CT-Based Radiomics Combined with Deep Learning for Preoperative Differentiation of Clear Cell and Non–Clear Cell Renal Cell Carcinoma: Internal and External Validation Study
Keywords:
Renal cell carcinoma, Computed Tomography, Radiomics, Deep Learning, Machine LearningAbstract
Objective: Accurate preoperative differentiation of renal cell carcinoma (RCC) subtypes remains challenging with conventional computed tomography (CT) owing to overlapping features. This study evaluated CT-based radiomics combined with deep learning for differentiation of clear cell RCC (ccRCC) from non–clear cell RCC (non-ccRCC), using internal and external validation. Methods: This retrospective, single-center study included an internal cohort of 121 patients with histopathologically confirmed RCC (84 ccRCC, 37 non-ccRCC) and an independent external cohort of 73 patients. All underwent preoperative multiphasic contrast-enhanced CT (128-slice Ingenuity). Corticomedullary-phase tumors were segmented in 3D Slicer by two radiologists; inter-observer reliability used the intraclass correlation coefficient (ICC). In total, 122 radiomic features were extracted (first-order, GLCM, GLRLM, GLSZM, GLDM, shape). Least absolute shrinkage and selection operator (LASSO) regression selected features for a deep learning–based classification model. Diagnostic efficacy was assessed by receiver operating characteristic (ROC) curve analysis. Results: Inter-observer agreement was excellent (ICC = 0.91; 95% CI, 0.87–0.94). In the internal cohort, the model achieved an area under the curve (AUC) of 0.92, sensitivity 83.3%, specificity 92.3%, and accuracy 86.0%. GLRLM features were most discriminative (AUC = 0.91, p < .001), followed by first-order uniformity (AUC = 0.88) and variance (AUC = 0.86). In the external cohort, performance remained robust (AUC = 0.86, sensitivity 82.0%, specificity 80.0%, accuracy 80.8%), confirming generalizability. Conclusion: CT-based radiomics combined with deep learning demonstrates high diagnostic performance for differentiating ccRCC from non-ccRCC, generalizing across internal and external datasets. This non-invasive approach may serve as a valuable imaging biomarker supporting clinical decision-making and personalized treatment planning.
0
References
1. Sheth S, Scatarige JC, Horton KM, et al. 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
2. Catalano C, Fraioli F, Laghi A, et al. High-resolution multidetector CT in the preoperative evaluation of patients with renal cell carcinoma. AJR Am J Roentgenol. 2003;180(5):1271-1277. https://doi.org/10.2214/ajr.180.5.1801271
3. Johnson CD, Dunnick NR, Cohan RH, et al. Renal adenocarcinoma: CT staging of 100 tumors. AJR Am J Roentgenol. 1987;148(1):59-63. https://doi.org/10.2214/ajr.148.1.59
4. Fein AB, Lee JK, Balfe DM, et al. Diagnosis and staging of renal cell carcinoma: a comparison of MR imaging and CT. AJR Am J Roentgenol. 1987;148(4):749-753. https://doi.org/10.2214/ajr.148.4.749
5. Sun M, Zhou Y, Zhao Z, et al. CT-based radiomics for prediction of distant metastasis in clear cell renal cell carcinoma. Eur Radiol. 2022;32(4):2305-2314. https://doi.org/10.1007/s00330-021-08376-w
6. Shan S, Zhang Y, Li J, et al. A clinicoradiomics model for progression-free survival in renal cell carcinoma. Eur J Radiol. 2025;180:111234. https://doi.org/10.1016/j.ejrad.2024.111234
7. Liu H, Chen Y, Zhang X, et al. Multiphase CT-based radiomics model for risk stratification in renal cell carcinoma. Insights Imaging. 2023;14(1):26. https://doi.org/10.1186/s13244-023-01378-w
8. Zannotti A, Carconi C, Carozza R, et al. The role of radiomics in renal mass characterization. J Med Imaging Radiat Oncol. 2024;68(2):210-218. https://doi.org/10.1111/1754-9485.13616
9. Zheng Z, Chen Z, Xie Y, et al. Development and validation of a CT-based nomogram for preoperative prediction of clear cell renal cell carcinoma grades. Eur Radiol. 2021;31(8):6078-6086. https://doi.org/10.1007/s00330-020-07667-y
10. Wang R, Yang L, Huang J, et al. A radiomics nomogram for preoperative prediction of WHO/ISUP grade in clear cell renal cell carcinoma. Front Oncol. 2021;11:543854. https://doi.org/10.3389/fonc.2021.543854
11. Wang P, Li H, Liu X, et al. A radiomics-based nomogram for preoperative grading of renal cell carcinoma. Sci Rep. 2021;11(1):15001. https://doi.org/10.1038/s41598-021-94319-w
12. Nazari M, Shiri I, Hajianfar G, et al. Radiomics-based machine learning model for Fuhrman grade prediction in clear cell renal cell carcinoma. Comput Biol Med. 2019;108:10-18. https://doi.org/10.1016/j.compbiomed.2019.03.011
13. Nie P, Yang G, Wang Y, et al. A CT-based deep learning radiomics nomogram outperforms the existing prognostic models for outcome prediction in clear cell renal cell carcinoma: a multicenter study. Eur Radiol. 2023;33(12):8858-8868. https://doi.org/10.1007/s00330-023-09869-6
14. Birnbaum BA, Jacobs JE, Ramchandani P. Multiphasic renal CT: comparison of renal mass enhancement during the corticomedullary and nephrographic phases. Radiology. 1996;200(3):753-758. https://doi.org/10.1148/radiology.200.3.8756927
15. Yuh BI, Cohan RH. Different phases of renal enhancement: role in detecting and characterizing renal masses during helical CT. AJR Am J Roentgenol. 1999;173(3):747-755. https://doi.org/10.2214/ajr.173.3.10470916
16. Young JR, Margolis D, Sauk S, et al. Clear cell renal cell carcinoma: discrimination from other renal cell carcinoma subtypes and oncocytoma at multiphasic multidetector CT. Radiology. 2013;267(2):444-453. https://doi.org/10.1148/radiol.13112617
17. Lee-Felker SA, Felker ER, Tan N, et al. Qualitative and quantitative MDCT features for differentiating clear cell renal cell carcinoma from other solid renal cortical masses. AJR Am J Roentgenol. 2014;203(5):W516-W524. https://doi.org/10.2214/AJR.14.12460
18. Coy H, Young JR, Douek ML, et al. Quantitative computer-aided diagnostic algorithm for automated detection of peak lesion attenuation in differentiating clear cell from papillary and chromophobe renal cell carcinoma, oncocytoma, and fat-poor angiomyolipoma on multiphasic multidetector computed tomography. Abdom Radiol (NY). 2017;42(7):1919-1928. https://doi.org/10.1007/s00261-017-1095-6
19. Kim SH, Kim CS, Kim MJ, et al. Differentiation of clear cell renal cell carcinoma from other subtypes and fat-poor angiomyolipoma by use of quantitative enhancement measurement during three-phase MDCT. AJR Am J Roentgenol. 2016;206(1):W21-W28. https://doi.org/10.2214/AJR.15.14666
20. Ruppert-Kohlmayr AJ, Uggowitzer M, Meissnitzer T, et al. Differentiation of renal clear cell carcinoma and renal papillary carcinoma using quantitative CT enhancement parameters. AJR Am J Roentgenol. 2004;183(5):1387-1391. https://doi.org/10.2214/ajr.183.5.1831387
21. Lin P, Lin YQ, Gao RZ, et al. Radiomic profiling of clear cell renal cell carcinoma reveals subtypes with distinct prognosis and molecular pathways. Transl Oncol. 2021;14(1):100959. https://doi.org/10.1016/j.tranon.2020.100959
22. Alessandrino F, Shinagare AB, Bosse D, et al. Radiogenomics in renal cell carcinoma. Abdom Radiol (NY). 2019;44(6):1990-1998. https://doi.org/10.1007/s00261-018-1624-y
23. Varghese BA, Chen F, Hwang DH, et al. Differentiation of predominantly solid enhancing lipid-poor renal cell masses by use of contrast-enhanced CT: evaluating the role of texture in tumor subtyping. AJR Am J Roentgenol. 2018;211(6):W288-W296. https://doi.org/10.2214/AJR.18.19551
24. Wentland AL, Yamashita R, Kino A, et al. Differentiation of benign from malignant solid renal lesions using CT-based radiomics and machine learning: comparison with radiologist interpretation. Abdom Radiol (NY). 2023;48(2):642-648. https://doi.org/10.1007/s00261-022-03735-7
25. Feng Z, Rong P, Cao P, 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):1625-1633. https://doi.org/10.1007/s00330-017-5118-z
26. Zhang H, Yin F, Chen M, et al. A CT-based radiomics model for differentiating renal cell carcinoma subtypes. Front Oncol. 2021;11:617010. https://doi.org/10.3389/fonc.2021.617010
27. Yao N, Hu H, Chen K, et al. Deep learning for renal cell carcinoma subtype classification using CT imaging. Med Image Anal. 2023;85:102750. https://doi.org/10.1016/j.media.2023.102750
28. Aymerich M, Ortega R, García-Baizán A, et al. Radiomics-based classification of clear cell renal cell carcinoma. Diagnostics (Basel). 2025;15(11):1337. https://doi.org/10.3390/diagnostics15111337
29. Han S, Hwang SI, Lee HJ. The classification of renal cancer in 3-phase CT images using a deep learning method. J Digit Imaging. 2019;32(4):638-643. https://doi.org/10.1007/s10278-019-00230-2
30. Uhlig A, Uhlig J, Leha A, et al. Radiomics and machine learning for renal tumor subtype assessment using multiphase computed tomography in a multicenter setting. Eur Radiol. 2024;34(9):6254-6263. https://doi.org/10.1007/s00330-024-10731-6
31. Kocak B, Yardimci AH, Bektas CT, et al. Textural differences between renal cell carcinoma subtypes: machine learning–based quantitative computed tomography texture analysis with independent external validation. Eur J Radiol. 2018;107:149-157. https://doi.org/10.1016/j.ejrad.2018.08.014
32. Karlo CA, Di Paolo PL, Chaim J, et al. Radiogenomics of clear cell renal cell carcinoma: associations between CT imaging features and mutations. Radiology. 2014;270(2):464-471. https://doi.org/10.1148/radiol.13130663
33. Hoang UN, Mojdeh Mirmomen S, Meirelles O, et al. Assessment of multiphasic contrast-enhanced MR imaging–based radiomic features for differentiating renal cell carcinoma subtypes. Sci Rep. 2018;8(1):1238. https://doi.org/10.1038/s41598-018-19503-x
34. Wu Y, Cao F, Lei H, et al. Interpretable multiphasic CT-based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study. Abdom Radiol (NY). 2024;49(9):3096-3106. https://doi.org/10.1007/s00261-024-04351-3
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Mongolian National University of Medical Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
