DOI QR코드

DOI QR Code

CT-Based Radiomics Signature for Preoperative Prediction of Coagulative Necrosis in Clear Cell Renal Cell Carcinoma

  • Kai Xu (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Lin Liu (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Wenhui Li (College of Computer Science and Technology, Jilin University) ;
  • Xiaoqing Sun (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Tongxu Shen (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Feng Pan (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Yuqing Jiang (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Yan Guo (Life Sciences, GE Healthcare) ;
  • Lei Ding (Department of Radiology, China-Japan Union Hospital of Jilin University) ;
  • Mengchao Zhang (Department of Radiology, China-Japan Union Hospital of Jilin University)
  • Received : 2019.08.31
  • Accepted : 2020.01.27
  • Published : 2020.06.01

Abstract

Objective: The presence of coagulative necrosis (CN) in clear cell renal cell carcinoma (ccRCC) indicates a poor prognosis, while the absence of CN indicates a good prognosis. The purpose of this study was to build and validate a radiomics signature based on preoperative CT imaging data to estimate CN status in ccRCC. Materials and Methods: Altogether, 105 patients with pathologically confirmed ccRCC were retrospectively enrolled in this study and then divided into training (n = 72) and validation (n = 33) sets. Thereafter, 385 radiomics features were extracted from the three-dimensional volumes of interest of each tumor, and 10 traditional features were assessed by two experienced radiologists using triple-phase CT-enhanced images. A multivariate logistic regression algorithm was used to build the radiomics score and traditional predictors in the training set, and their performance was assessed and then tested in the validation set. The radiomics signature to distinguish CN status was then developed by incorporating the radiomics score and the selected traditional predictors. The receiver operating characteristic (ROC) curve was plotted to evaluate the predictive performance. Results: The area under the ROC curve (AUC) of the radiomics score, which consisted of 7 radiomics features, was 0.855 in the training set and 0.885 in the validation set. The AUC of the traditional predictor, which consisted of 2 traditional features, was 0.843 in the training set and 0.858 in the validation set. The radiomics signature showed the best performance with an AUC of 0.942 in the training set, which was then confirmed with an AUC of 0.969 in the validation set. Conclusion: The CT-based radiomics signature that incorporated radiomics and traditional features has the potential to be used as a non-invasive tool for preoperative prediction of CN in ccRCC.

Keywords

Acknowledgement

This study was supported by the science and Technology Development Plant of Jilin Province (No.20180101015JC), the research grant from the Jilin Province Science and Technology Development Plan Project (NO.20190303182SF).

References

  1. Lane BR, Kattan MW. Predicting outcomes in renal cell carcinoma. Curr Opin Urol 2005;15:289-297 https://doi.org/10.1097/01.mou.0000178336.94991.17
  2. Sheth S, Scatarige JC, Horton KM, Corl FM, Fishman EK. Current concepts in the diagnosis and management of renal cell carcinoma: role of multidetector CT and three-dimensional CT. Radiographics 2001;21:S237-S254 https://doi.org/10.1148/radiographics.21.suppl_1.g01oc18s237
  3. Tsui KH, Shvarts O, Smith RB, Figlin R, de Kernion JB, Belldegrun A. Renal cell carcinoma: prognostic significance of incidentally detected tumors. J Urol 2000;163:426-430 https://doi.org/10.1016/S0022-5347(05)67892-5
  4. Rabjerg M, Mikkelsen MN, Walter S, Marcussen N. Incidental renal neoplasms: is there a need for routine screening? A Danish single-center epidemiological study. APMIS 2014;122:708-714 https://doi.org/10.1111/apm.12282
  5. Hollingsworth JM, Miller DC, Daignault S, Hollenbeck BK. Rising incidence of small renal masses: a need to reassess treatment effect. J Natl Cancer Inst 2006;98:1331-1334 https://doi.org/10.1093/jnci/djj362
  6. Leibovich BC, Lohse CM, Crispen PL, Boorjian SA, Thompson RH, Blute ML, et al. Histological subtype is an independent predictor of outcome for patients with renal cell carcinoma. J Urol 2010;183:1309-1315 https://doi.org/10.1016/j.juro.2009.12.035
  7. Delahunt B, Cheville JC, Martignoni G, Humphrey PA, Magi-Galluzzi C, McKenney J, et al. The International Society of Urological Pathology (ISUP) grading system for renal cell carcinoma and other prognostic parameters. Am J Surg Pathol 2013;37:1490-1504 https://doi.org/10.1097/PAS.0b013e318299f0fb
  8. Klatte T, Kroeger N, Zimmermann U, Burchardt M, Belldegrun AS, Pantuck AJ. The contemporary role of ablative treatment approaches in the management of renal cell carcinoma (RCC): focus on radiofrequency ablation (RFA), high-intensity focused ultrasound (HIFU), and cryoablation. World J Urol 2014;32:597-605 https://doi.org/10.1007/s00345-014-1284-7
  9. Ljungberg B, Cowan NC, Hanbury DC, Hora M, Kuczyk MA, Merseburger AS, et al. EAU guidelines on renal cell carcinoma: the 2010 update. Eur Urol 2010;58:398-406 https://doi.org/10.1016/j.eururo.2010.06.032
  10. Amtrup F, Hansen JB, Thybo E. Prognosis in renal carcinoma evaluated from histological criteria. Scand J Urol Nephrol 1974;8:198-202 https://doi.org/10.3109/00365597409132129
  11. Sengupta S, Lohse CM, Leibovich BC, Frank I, Thompson RH, Webster WS, et al. Histologic coagulative tumor necrosis as a prognostic indicator of renal cell carcinoma aggressiveness. Cancer 2005;104:511-520 https://doi.org/10.1002/cncr.21206
  12. Zhang L, Zha Z, Qu W, Zhao H, Yuan J, Feng Y, et al. Tumor necrosis as a prognostic variable for the clinical outcome in patients with renal cell carcinoma: a systematic review and meta-analysis. BMC Cancer 2018;18:870
  13. Dagher J, Delahunt B, Rioux-Leclercq N, Egevad L, Coughlin G, Dunglison N, et al. Assessment of tumour-associated necrosis provides prognostic information additional to World Health Organization/International Society of Urological Pathology grading for clear cell renal cell carcinoma. Histopathology 2019;74:284-290 https://doi.org/10.1111/his.13737
  14. Ficarra V, Brunelli M, Novara G, D'Elia C, Segala D, Gardiman M, et al. Accuracy of on-bench biopsies in the evaluation of the histological subtype, grade, and necrosis of renal tumours. Pathology 2011;43:149-155 https://doi.org/10.1097/PAT.0b013e32834317a4
  15. Mally AD, Gayed B, Averch T, Davies B. The current role of percutaneous biopsy of renal masses. Can J Urol 2012;19:6243-6249
  16. Herts BR, Coll DM, Novick AC, Obuchowski N, Linnell G, Wirth SL, et al. Enhancement characteristics of papillary renal neoplasms revealed on triphasic helical CT of the kidneys. AJR Am J Roentgenol 2002;178:367-372 https://doi.org/10.2214/ajr.178.2.1780367
  17. Choi SY, Sung DJ, Yang KS, Kim KA, Yeom SK, Sim KC, et al. Small (< 4 cm) clear cell renal cell carcinoma: correlation between CT findings and histologic grade. Abdom Radiol (NY) 2016;41:1160-1169 https://doi.org/10.1007/s00261-016-0732-9
  18. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 2012;48:441-446 https://doi.org/10.1016/j.ejca.2011.11.036
  19. Ding J, Xing Z, Jiang Z, Chen J, Pan L, Qiu J, et al. CT-based radiomic model predicts high grade of clear cell renal cell carcinoma. Eur J Radiol 2018;103:51-56 https://doi.org/10.1016/j.ejrad.2018.04.013
  20. Zhang X, Xu X, Tian Q, Li B, Wu Y, Yang Z, et al. Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging. J Magn Reson Imaging 2017;46:1281-1288 https://doi.org/10.1002/jmri.25669
  21. Zhu X, Dong D, Chen Z, Fang M, Zhang L, Song J, et al. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol 2018;28:2772-2778 https://doi.org/10.1007/s00330-017-5221-1
  22. Smyth EC, Verheij M, Allum W, Cunningham D, Cervantes A, Arnold D, et al. Gastric cancer: ESMO clinical practice guidelines for diagnosis, treatment and follow-up. Ann Oncol 2016;27:v38-v49 https://doi.org/10.1093/annonc/mdw350
  23. Tsili AC, Argyropoulou MI, Gousia A, Kalef-Ezra J, Sofikitis N, Malamou-Mitsi V, et al. Renal cell carcinoma: value of multiphase MDCT with multiplanar reformations in the detection of pseudocapsule. AJR Am J Roentgenol 2012;199:379-386 https://doi.org/10.2214/AJR.11.7747
  24. Schiavina R, Borghesi M, Chessa F, Dababneh H, Bianchi L, Della Mora L, et al. The prognostic impact of tumor size on cancer-specific and overall survival among patients with pathologic T3a renal cell carcinoma. Clin Genitourin Cancer 2015;13:e235-e241 https://doi.org/10.1016/j.clgc.2014.06.011
  25. Cho S, Lee JH, Jeon SH, Park J, Lee SH, Kim CH, et al. A prospective, multicenter analysis of pseudocapsule characteristics: do all stages of renal cell carcinoma have complete pseudocapsules? Urol Oncol 2017;35:370-378 https://doi.org/10.1016/j.urolonc.2017.01.003
  26. Ng F, Ganeshan B, Kozarski R, Miles KA, Goh V. Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival. Radiology 2013;266:177-184 https://doi.org/10.1148/radiol.12120254
  27. 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
  28. Brinker DA, Amin MB, de Peralta-Venturina M, Reuter V, Chan DY, Epstein JI. Extensively necrotic cystic renal cell carcinoma: a clinicopathologic study with comparison to other cystic and necrotic renal cancers. Am J Surg Pathol 2000;24:988-995 https://doi.org/10.1097/00000478-200007000-00010
  29. Khor LY, Dhakal HP, Jia X, Reynolds JP, McKenney JK, Rini BI, et al. Tumor necrosis adds prognostically significant information to grade in clear cell renal cell carcinoma: a study of 842 consecutive cases from a single institution. Am J Surg Pathol 2016;40:1224-1231 https://doi.org/10.1097/PAS.0000000000000690