Advertisement

European Radiology

, Volume 29, Issue 7, pp 3358–3371 | Cite as

Magnetic resonance imaging radiomics in categorizing ovarian masses and predicting clinical outcome: a preliminary study

  • He Zhang
  • Yunfei Mao
  • Xiaojun Chen
  • Guoqing Wu
  • Xuefen Liu
  • Peng Zhang
  • Yu Bai
  • Pengcong Lu
  • Weigen Yao
  • Yuanyuan Wang
  • Jinhua YuEmail author
  • Guofu ZhangEmail author
Imaging Informatics and Artificial Intelligence

Abstract

Purpose

To evaluate the ability of MRI radiomics to categorize ovarian masses and to determine the association between MRI radiomics and survival among ovarian epithelial cancer (OEC) patients.

Method

A total of 286 patients with pathologically proven adnexal tumor were retrospectively included in this study. We evaluated diagnostic performance of the signatures derived from MRI radiomics in differentiating (1) between benign adnexal tumors and malignancies and (2) between type I and type II OEC. The least absolute shrinkage and selection operator method was used for radiomics feature selection. Risk scores were calculated from the Lasso model and were used for survival analysis.

Result

For the classification between benign and malignant masses, the MRI radiomics model achieved a high accuracy of 0.90 in the leave-one-out (LOO) cross-validation cohort and an accuracy of 0.87 in the independent validation cohort. For the classification between type I and type II subtypes, our method made a satisfactory classification in the LOO cross-validation cohort (accuracy = 0.93) and in the independent validation cohort (accuracy = 0.84). Low-high-high short-run high gray-level emphasis and low-low-high variance from coronal T2-weighted imaging (T2WI) and eccentricity from axial T1-weighted imaging (T1WI) images had the best performance in two classification tasks. The patients with higher risk scores were more likely to have poor prognosis (hazard ratio = 4.1694, p = 0.001).

Conclusion

Our results suggest radiomics features extracted from MRI are highly correlated with OEC classification and prognosis of patients. MRI radiomics can provide survival estimations with high accuracy.

Key Points

• The MRI radiomics model could achieve a higher accuracy in discriminating benign ovarian diseases from malignancies.

• Low-high-high short-run high gray-level emphasis, low-low-high variance from coronal T2WI, and eccentricity from axial T1WI had the best performance outcomes in various classification tasks.

• The ovarian cancer patients with high-risk scores had poor prognosis.

Keywords

Ovarian epithelial cancer Magnetic resonance imaging Computer-assisted diagnosis Radiomics 

Abbreviations

ADC

Apparent diffusion coefficient

DWI

Diffusion-weighted magnetic resonance imaging

FIGO

International Federation of Gynecology and Obstetrics

ISR

Iterative sparse representation

OEC

Ovarian epithelial cancer

PACS

Picture archiving and communication system

SRC

System sparse representation coefficient

SVM

Support vector machine

Notes

Funding

This work is financially supported by the Shanghai Emerging Advanced Technology Joint Research Project (SHDC12014130).

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Guofu Zhang.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

Statistician Yu Bai kindly provided all statistical work for this study.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Observational

• Performed at one institution

Supplementary material

330_2019_6124_MOESM1_ESM.docx (65 kb)
ESM 1 (DOCX 65 kb)

References

  1. 1.
    Chen WZR, Baade PD, Zhang S et al (2016) Cancer statistics in China, 2015. CA Cancer J Clin 66:115–132CrossRefGoogle Scholar
  2. 2.
    Cannistra SA (2004) Cancer of the ovary. N Engl J Med 351:2519–2529CrossRefGoogle Scholar
  3. 3.
    Bowtell DD, Böhm S, Ahmed AA et al (2015) Rethinking ovarian cancer II: reducing mortality from high-grade serous ovarian cancer. Nat Rev Cancer 15:668–679CrossRefGoogle Scholar
  4. 4.
    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 31:625–646CrossRefGoogle Scholar
  5. 5.
    Menon U, Griffin M, Gentry-Maharaj A (2014) Ovarian cancer screening—current status, future directions. Gynecol Oncol 132:490–495CrossRefGoogle Scholar
  6. 6.
    Medeiros LR, Freitas LB, Rosa DD et al (2011) Accuracy of magnetic resonance imaging in ovarian tumor: a systematic quantitative review. Am J Obstet Gynecol 204:67–e1CrossRefGoogle Scholar
  7. 7.
    Sala E, Wakely S, Senior E, Lomas D (2007) MRI of malignant neoplasms of the uterine corpus and cervix. AJR Am J Roentgenol 188:1577–1587CrossRefGoogle Scholar
  8. 8.
    Li W, Chu C, Cui Y, Zhang P, Zhu M (2012) Diffusion-weighted MRI: a useful technique to discriminate benign versus malignant ovarian surface epithelial tumors with solid and cystic components. Abdom Imaging 37:897–903CrossRefGoogle Scholar
  9. 9.
    Mitchell CL, O'Connor JPB, Jackson A et al (2010) Identification of early predictive imaging biomarkers and their relationship to serological angiogenic markers in patients with ovarian cancer with residual disease following cytotoxic therapy. Ann Oncol 21:1982–1989CrossRefGoogle Scholar
  10. 10.
    Zhang H, Zhang G-F, He Z-Y, Li Z-Y, Zhang G-X (2014) Prospective evaluation of 3T MRI findings for primary adnexal lesions and comparison with the final histological diagnosis. Arch Gynecol Obstet 289:357–364CrossRefGoogle Scholar
  11. 11.
    Thomassin-Naggara I, Balvay D, Aubert E et al (2012) Quantitative dynamic contrast-enhanced MR imaging analysis of complex adnexal masses: a preliminary study. Eur Radiol 22:738–745CrossRefGoogle Scholar
  12. 12.
    Stein EB, Wasnik AP, Sciallis AP, Kamaya A, Maturen KE (2017) MR imaging–pathologic correlation in ovarian cancer. Magn Reson Imaging Clin N Am 25:545–562CrossRefGoogle Scholar
  13. 13.
    Alcázar JL, Utrilla-Layna J, Mínguez JÁ, Jurado M (2013) Clinical and ultrasound features of type I and type II epithelial ovarian cancer. Int J Gynecol Cancer 23:680–684CrossRefGoogle Scholar
  14. 14.
    Prahm KP, Karlsen MA, Høgdall E et al (2015) The prognostic value of dividing epithelial ovarian cancer into type I and type II tumors based on pathologic characteristics. Gynecol Oncol 136:205–211CrossRefGoogle Scholar
  15. 15.
    Tang H, Liu Y, Wang X et al (2018) Clear cell carcinoma of the ovary: clinicopathologic features and outcomes in a Chinese cohort. Medicine (Baltimore) 97:e10881Google Scholar
  16. 16.
    Lee JY, Kim S, Kim YT et al (2018) Changes in ovarian cancer survival during the 20 years before the era of targeted therapy. BMC Cancer 18:601Google Scholar
  17. 17.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefGoogle Scholar
  18. 18.
    Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749CrossRefGoogle Scholar
  19. 19.
    Anastasi E, Gigli S, Ballesio L, Angeloni A, Manganaro L (2018) The complementary role of imaging and tumor biomarkers in gynecological cancers: an update of the literature. Asian Pac J Cancer Prev 19:309–317Google Scholar
  20. 20.
    Rajkotia K, Veeramani M, Macura KJ (2006) Magnetic resonance imaging of adnexal masses. Top Magn Reson Imaging 17:379–397CrossRefGoogle Scholar
  21. 21.
    Thomassin-Naggara I, Daraï E, Cuenod CA, Rouzier R, Callard P, Bazot M (2008) Dynamic contrast-enhanced magnetic resonance imaging: a useful tool for characterizing ovarian epithelial tumors. J Magn Reson Imaging 28:111–120CrossRefGoogle Scholar
  22. 22.
    Ortiz-Ramón R, Larroza A, Ruiz-España S, Arana E, Moratal D (2018) Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study. Eur Radiol 28:4514–4523CrossRefGoogle Scholar
  23. 23.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006Google Scholar
  24. 24.
    Yu J, Shi Z, Lian Y et al (2017) Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol 27:3509–3522CrossRefGoogle Scholar
  25. 25.
    Wu G, Chen Y, Wang Y et al (2018) Sparse representation-based radiomics for the diagnosis of brain tumors. IEEE Trans Med Imaging 37:893–905CrossRefGoogle Scholar
  26. 26.
    Li H, Zhu Y, Burnside ES et al (2016) Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set. NPJ Breast Cancer 2:16012Google Scholar
  27. 27.
    Kazerooni AF, Malek M, Haghighatkhah H et al (2017) Semiquantitative dynamic contrast-enhanced MRI for accurate classification of complex adnexal masses. J Magn Reson Imaging.  https://doi.org/10.1002/jmri.25359
  28. 28.
    Meng Y, Zhang Y, Dong D et al (2018) Novel radiomic signature as a prognostic biomarker for locally advanced rectal cancer. J Magn Reson Imaging 48:605–614Google Scholar
  29. 29.
    Zhu X, Dong D, Chen Z et al (2018) Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol 28:2772–2778Google Scholar
  30. 30.
    Ferreira Junior JR, Koenigkam-Santos M, Cipriano FEG, Fabro AT, Azevedo-Marques PM (2018) Radiomics-based features for pattern recognition of lung cancer histopathology and metastases. Comput Methods Programs Biomed 159:23–30Google Scholar
  31. 31.
    Lindgren A, Anttila M, Rautiainen S et al (2017) Primary and metastatic ovarian cancer: characterization by 3.0T diffusion-weighted MRI. Eur Radiol 27:4002–4012CrossRefGoogle Scholar
  32. 32.
    Wang F, Wang Y, Zhou Y (2017) Comparison between types I and II epithelial ovarian cancer using histogram analysis of monoexponential, biexponential, and stretched-exponential diffusion models. J Magn Reson Imaging 46:1797–1809Google Scholar
  33. 33.
    Rizzo S, Botta F, Raimondi S et al (2018) Radiomics of high-grade serous ovarian cancer: association between quantitative CT features, residual tumour and disease progression within 12 months. Eur Radiol 28:4849–4859CrossRefGoogle Scholar
  34. 34.
    Qiu Y, Tan M, McMeekin S et al (2016) Early prediction of clinical benefit of treating ovarian cancer using quantitative CT image feature analysis. Acta Radiol 57:1149–1155CrossRefGoogle Scholar
  35. 35.
    Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJ (2015) Machine learning methods for quantitative radiomic biomarkers. Sci Rep 5:13087Google Scholar
  36. 36.
    Liu Y, Zhang Y, Cheng R et al (2019) Radiomics analysis of apparent diffusion coefficient in cervical cancer: a preliminary study on histological grade evaluation. J Magn Reson Imaging 49:280–290Google Scholar
  37. 37.
    Ueno Y, Forghani B, Forghani R et al (2017) Endometrial carcinoma: MR imaging–based texture model for preoperative risk stratification—a preliminary analysis. Radiology 284:748–757CrossRefGoogle Scholar
  38. 38.
    Marth C, Reimer D, Zeimet AG (2017) Front-line therapy of advanced epithelial ovarian cancer: standard treatment. Ann Oncol 28:viii36–viii39CrossRefGoogle Scholar
  39. 39.
    Nakamura K, Joja I, Nagasaka T et al (2012) The mean apparent diffusion coefficient value (ADCmean) on primary cervical cancer is a predictive marker for disease recurrence. Gynecol Oncol 127:478–483CrossRefGoogle Scholar
  40. 40.
    Schob S, Meyer HJ, Pazaitis N et al (2017) ADC histogram analysis of cervical cancer aids detecting lymphatic metastases—a preliminary study. Mol Imaging Biol 19:953–962CrossRefGoogle Scholar
  41. 41.
    Zhang B, Tian J, Dong D et al (2017) Radiomics features of multiparametric MRI as novel prognostic factors in advanced nasopharyngeal carcinoma. Clin Cancer Res 23:4259–4269CrossRefGoogle Scholar
  42. 42.
    Vasquez MM, Hu C, Roe DJ, Chen Z, Halonen M, Guerra S (2016) Least absolute shrinkage and selection operator type methods for the identification of serum biomarkers of overweight and obesity: simulation and application. BMC Med Res Methodol 16:154CrossRefGoogle Scholar
  43. 43.
    Huang Y, Liang CH, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. Jpn J Clin Oncol 34:2157–2164Google Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  • He Zhang
    • 1
  • Yunfei Mao
    • 2
  • Xiaojun Chen
    • 3
  • Guoqing Wu
    • 2
  • Xuefen Liu
    • 1
  • Peng Zhang
    • 1
  • Yu Bai
    • 4
  • Pengcong Lu
    • 5
  • Weigen Yao
    • 5
  • Yuanyuan Wang
    • 2
  • Jinhua Yu
    • 2
    • 6
    Email author
  • Guofu Zhang
    • 1
    Email author
  1. 1.Department of Radiology, Obstetrics and Gynecology HospitalFudan UniversityShanghaiPeople’s Republic of China
  2. 2.Department of Electronic EngineeringFudan UniversityShanghaiPeople’s Republic of China
  3. 3.Department of Gynecology, Obstetrics and Gynecology HospitalFudan UniversityShanghaiPeople’s Republic of China
  4. 4.Center for Child and Family PolicyDuke UniversityDurhamUSA
  5. 5.Department of RadiologyYuyao People’s HospitalNingboPeople’s Republic of China
  6. 6.Key Laboratory of Medical Imaging Computing and Computer Assisted InterventionShanghaiPeople’s Republic of China

Personalised recommendations