Differentiation of clear cell and non-clear cell renal cell carcinomas by all-relevant radiomics features from multiphase CT: a VHL mutation perspective
- 161 Downloads
To develop a radiomics model with all-relevant imaging features from multiphasic computed tomography (CT) for differentiating clear cell renal cell carcinoma (ccRCC) from non-ccRCC and to investigate the possible radiogenomics link between the imaging features and a key ccRCC driver gene—the von Hippel-Lindau (VHL) gene mutation.
In this retrospective two-center study, two radiomics models were built using random forest from a training cohort (170 patients), where one model was built with all-relevant features and the other with minimum redundancy maximum relevance (mRMR) features. A model combining all-relevant features and clinical factors (sex, age) was also built. The radiogenomics association between selected features and VHL mutation was investigated by Wilcoxon rank-sum test. All models were tested on an independent validation cohort (85 patients) with ROC curves analysis.
The model with eight all-relevant features from corticomedullary phase CT achieved an AUC of 0.949 and an accuracy of 92.9% in the validation cohort, which significantly outperformed the model with eight mRMR features (seven from nephrographic phase and one from corticomedullary phase) with an AUC of 0.851 and an accuracy of 81.2%. Combining age and sex did not benefit the performance. Five out of eight all-relevant features were significantly associated with VHL mutation, while all eight mRMR features were significantly associated with VHL mutation (false discovery rate-adjusted p < 0.05).
All-relevant features in corticomedullary phase CT can be used to differentiate ccRCC from non-ccRCC. Most subtype-discriminative imaging features were found to be significantly associated with VHL mutation, which may underlie the molecular basis of the radiomics features.
• All-relevant features in corticomedullary phase CT can be used to differentiate ccRCC from non-ccRCC with high accuracy.
• Most RCC-subtype-discriminative CT features were associated with the key RCC-driven gene—the VHL gene mutation.
• Radiomics model can be more accurate and interpretable when the imaging features could reflect underlying molecular basis of RCC.
KeywordsRenal cell carcinomas Diagnostic imaging Radiomics von Hippel-Lindau disease
Area under the ROC curve
Clear cell renal cell carcinoma
Chromophobe renal cell carcinoma
False discovery rate
Gray-level co-occurrence matrix
Gray-level run length matrix
Gray level size zone matrix
Intraclass correlation coefficient
Magnetic resonance imaging
Minimum redundancy maximum relevance ensemble
Neighborhood gray-tone difference matrix
Papillary renal cell carcinoma
Renal cell carcinoma
Receiver operating characteristic curve
This study has received funding from the National Natural Science Foundation of China (no. 61571432) and Shenzhen Basic Research Program (JCYJ20170413162354654).
Compliance with ethical standards
The scientific guarantor of this publication is Hairong Zheng.
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
One of the authors (Zhi-Cheng Li) has significant statistical expertise.
Written informed consent was obtained from all patients.
Institutional Review Board approval was obtained.
• diagnostic or prognostic study
• multicenter study
- 1.Ferlay J, Soerjomataram I, Ervik M et al (2013) Cancer incidence and mortality worldwide: IARC cancer base No. 11. Available via: http://globocan.iarc.fr. Accessed 22 July 2018
- 17.Hodgdon T, McInnes MD, Schieda N, Flood TA, Lamb L, Thornhill RE (2017) Can quantitative CT texture analysis be used to differentiate fat-poor renal angiomyolipoma from renal cell carcinoma on unenhanced CT images? Radiology 276:787–796Google Scholar
- 24.Yu HS, Scalera J, Khalid M et al (2017) Texture analysis as a radiomic marker for differentiating renal tumors. Abdom Radiol (NY) (10):2470–2478Google Scholar
- 27.Nilsson R, Peña JM, Björkegren J, Tegnér J (2007) Consistent feature selection for pattern recognition in polynomial time. J Mach Learn Res 8:589–612Google Scholar
- 28.Rudnicki WR, Wrzesień M, Paja W (2015) All relevant feature selection methods and applications. In: Stańczyk U, Jain LC (Eds.) Feature selection for data and pattern recognition. Springer, Berlin, pp 11–28Google Scholar
- 32.Díaz-Uriarte R, Alvarez de Andrés S (2006) Gene selection and classification of microarray data using random forest. BMC Bioinformatics 7(3)Google Scholar
- 34.De Jay N, Papillon-Cavanagh S, Olsen C, El-Hachem N, Bontempi G, Haibe-Kains B (2015) mRMRe: an R package for parallelized mRMR ensemble feature selection. Bioinformatics 29:2365–2368Google Scholar
- 36.Louppe G, Wehenkel L, Sutera A, Geurts P (2013) Understanding variable importances in forests of randomized trees. Adv Neural Inf Process Syst:431–439Google Scholar
- 37.DeLong ER, DeLong DM, Clarke-Pearson DL (1998) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics:837–845Google Scholar
- 38.Benjamini Y, Hochberg Y (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. J R Stat Soc Series B Stat Methodol 57:289–300Google Scholar
- 41.Baessler B, Mannil M, Oebel S, Maintz D, Alkadhi H, Manka R (2017) Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology 286:103–112Google Scholar
- 46.Zhang L, Fried DV, Fave XJ, Hunter LA, Yang J, Court LE (2015) IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics. Med Phys 42:1341–1353Google Scholar
- 47.Food and Drug Administration (2017) Device classification under Section 513(f)(2)(de novo). Available via http://www.accessdata.fda.gov/cdrh_docs/pdf17/DEN170022.pdf. Accessed 18 Oct 2018