Advertisement

Abdominal Radiology

, Volume 44, Issue 1, pp 201–208 | Cite as

Computed tomography-based texture analysis of bladder cancer: differentiating urothelial carcinoma from micropapillary carcinoma

  • Ting-wei FanEmail author
  • Harshawn Malhi
  • Bino Varghese
  • Steve Cen
  • Darryl Hwang
  • Manju Aron
  • Nieroshan Rajarubendra
  • Mihir Desai
  • Vinay Duddalwar
Article

Abstract

Purpose

The purpose of the study is to determine the feasibility of using computed tomography-based texture analysis (CTTA) in differentiating between urothelial carcinomas (UC) of the bladder from micropapillary carcinomas (MPC) of the bladder.

Methods

Regions of interests (ROIs) of computerized tomography (CT) images of 33 MPCs and 33 UCs were manually segmented and saved. Custom MATLAB code was used to extract voxel information corresponding to the ROI. The segmented tumors were input to a pre-existing radiomics platform with a CTTA panel. A total of 58 texture metrics were extracted using four different texture extraction techniques and statistically analyzed using a Wilcoxon rank-sum test to determine the differences between UCs and MPCs.

Results

Of the 58 texture metrics extracted using the gray level co-occurrence matrix (GLCM) and gray level difference matrix (GLDM), 28 texture metrics were statistically significant (p < 0.05) for differences in tumor textures and 27 texture metrics were statistically significant (p < 0.05) for peritumoral fat textures. The remaining nine metrics extracted using histogram and fast Fourier transform analyses did not show significant differences between the textures of the tumors and their peritumoral fat.

Conclusions

CTTA shows that MPC have a more heterogeneous texture compared to UC. As visual discrimination of MPC from UC from clinical CT scans are difficult, results from this study suggest that tumor heterogeneity extracted using GLCM and GLDM may be a good imaging aid in segregating MPC from UC. This tool can aid clinicians in further sub-classifying bladder cancers on routine imaging, a process which has potential to alter treatment and patient care.

Keywords

Micropapillary carcinoma Urothelial carcinoma Texture analysis Radiomics Bladder cancer 

Notes

Acknowledgments

This research was supported by the Radiological Society of North America Medical Student Grant. We would like to acknowledge Fujifilm and all the personnel at the radiomics laboratory at the University of Southern California for their help with this project.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This study has been approved by the appropriate institutional review boards and have been performed in accordance with the ethical standards as laid down in the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards.

Funding

RSNA Medical Student Grant (No. RMS172).

References

  1. 1.
    American Cancer Society (2018) Cancer facts and figures. Atlanta: American Cancer SocietyGoogle Scholar
  2. 2.
    Wong MCS, Fung FDH, Leung C, et al. (2018) The global epidemiology of bladder cancer: a joinpoint regression analysis of its incidence and mortality trends and projection. Sci Rep 8:1129Google Scholar
  3. 3.
    Nielsen ME, Smith AB, Meyer AM, et al. (2013) Trends in stage-specific incidence rates for urothelial carcinoma of the bladder in the United States: 1988 to 2006. Cancer 120:86–95Google Scholar
  4. 4.
    Sui W, Matulay JT, James MB, et al. (2016) Micropapillary bladder cancer: insights from the National Cancer Database. Bladder Cancer 2(4):415–423.  https://doi.org/10.3233/blc-160066 Google Scholar
  5. 5.
    Kwon GY, Ro JY (2011) Micropapillary variant of urothelial carcinoma. Adv Urol 2011:217153.  https://doi.org/10.1155/2011/217153 Google Scholar
  6. 6.
    Gofrit ON, Yutkin V, Shapiro A, et al. (2016) The response of variant histology bladder cancer to intravesical immunotherapy compared to conventional cancer. Front Oncol 6:43.  https://doi.org/10.3389/fonc.2016.00043 Google Scholar
  7. 7.
    Fairey AS, Daneshmand S, Wang L, et al. (2014) Impact of micropapillary urothelial carcinoma variant histology on survival after radical cystectomy. Urol Oncol 32(2):110–116.  https://doi.org/10.1016/j.urolonc.2012.04.020 Google Scholar
  8. 8.
    Willis DL, Flaig TW, Hansel DE, et al. (2014) Micropapillary bladder cancer: current treatment patterns and review of the literature. Urol Oncol 32(6):826–832Google Scholar
  9. 9.
    Amin MB (2009) Histological variants of urothelial carcinoma: diagnostic, therapeutic and prognostic implications. Mod Pathol 22:S96–S118Google Scholar
  10. 10.
    Zhanx X, Xu X, et al. (2017) Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging. J Magn Reson Imaging.  https://doi.org/10.1002/jmri.25669 Google Scholar
  11. 11.
    Chen F, Gulati M, Hwang D, et al. (2017) Voxel-based whole-lesion enhancement parameters: a study of its clinical value in differentiating clear cell renal cell carcinoma from renal oncocytoma. Abdom Radiol 42(2):552–560.  https://doi.org/10.1007/s00261-016-0891-8 Google Scholar
  12. 12.
    Pena E, Ojiaku M, et al. (2017) Can CT and MR shape and textural features differentiate benign versus malignant pleural lesions? Acad Radiol.  https://doi.org/10.1016/j.acra.2017.03.006 Google Scholar
  13. 13.
    Li Z, Wang Y, et al. (2017) Deep learning based radiomics (DLR) and its usage in noninvasive IDH1 prediction for low grade glioma. Sci Rep 7(1):5467.  https://doi.org/10.1038/s41598-017-05848-2 Google Scholar
  14. 14.
    Wang J, Wu CJ, et al. (2017) Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer. Eur Radiol.  https://doi.org/10.1007/s00330-017-4800-5 Google Scholar
  15. 15.
    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(2):382–391.  https://doi.org/10.1148/radiol.2016152110 Google Scholar
  16. 16.
    Varghese B, Chen F, Hwang D, Cen S, Desai B, Gill I, Duddalwar V. Differentiation of predominantly solid, enhancing lipid-poor renal cell masses using contrast-enhanced computed tomography: evaluating the role of texture in tumor sub-typing. American Journal of Roentgenology (In press)Google Scholar
  17. 17.
    Varghese B, Hwang D, Cen S, et al. (2017) Fast fourier transform based analysis of renal masses on contrast-enhanced computed tomography images for grading of tumor. SPIE Proc. doi 10(1117/12):2256871Google Scholar
  18. 18.
    Huhdanpaa H, Chen F, Hwang D, et al. (2015) CT prediction of the fuhrman grade of clear cell renal cell carcinoma (RCC): towards the development of a quantitative metric. Abdominal Imaging 40(8):3168–3174.  https://doi.org/10.1007/s00261-015-0531-8 Google Scholar
  19. 19.
    Aerts HJWL, Grossmann P, Tan Y, et al. (2016) Defining a radiomic response phenotype: a pilot study using targeted therapy in NSCLC. Sci Rep 6:33860.  https://doi.org/10.1038/srep33860 Google Scholar
  20. 20.
    Hanania A, Bantis L, Feng Z, et al. (2016) Quantitative imaging to evaluate malignant potential of IPMNs. Oncotarget 7(52):85776–85784Google Scholar
  21. 21.
    Hodgdon T, McInnes MD, et al. (2015) Can quantitative CT texture analysis be used to differentiate fat-poor renal angiomyolipoma from renal cell carcinoma on unenhanced CT images? Radiology 276(3):787–796Google Scholar
  22. 22.
    Wibmer A, Hricak H, Gondo T, et al. (2015) Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol 25(10):2840–2850Google Scholar
  23. 23.
    Xu X, Liu Y, Zhang X, et al. (2017) Preoperative prediction of muscular invasiveness of bladder cancer with radiomic features on conventional MRI and its high-order derivative maps. Abdom Radiol (NY) 42(7):1896–1905Google Scholar
  24. 24.
    Zhang GM, Sun H, Shi B, Jin ZY, Xue HD (2017) Quantitative CT texture analysis for evaluating histologic grade of urothelial carcinoma. Abdom Radiol (NY) 42(2):561–568Google Scholar
  25. 25.
    Choi HK, Jarkrans T, Bengtsson E, et al. (1997) Image analysis based grading of bladder carcinoma. Comparison of object, texture and graph based methods and their reproducibility. Anal Cell Pathol 15(1):1–18Google Scholar
  26. 26.
    Mammen S, Krishna S, Quon M, et al. (2018) Diagnostic accuracy of qualitative and quantitative computed tomography analysis for diagnosis of pathological grade and stage in upper tract urothelial cell carcinoma. J Comput Assist Tomogr 42(2):204–210Google Scholar
  27. 27.
    Warrick JI (2017) Clinical significance of histologic variants of bladder cancer. J Natl Compr Cancer Netw 15(10):1268–1274Google Scholar
  28. 28.
    Li Z, Liao H, Tan Z, et al. (2017) Micropaillary bladder cancer: a clinico-pathological characterization and treatment analysis. Clin Transl Oncol 19(10):1217–1224Google Scholar
  29. 29.
    Samaratunga H, Khoo K (2004) Micropapillary variant of urothelial carcinoma of the urinary bladder; a clinicopathological and immunohistochemical study. Histopathology 45:55–64Google Scholar
  30. 30.
    Chatterjee D, Das A, Radotra BD (2015) Invasive micropapillary carcinoma of urinary bladder: a clinicopathological study. Indian J Pathol Microbiol 58(1):2–6.  https://doi.org/10.4103/0377-4929.15115 Google Scholar
  31. 31.
    Bertz S, Wach S, Taubert H, et al. (2016) Micropapillary morphology is an indicator of poor prognosis in patients with urothelial carcinoma treated with transurethral resection and radiochemotherapy. Virchows Arch 469(3):339–344.  https://doi.org/10.1007/s00428-016-1986-x Google Scholar
  32. 32.
    Fernandez MI, Williams SB, Willis DL, et al. (2017) Clinical risk stratification in patients with surgically resectable micropapillary bladder cancer. BJU Int 119(5):684–691.  https://doi.org/10.1111/bju.13689 Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Keck School of Medicine of USCLos AngelesUSA

Personalised recommendations