Computed Tomography Radiomics for Predicting Pathological Grade of Renal Cell Carcinoma

Xiaoping Yi, Qiao Xiao, Feiyue Zeng, Hongling Yin, Zan Li, Cheng Qian, Cikui Wang, Guangwu Lei, Qingsong Xu, Chuanquan Li, Minghao Li, Guanghui Gong, Chishing Zee, Xiao Guan, Longfei Liu, Bihong T Chen, Xiaoping Yi, Qiao Xiao, Feiyue Zeng, Hongling Yin, Zan Li, Cheng Qian, Cikui Wang, Guangwu Lei, Qingsong Xu, Chuanquan Li, Minghao Li, Guanghui Gong, Chishing Zee, Xiao Guan, Longfei Liu, Bihong T Chen

Abstract

Background: Clear cell renal cell carcinoma (ccRCC) is the most common renal cancer and it has the worst prognosis among all renal cancers. However, traditional radiological characteristics on computed tomography (CT) scans of ccRCC have been insufficient to predict the pathological grade of ccRCC before surgery.

Methods: Patients with ccRCC were retrospectively enrolled into this study and were separated into two groups according to the World Health Organization (WHO)/International Society of Urological Pathology (ISUP) grading system, i.e., low-grade (Grade I and II) group and high-grade (Grade III and IV) group. Traditional CT radiological characteristics such as tumor size, pre- and post-enhancing CT densities were assessed. In addition, radiomic texture analysis based on the CT imaging of the ccRCC were also performed. A CT-based machine learning method combining the traditional radiological characteristics and radiomic features was used in the predictive modeling for differentiating the low-grade from the high-grade ccRCC. Model performance was evaluated with the receiver operating characteristic curve (ROC) analysis.

Results: A total of 264 patients with pathologically confirmed ccRCC were included in this study. In this cohort, 206 patients had the low-grade tumors and 58 had the high-grade tumors. The model built with traditional radiological characteristics achieved an area under the curve (AUC) of 0.9175 (95% CI: 0.8765-0.9585) and 0.8088 (95% CI: 0.7064-0.9113) in differentiating the low-grade from the high-grade ccRCC for the training cohort and the validation cohort respectively. The model built with the radiomic textural features yielded an AUC value of 0.8170 (95% CI: 0.7353-0.8987) and 0.8017 (95% CI: 0.6878-0.9157) for the training cohort and the validation cohort, respectively. The combined model integrating both the traditional radiological characteristics and the radiomic textural features achieved the highest efficacy, with an AUC of 0.9235 (95% CI: 0.8646-0.9824) and an AUC of 0.9099 (95% CI: 0.8324-0.9873) for the training cohort and validation cohort, respectively.

Conclusion: We developed a machine learning radiomic model achieving a satisfying performance in differentiating the low-grade from the high-grade ccRCC. Our study presented a potentially useful non-invasive imaging-focused method to predict the pathological grade of renal cancers prior to surgery.

Keywords: clear cell renal cell carcinoma; computed tomography (CT); machine learning; predictive modeling; radiomics.

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2021 Yi, Xiao, Zeng, Yin, Li, Qian, Wang, Lei, Xu, Li, Li, Gong, Zee, Guan, Liu and Chen.

Figures

Figure 1
Figure 1
Study recruitment diagram with respect to inclusion and exclusion criteria.
Figure 2
Figure 2
Flow chart for radiomic feature extraction, feature selection and predictive modeling. (I) Representative tumor segmentation computed tomography (CT) images. (II) Radiomic feature extraction. (III) Radiomic feature selection. (IV) Classification algorithm and predictive modeling.
Figure 3
Figure 3
Classification efficiencies of the three support vector machine (SVM) models. (A) Model built with radiomic textural features. (B) Model built with traditional radiological characteristics. (C) Model built with both radiomic textural features and traditional radiological features. (D) Receiver operating characteristic (ROC) curve analysis for the training cohort. (E) Receiver operating characteristic (ROC) curve analysis for the validation cohort. LASSO, least absolute shrinkage and selection operator; SVM, Support vector machine.
Figure 4
Figure 4
Classification efficiency for the training cohort and the validation cohort for the support vector machine (SVM) models.
Figure 5
Figure 5
Correlation matrix test among all 19 radiomic textural features and four traditional radiological features (bold font) used in predictive modeling. S-S, indicating the craniocaudal dimension of the tumor; L-R, indicating the transverse dimension of the tumor.

References

    1. Siegel RL, Miller KD, Jemal A. Cancer statistics, 2018. CA Cancer J Clin (2018) 68(1):7–30. 10.3322/caac.21442
    1. Wan XM, Peng LB, Ma JA, Li YJ. Economic evaluation of nivolumab as a second-line treatment for advanced renal cell carcinoma from US and Chinese perspectives. Cancer (2017) 123(14):2634–41. 10.1002/cncr.30666
    1. Znaor A, Lortet-Tieulent J, Laversanne M, Jemal A, Bray F. International variations and trends in renal cell carcinoma incidence and mortality. Eur Urol (2015) 67(3):519–30. 10.1016/j.eururo.2014.10.002
    1. Wang Z, Qi L, Yuan P, Zu X, Chen W, Cao Z, et al. Application of Three-Dimensional Visualization Technology in Laparoscopic Partial Nephrectomy of Renal Tumor: A Comparative Study. J Laparoendosc Adv Surg Tech A (2017) 27(5):516–23. 10.1089/lap.2016.0645
    1. Liu L, Qi L, Li Y, Chen M, Li C, Cheng X, et al. Retroperitoneoscopic Partial Nephrectomy for Moderately Complex Ventral Hilar Tumors: Surgical Technique and Trifecta Outcomes from a Single Institution in China. J Laparoendosc Adv Surg Tech A (2017) 27(8):812–7. 10.1089/lap.2016.0194
    1. Ljungberg B, Bensalah K, Canfield S, Dabestani S, Hofmann F, Hora M, et al. EAU guidelines on renal cell carcinoma: 2014 update. Eur Urol (2015) 67(5):913–24. 10.1016/j.eururo.2015.01.005
    1. 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(10):1490–504. 10.1097/PAS.0b013e318299f0fb
    1. Kim H, Inomoto C, Uchida T, Furuya H, Komiyama T, Kajiwara H, et al. Verification of the International Society of Urological Pathology recommendations in Japanese patients with clear cell renal cell carcinoma. Int J Oncol (2018) 52(4):1139–48. 10.3892/ijo.2018.4294
    1. Dagher J, Delahunt B, Rioux-Leclercq N, Egevad L, Srigley JR, Coughlin G, et al. Clear cell renal cell carcinoma: validation of World Health Organization/International Society of Urological Pathology grading. Histopathology (2017) 71(6):918–25. 10.1111/his.13311
    1. Moch H, Cubilla AL, Humphrey PA, Reuter VE, Ulbright TM. The 2016 WHO Classification of Tumours of the Urinary System and Male Genital Organs-Part A: Renal, Penile, and Testicular Tumours. Eur Urol (2016) 70(1):93–105. 10.1016/j.eururo.2016.02.029
    1. Ficarra V, Martignoni G, Galfano A, Novara G, Gobbo S, Brunelli M, et al. Prognostic role of the histologic subtypes of renal cell carcinoma after slide revision. Eur Urol (2006) 50(4):786–93; discussion 793-4. 10.1016/j.eururo.2006.04.009
    1. Cheville JC, Lohse CM, Zincke H, Weaver AL, Blute ML. Comparisons of outcome and prognostic features among histologic subtypes of renal cell carcinoma. Am J Surg Pathol (2003) 27(5):612–24. 10.1097/00000478-200305000-00005
    1. Amin MB, Amin MB, Tamboli P, Javidan J, Stricker H, de-Peralta Venturina M, et al. Prognostic impact of histologic subtyping of adult renal epithelial neoplasms: an experience of 405 cases. Am J Surg Pathol (2002) 26(3):281–91. 10.1097/00000478-200203000-00001
    1. Kuthi L, Jenei A, Hajdu A, Németh I, Varga Z, Bajory Z, et al. Prognostic Factors for Renal Cell Carcinoma Subtypes Diagnosed According to the 2016 WHO Renal Tumor Classification: a Study Involving 928 Patients. Pathol Oncol Res (2017) 23(3):689–98. 10.1007/s12253-016-0179-x
    1. Mouracade P, Kara O, Maurice MJ, Dagenais J, Malkoc E, Nelson RJ, et al. Patterns and Predictors of Recurrence after Partial Nephrectomy for Kidney Tumors. J Urol (2017) 197(6):1403–9. 10.1016/j.juro.2016.12.046
    1. Chen W, Zheng R, Baade PD, Zhang S, Zeng H, Bray F, et al. Cancer statistics in China, 2015. CA Cancer J Clin (2016) 66(2):115–32. 10.3322/caac.21338
    1. Yan Y, Liu L, Zhou J, Li L, Yuan Li Y, Chen M, et al. Clinicopathologic characteristics and prognostic factors of sarcomatoid renal cell carcinoma. J Cancer Res Clin Oncol (2015) 141(2):345–52. 10.1007/s00432-014-1740-1
    1. Lane BR, Samplaski MK, Herts BR, Zhou M, Novick AC, Campbell SC. Renal mass biopsy–a renaissance. J Urol (2008) 179(1):20–7. 10.1016/j.juro.2007.08.124
    1. Bjurlin MA, Elkin EB, Atoria CL, Russo P, Taneja SS, Huang WC. Influence of renal biopsy results on the management of small kidney cancers in older patients: Results from a population-based cohort. Urol Oncol (2017) 35(10):604.e1–9. 10.1016/j.urolonc.2017.05.025
    1. Chen SH, Wu YP, Li XD, Lin T, Guo QY, Chen YH, et al. R.E.N.A.L. Nephrometry Score: A Preoperative Risk Factor Predicting the Fuhrman Grade of Clear-Cell Renal Carcinoma. J Cancer (2017) 8(18):3725–32. 10.7150/jca.21189
    1. Oh S, Sung DJ, Yang KS, Sim KC, Han NY, Park BJ, et al. Correlation of CT imaging features and tumor size with Fuhrman grade of clear cell renal cell carcinoma. Acta Radiol (2017) 58:376–84. 10.1177/0284185116649795
    1. Cornelis F, Tricaud E, Lasserre AS, Petitpierre F, Bernhard JC, Le Bras Y, et al. Multiparametric magnetic resonance imaging for the differentiation of low and high grade clear cell renal carcinoma. Eur Radiol (2015) 25(1):24–31. 10.1007/s00330-014-3380-x
    1. Zhu YH, Wang X, Zhang J, Chen YH, Kong W, Huang YR. Low enhancement on multiphase contrast-enhanced CT images: an independent predictor of the presence of high tumor grade of clear cell renal cell carcinoma. AJR Am J Roentgenol (2014) 203:W295–300. 10.2214/AJR.13.12297
    1. Vargas HA, Delaney HG, Delappe EM, Wang Y, Zheng J, Moskowitz CS, et al. Multiphasic contrast-enhanced MRI: single-slice versus volumetric quantification of tumor enhancement for the assessment of renal clear-cell carcinoma fuhrman grade. J Magn Reson Imaging (2013) 37(5):1160–7. 10.1002/jmri.23899
    1. Feng Z, Rong P, Cao P, Zhou Q, Zhu W, Yan Z, et al. Machine learning-based quantitative texture analysis of CT images of small renal masses: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur Radiol (2018) 28(4):1625–33. 10.1007/s00330-017-5118-z
    1. Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol (2017) 14(12):749–62. 10.1038/nrclinonc.2017.141
    1. 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) 103:51–6. 10.1016/j.ejrad.2018.04.013
    1. Cho H, Park H. Classification of low-grade and high-grade glioma using multi-modal image radiomics features. Conf Proc IEEE Eng Med Biol Soc (2017) 2017:3081–4. 10.1109/EMBC.2017.8037508
    1. Shu J, Wen D, Xi Y, Xia Y, Cai Z, Xu W, et al. Clear cell renal cell carcinoma: Machine learning-based computed tomography radiomics analysis for the prediction of WHO/ISUP grade. Eur J Radiol (2019) 121:108738. 10.1016/j.ejrad.2019.108738
    1. Ren S, Zhao R, Cui W, Qiu W, Guo K, Cao Y, et al. Computed Tomography-Based Radiomics Signature for the Preoperative Differentiation of Pancreatic Adenosquamous Carcinoma From Pancreatic Ductal Adenocarcinoma. Front Oncol (2020) 10:1618. 10.3389/fonc.2020.01618
    1. Szczypiński PM, Strzelecki M, Materka A, Klepaczko A. MaZda–a software package for image texture analysis. Comput Methods Programs Biomed (2009) 94:66–76. 10.1016/j.cmpb.2008.08.005
    1. Yi X, Pei Q, Zhang Y, Zhu H, Wang Z, Chen C, et al. MRI-Based Radiomics Predicts Tumor Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer. Front Oncol (2019) 9:552. 10.3389/fonc.2019.00552
    1. 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(4):441–6. 10.1016/j.ejca.2011.11.036
    1. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology (2016) 278(2):563–77. 10.1148/radiol.2015151169
    1. Lubner MG. Radiomics and Artificial Intelligence for Renal Mass Characterization. Radiol Clin North Am (2020) 58:995–1008. 10.1016/j.rcl.2020.06.001
    1. Shu J, Tang Y, Cui J, Yang R, Meng X, Cai Z, et al. Clear cell renal cell carcinoma: CT-based radiomics features for the prediction of Fuhrman grade. Eur J Radiol (2018) 109:8–12. 10.1016/j.ejrad.2018.10.005
    1. Chaddad A, Kucharczyk MJ, Daniel P, Sabri S, Jean-Claude BJ, Niazi T, et al. Radiomics in Glioblastoma: Current Status and Challenges Facing Clinical Implementation. Front Oncol (2019) 9:374. 10.3389/fonc.2019.00374
    1. Cui E, Li Z, Ma C, Li Q, Lei Y, Lan Y, et al. Predicting the ISUP grade of clear cell renal cell carcinoma with multiparametric MR and multiphase CT radiomics. Eur Radiol (2020) 30:2912–21. 10.1007/s00330-019-06601-1
    1. Zhao Y, Chang M, Wang R, Xi IL, Chang K, Huang RY, et al. Deep Learning Based on MRI for Differentiation of Low- and High-Grade in Low-Stage Renal Cell Carcinoma. J Magn Reson Imaging (2020). 10.1002/jmri.27153
    1. Sun X, Liu L, Xu K, Li W, Huo Z, Liu H, et al. Prediction of ISUP grading of clear cell renal cell carcinoma using support vector machine model based on CT images. Med (Baltimore) (2019) 98:e15022. 10.1097/MD.0000000000015022
    1. Han D, Yu Y, Yu N, Dang S, Wu H, Jialiang R, et al. Prediction models for clear cell renal cell carcinoma ISUP/WHO grade: comparison between CT radiomics and conventional contrast-enhanced CT. Br J Radiol (2020) 93:20200131. 10.1259/bjr.20200131

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe