Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Texture Analysis of Three-Dimensional MRI Images May Differentiate Borderline and Malignant Epithelial Ovarian Tumors

  • Rongping Ye (Department of Radiology, The First Affiliated Hospital of Fujian Medical University) ;
  • Shuping Weng (Department of Radiology, Fujian Maternity and Child Health Hospital) ;
  • Yueming Li (Department of Radiology, The First Affiliated Hospital of Fujian Medical University) ;
  • Chuan Yan (Department of Radiology, The First Affiliated Hospital of Fujian Medical University) ;
  • Jianwei Chen (Department of Radiology, The First Affiliated Hospital of Fujian Medical University) ;
  • Yuemin Zhu (Department of Radiology, The First Affiliated Hospital of Fujian Medical University) ;
  • Liting Wen (Department of Radiology, The First Affiliated Hospital of Fujian Medical University)
  • Received : 2020.02.15
  • Accepted : 2020.06.01
  • Published : 2021.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To explore the value of magnetic resonance imaging (MRI)-based whole tumor texture analysis in differentiating borderline epithelial ovarian tumors (BEOTs) from FIGO stage I/II malignant epithelial ovarian tumors (MEOTs). Materials and Methods: A total of 88 patients with histopathologically confirmed ovarian epithelial tumors after surgical resection, including 30 BEOT and 58 MEOT patients, were divided into a training group (n = 62) and a test group (n = 26). The clinical and conventional MRI features were retrospectively reviewed. The texture features of tumors, based on T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging, were extracted using MaZda software and the three top weighted texture features were selected by using the Random Forest algorithm. A non-texture logistic regression model in the training group was built to include those clinical and conventional MRI variables with p value < 0.10. Subsequently, a combined model integrating non-texture information and texture features was built for the training group. The model, evaluated using patients in the training group, was then applied to patients in the test group. Finally, receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of the models. Results: The combined model showed superior performance in categorizing BEOTs and MEOTs (sensitivity, 92.5%; specificity, 86.4%; accuracy, 90.3%; area under the ROC curve [AUC], 0.962) than the non-texture model (sensitivity, 78.3%; specificity, 84.6%; accuracy, 82.3%; AUC, 0.818). The AUCs were statistically different (p value = 0.038). In the test group, the AUCs, sensitivity, specificity, and accuracy were 0.840, 73.3%, 90.1%, and 80.8% when the non-texture model was used and 0.896, 75.0%, 94.0%, and 88.5% when the combined model was used. Conclusion: MRI-based texture features combined with clinical and conventional MRI features may assist in differentitating between BEOT and FIGO stage I/II MEOT patients.

Keywords

Acknowledgement

The authors thank the radiographers in our departments for their assistance in the experimental studies as well as data analysis.

References

  1. Lalwani N, Prasad SR, Vikram R, Shanbhogue AK, Huettner PC, Fasih N. Histologic, molecular, and cytogenetic features of ovarian cancers: implications for diagnosis and treatment. Radiographics 2011;31:625-646  https://doi.org/10.1148/rg.313105066
  2. Kurman RJ, Carcangiu ML, Herrington CS, Young RH. WHO classification of tumors of female reproductive organs, 4th ed. Lyon: International Agency for Research on Cancer, 2014 
  3. National Comprehensive Cancer Network. Ovarian cancer including fallopian tube cancer and primary peritoneal cancer (Version 1.2020). Philadelphia: National Comprehensive Cancer Network, 2020 
  4. Bentivegna E, Gouy S, Maulard A, Pautier P, Leary A, Colombo N, et al. Fertility-sparing surgery in epithelial ovarian cancer: a systematic review of oncological issues. Ann Oncol 2016;27:1994-2004  https://doi.org/10.1093/annonc/mdw311
  5. Vasconcelos I, de Sousa Mendes M. Conservative surgery in ovarian borderline tumours: a meta-analysis with emphasis on recurrence risk. Eur J Cancer 2015;51:620-631  https://doi.org/10.1016/j.ejca.2015.01.004
  6. Naqvi J, Nagaraju E, Ahmad S. MRI appearances of pure epithelial papillary serous borderline ovarian tumours. Clin Radiol 2015;70:424-432  https://doi.org/10.1016/j.crad.2014.11.005
  7. Sherman ME, Mink PJ, Curtis R, Cote TR, Brooks S, Hartge P, et al. Survival among women with borderline ovarian tumors and ovarian carcinoma: a population-based analysis. Cancer 2004;100:1045-1052  https://doi.org/10.1002/cncr.20080
  8. Bazot M, Haouy D, Darai E, Cortez A, Dechoux-Vodovar S, Thomassin-Naggara I. Is MRI a useful tool to distinguish between serous and mucinous borderline ovarian tumours? Clin Radiol 2013;68:e1-e8  https://doi.org/10.1016/j.crad.2012.08.021
  9. Bent CL, Sahdev A, Rockall AG, Singh N, Sohaib SA, Reznek RH. MRI appearances of borderline ovarian tumours. Clin Radiol 2009;64:430-438  https://doi.org/10.1016/j.crad.2008.09.011
  10. Takemori M, Nishimura R, Hasegawa K. Clinical evaluation of MRI in the diagnosis of borderline ovarian tumors. Acta Obstet Gynecol Scand 2002;81:157-161  https://doi.org/10.1034/j.1600-0412.2002.810212.x
  11. deSouza NM, O'Neill R, McIndoe GA, Dina R, Soutter WP. Borderline tumors of the ovary: CT and MRI features and tumor markers in differentiation from stage I disease. AJR Am J Roentgenol 2005;184:999-1003  https://doi.org/10.2214/ajr.184.3.01840999
  12. Thomassin-Naggara I, Darai E, Cuenod CA, Rouzier R, Callard P, Bazot M. Dynamic contrast-enhanced magnetic resonance imaging: a useful tool for characterizing ovarian epithelial tumors. J Magn Reson Imaging 2008;28:111-120  https://doi.org/10.1002/jmri.21377
  13. Zhao SH, Qiang JW, Zhang GF, Ma FH, Cai SQ, Li HM, et al. Diffusion-weighted MR imaging for differentiating borderline from malignant epithelial tumours of the ovary: pathological correlation. Eur Radiol 2014;24:2292-2299  https://doi.org/10.1007/s00330-014-3236-4
  14. Lu J, Pi S, Ma FH, Zhao SH, Li HM, Cai SL, et al. Value of normalized apparent diffusion coefficients in differentiating between borderline and malignant epithelial ovarian tumors. Eur J Radiol 2019;118:44-50  https://doi.org/10.1016/j.ejrad.2019.06.020
  15. Han X, Sun M, Wang M, Fan R, Chen D, Xie L, et al. The enhanced T2 star weighted angiography (ESWAN) value for differentiating borderline from malignant epithelial ovarian tumors. Eur J Radiol 2019;118:187-193  https://doi.org/10.1016/j.ejrad.2019.07.011
  16. Incoronato M, Aiello M, Infante T, Cavaliere C, Grimaldi AM, Mirabelli P, et al. Radiogenomic analysis of oncological data: a technical survey. Int J Mol Sci 2017;18:805 
  17. Ng F, Kozarski R, Ganeshan B, Goh V. Assessment of tumor heterogeneity by CT texture analysis: can the largest cross-sectional area be used as an alternative to whole tumor analysis? Eur J Radiol 2013;82:342-348  https://doi.org/10.1016/j.ejrad.2012.10.023
  18. Denewar FA, Takeuchi M, Urano M, Kamishima Y, Kawai T, Takahashi N, et al. Multiparametric MRI for differentiation of borderline ovarian tumors from stage I malignant epithelial ovarian tumors using multivariate logistic regression analysis. Eur J Radiol 2017;91:116-123  https://doi.org/10.1016/j.ejrad.2017.04.001
  19. Li YA, Qiang JW, Ma FH, Li HM, Zhao SH. MRI features and score for differentiating borderline from malignant epithelial ovarian tumors. Eur J Radiol 2018;98:136-142  https://doi.org/10.1016/j.ejrad.2017.11.014
  20. Thomassin-Naggara I, Aubert E, Rockall A, Jalaguier-Coudray A, Rouzier R, Darai E, et al. Adnexal masses: development and preliminary validation of an MR imaging scoring system. Radiology 2013;267:432-443  https://doi.org/10.1148/radiol.13121161
  21. Ma FH, Zhao SH, Qiang JW, Zhang GF, Wang XZ, Wang L. MRI appearances of mucinous borderline ovarian tumors: pathological correlation. J Magn Reson Imaging 2014;40:745-751  https://doi.org/10.1002/jmri.24408
  22. Szczypin'ski PM, Strzelecki M, Materka A, Klepaczko A. MaZda--a software package for image texture analysis. Comput Methods Programs Biomed 2009;94:66-76  https://doi.org/10.1016/j.cmpb.2008.08.005
  23. Strzelecki M, Szczypinski P, Materka A, Klepaczko A. A software tool for automatic classification and segmentation of 2D/3D medical images. Nucl Instrum Methods Phys Res A 2013;702:137-140  https://doi.org/10.1016/j.nima.2012.09.006
  24. Szczypinski PM, Strzelecki M, Materka A. MaZda-A software for texture analysis. 2007 international symposium on information technology convergence (ISITC 2007);2007 November 23-24; Jeonju, Korea 
  25. Tourassi GD, Frederick ED, Markey MK, Floyd CE Jr. Application of the mutual information criterion for feature selection in computer-aided diagnosis. Med Phys 2001;28:2394-2402  https://doi.org/10.1118/1.1418724
  26. Kurata Y, Kido A, Moribata Y, Kameyama K, Himoto Y, Minamiguchi S, et al. Diagnostic performance of MR imaging findings and quantitative values in the differentiation of seromucinous borderline tumour from endometriosis-related malignant ovarian tumour. Eur Radiol 2017;27:1695-1703  https://doi.org/10.1007/s00330-016-4533-x
  27. Iasonos A, Schrag D, Raj GV, Panageas KS. How to build and interpret a nomogram for cancer prognosis. J Clin Oncol 2008;26:1364-1370 https://doi.org/10.1200/JCO.2007.12.9791