CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma
To predict the Fuhrman grade of clear cell renal cell carcinoma (ccRCC) with a machine learning classifier based on single- or three-phase computed tomography (CT) images.
Materials and methods
Patients with pathologically proven ccRCC from February 1, 2009 to September 31, 2018 who were not treated were retrospectively collected for machine learning-based analysis. The texture features were extracted and ranked from precontrast phase (PCP), corticomedullary phase (CMP), nephrographic phase (NP) and three-phase CT images, and open-source gradient boosting from the decision tree library of CatBoost was used to establish a machine learning classifier to differentiate low- from high-grade ccRCC. The performances of machine learning classifiers based on features from single- and three-phase CT images were compared with each other.
A total of 231 patients with 232 pathologically proven ccRCC lesions were retrospectively collected. 35, 36, 41, and 22 Features were extracted and ranked from PCP, CMP, NP, and three-phase CT images, respectively. The machine learning model based on three-phase CT images [area under the ROC curve (AUC) = 0.87] achieved the best diagnostic performance for differentiating low- from high-grade ccRCC, followed by single-phase NP (AUC = 0.84), CMP (AUC = 0.80), and PCP images (AUC = 0.82).
Machine learning classifiers can be promising noninvasive techniques to differentiate low- and high-Fuhrman nuclear grade ccRCC, and classifiers based on three-phase CT images are superior to those based on features from each single phase.
KeywordsMachine learning Texture analysis Clear cell carcinoma Fuhrman nuclear grade
Compliance with ethical standards
Conflict of interest
The authors declare there are no conflicts of interest regarding the publication of this paper.
- 1.C. Global Burden of Disease Cancer, C. Fitzmaurice, D. Dicker, et al. The Global Burden of Cancer 2013. JAMA Oncol. 2015;1(4):505–527.Google Scholar
- 19.A. Zwanenburg, S. Leger, M. Vallières, et al. Image biomarker standardisation initiative. arXiv preprint arXiv:1612.07003. 2016.
- 20.A. V. Dorogush, A. Gulin, G. Gusev, et al. Fighting biases with dynamic boosting. arXiv preprint arXiv:1706.09516. 2017.
- 21.A. V. Dorogush, V. Ershov and A. Gulin. CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363. 2018.
- 22.H. Coy, J. R. Young, M. L. Douek, et al. Association of qualitative and quantitative imaging features on multiphasic multidetector CT with tumor grade in clear cell renal cell carcinoma. Abdom Radiol (NY). 2018.Google Scholar
- 23.L. C. Adams, B. Ralla, P. Jurmeister, et al. Native T1 Mapping as an In Vivo Biomarker for the Identification of Higher-Grade Renal Cell Carcinoma: Correlation With Histopathological Findings. Invest Radiol. 2018.Google Scholar
- 27.Y. W. Park, J. Oh, S. C. You, et al. Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging. Eur Radiol. 2018.Google Scholar
- 29.C. T. Bektas, B. Kocak, A. H. Yardimci, et al. Clear Cell Renal Cell Carcinoma: Machine Learning-Based Quantitative Computed Tomography Texture Analysis for Prediction of Fuhrman Nuclear Grade. Eur Radiol. 2018.Google Scholar
- 36.R. Guarch, J. M. Cortes, C. H. Lawrie, et al. Multi-site tumor sampling (MSTS) improves the performance of histological detection of intratumor heterogeneity in clear cell renal cell carcinoma (CCRCC). F1000Res. 2016;5:2020.Google Scholar