stage. Eur J Radiol 84:590–595. https://doi.org/10.1016/j.ejrad.2015.01.005

  11. 11.

    Higano S, Yun X, Kumabe T et al (2006) Malignant astrocytic tumors: clinical importance of apparent diffusion coefficient in prediction of grade and prognosis. Radiology 241:839–846. https://doi.org/10.1148/radiol.2413051276

    Article  PubMed  Google Scholar 

  12. 12.

    Kovač JD, Terzić M, Mirković M, Banko B, Đikić-Rom A, Maksimović R (2016) Endometrioid adenocarcinoma of the ovary: MRI findings with emphasis on diffusion-weighted imaging for the differentiation of ovarian tumors. Acta Radiol 57:758–766. https://doi.org/10.1177/0284185115599805

  13. 13.

    Wang F, Wang Y, Zhou Y et al (2017) Comparison between types I and II epithelial ovarian cancer using histogram analysis of monoexponential, biexponential, and stretched-exponential diffusion models: Comparison of Types I and II Ovarian Cancer. J Magn Reson Imaging 46:1797–1809. https://doi.org/10.1002/jmri.25722

    Article  PubMed  Google Scholar 

  14. 14.

    Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: Extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446. https://doi.org/10.1016/j.ejca.2011.11.036

    Article  PubMed  PubMed Central  Google Scholar 

  15. 15.

    Kumar V, Gu Y, Basu S et al (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234–1248. https://doi.org/10.1016/j.mri.2012.06.010

    Article  PubMed  PubMed Central  Google Scholar 

  16. 16.

    Gillies RJ, Kinahan PE, Hricak H (2015) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169

    Article  PubMed  PubMed Central  Google Scholar 

  17. 17.

    Meng X, Xia W, Xie P et al (2018) Preoperative radiomic signature based on multiparametric magnetic resonance imaging for noninvasive evaluation of biological characteristics in rectal cancer. Eur Radiol. https://doi.org/10.1007/s00330-018-5763-x

  18. 18.

    Zhang Q, Xiao Y, Suo J et al (2017) Sonoelastomics for breast tumor classification: a radiomics approach with clustering-based feature selection on sonoelastography. Ultrasound Med Biol 43:1058–1069. https://doi.org/10.1016/j.ultrasmedbio.2016.12.016

    Article  PubMed  Google Scholar 

  19. 19.

    Huang Y, Liang C, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164. https://doi.org/10.1200/JCO.2015.65.9128

    Article  PubMed  Google Scholar 

  20. 20.

    Wang X, Zhao X, Li Q et al (2019) Can peritumoral radiomics increase the efficiency of the prediction for lymph node metastasis in clinical stage T1 lung adenocarcinoma on CT? Eur Radiol. https://doi.org/10.1007/s00330-019-06084-0

  21. 21.

    Huang Y, Liu Z, He L et al (2016) Radiomics signature: a potential biomarker for the prediction of disease-free survival in early-stage (I or II) non—small cell lung cancer. Radiology 281:947–957

    Article  Google Scholar 

  22. 22.

    Song J, Shi J, Dong D et al (2018) A New Approach to Predict Progression-free Survival in Stage IV EGFR-mutant NSCLC Patients with EGFR-TKI Therapy. Clin Cancer Res 24:3583–3592. https://doi.org/10.1158/1078-0432.CCR-17-2507

    Article  PubMed  CAS  Google Scholar 

  23. 23.

    Li H, Zhu Y, Burnside ES et al (2016) MR imaging radiomics signatures for predicting the risk of breast cancer recurrence as given by research versions of MammaPrint, Oncotype DX, and PAM50 gene assays. Radiology 281:382–391. https://doi.org/10.1148/radiol.2016152110

    Article  PubMed  PubMed Central  Google Scholar 

  24. 24.

    Nie K, Shi L, Chen Q et al (2016) Rectal cancer: assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI. Clin Cancer Res 22:5256–5264. https://doi.org/10.1158/1078-0432.CCR-15-2997

    Article  PubMed  Google Scholar 

  25. 25.

    Nerad E, Lambregts DMJ, Kersten ELJ et al (2017) MRI for local staging of colon cancer: can mri become the optimal staging modality for patients with colon cancer? Dis Colon Rectum 60:385–392. https://doi.org/10.1097/DCR.0000000000000794

    Article  PubMed  Google Scholar 

  26. 26.

    Zhang H, Mao Y, Chen X et al (2019) Magnetic resonance imaging radiomics in categorizing ovarian masses and predicting clinical outcome: a preliminary study. Eur Radiol. https://doi.org/10.1007/s00330-019-06124-9

  27. 27.

    Hauptmann S, Friedrich K, Redline R, Avril S (2017) Ovarian borderline tumors in the 2014 WHO classification: evolving concepts and diagnostic criteria. Virchows Arch 470:125–142. https://doi.org/10.1007/s00428-016-2040-8

    Article  PubMed  CAS  Google Scholar 

  28. 28.

    Park MY, Hastie T (2007) L 1 -regularization path algorithm for generalized linear models. J R Stat Soc Series B Stat Methodology 69:659–677. https://doi.org/10.1111/j.1467-9868.2007.00607.x

    Article  Google Scholar 

  29. 29.

    Li Y, Jian J, Pickhardt PJ, et al MRI-based machine learning for differentiating borderline from malignant epithelial ovarian tumors: a multicenter study. J Magn Reson Imaging n/a: https://doi.org/10.1002/jmri.27084

  30. 30.

    Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision – ECCV 2014. Springer International Publishing, Cham, pp 818–833

    Google Scholar 

  31. 31.

    Lee CS, Baughman DM, Lee AY (2017) Deep learning is effective for classifying normal versus age-related macular degeneration OCT images. Ophthalmol Retina 1:322–327. https://doi.org/10.1016/j.oret.2016.12.009

    Article  PubMed  PubMed Central  Google Scholar 

  32. 32.

    Kermany DS, Goldbaum M, Cai W et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172:1122–1131.e9. https://doi.org/10.1016/j.cell.2018.02.010

    Article  PubMed  CAS  Google Scholar 

  33. 33.

    Muller P, Coates PJ, Nenutil R et al (2019) Tomm34 is commonly expressed in epithelial ovarian cancer and associates with tumour type and high FIGO stage. J Ovarian Res 12. https://doi.org/10.1186/s13048-019-0498-0

Download references

Funding

This study has received funding from the National Natural Science Foundation of China (No. 81871439, No. 81501439, No. 81571772, No. 81471628); Key R&D Program of Jiangsu (No. BE2017671); Shanghai Municipal Commission (No. 20184Y0049); Foundation of Jinshan Hospital, Shanghai Medical College, Fudan University (No. 2018-JSYYQH-03); and Science and Technology Commission Shanghai Municipality (No. 19411972000); and Chinese Academy of Sciences-Iranian Vice Presidency for Science and Technology Silk Road Science Fund (No. GJHZ1857).

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Xin Gao or Jinwei Qiang.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jinwei Qiang.

Conflict of interest

Dr. Pickhardt is an advisor to Bracco and a shareholder in SHINE and Elucent. All remaining authors have declared no conflicts of interest.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical Approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• multicenter study

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

ESM 1

(DOCX 29 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Jian, J., Li, Y., Pickhardt, P.J. et al. MR image-based radiomics to differentiate type Ι and type ΙΙ epithelial ovarian cancers. Eur Radiol (2020). https://doi.org/10.1007/s00330-020-07091-2

Download citation

Keywords

  • Diagnosis
  • Epithelial ovarian cancer
  • Magnetic resonance imaging
  • Machine learning
  • radiomics