Abstract
Purpose
Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma. Currently, there is a lack of noninvasive methods to stratify ccRCC prognosis prior to any invasive therapies. The purpose of this study was to preoperatively predict the tumor stage, size, grade, and necrosis (SSIGN) score of ccRCC using MRI-based radiomics.
Methods
A multicenter cohort of 364 histopathologically confirmed ccRCC patients (272 low [< 4] and 92 high [≥ 4] SSIGN score) with preoperative T2-weighted and T1-contrast-enhanced MRI were retrospectively identified and divided into training (254 patients) and testing sets (110 patients). The performance of a manually optimized radiomics model was assessed by measuring accuracy, sensitivity, specificity, area under receiver operating characteristic curve (AUROC), and area under precision-recall curve (AUPRC) on an independent test set, which was not included in model training. Lastly, its performance was compared to that of a machine learning pipeline, Tree-Based Pipeline Optimization Tool (TPOT).
Results
The manually optimized radiomics model using Random Forest classification and Analysis of Variance feature selection methods achieved an AUROC of 0.89, AUPRC of 0.81, accuracy of 0.89 (95% CI 0.816–0.937), specificity of 0.95 (95% CI 0.875–0.984), and sensitivity of 0.72 (95% CI 0.537–0.852) on the test set. The TPOT using Extra Trees Classifier achieved an AUROC of 0.94, AUPRC of 0.83, accuracy of 0.89 (95% CI 0.816–0.937), specificity of 0.95 (95% CI 0.875–0.984), and sensitivity of 0.72 (95% CI 0.537–0.852) on the test set.
Conclusion
Preoperative MR radiomics can accurately predict SSIGN score of ccRCC, suggesting its promise as a prognostic tool that can be used in conjunction with diagnostic markers.
Similar content being viewed by others
Data availability
The material is not available for public use to protect patient information.
Code availability
The code is available for public use. The link is provided under Code Availability in Methods.
References
Inamura, K (2017) Renal Cell Tumors: Understanding Their Molecular Pathological Epidemiology and the 2016 WHO Classification. Int J Mol Sci 18(10): 2195.
Garfield K, LaGrange CA (2020) Cancer, Renal Cell. In: StatPearls; StatPearls Publishing LLC. https://www.ncbi.nlm.nih.gov/books/NBK470336/ Updated 2 August 2020. Accessed 27 September 2020.
Krabbe LM, Bagrodia A, Margulis V, Wood CG (2014) Surgical management of renal cell carcinoma. Semin Intervent Radiol 31(1): 27-32.
Klatte T, Rossi SH, Stewart GD (2018) Prognostic factors and prognostic models for renal cell carcinoma: a literature review. World J Urol 36(12): 1943-1952.
Frank I, Blute ML, Cheville JC, Lohse CM, Weaver AL, Zincke H (2002) An outcome prediction model for patients with clear cell renal cell carcinoma treated with radical nephrectomy based on tumor stage, size, grade and necrosis: the SSIGN score. J Urol 168(6): 2395-400.
Rossi SH, Klatte T, Usher-Smith J, Steward GD (2018) Epidemiology and screening for renal cancer. World J Urol 36(9): 1341-1353.
Malaeb BS, Martin DJ, Littooy FN, Lotan Y, Waters WB, Flanigan RC, Konenman KS (2005) The utility of screening renal ultrasonography: identifying renal cell carcinoma in an elderly asymptomatic population. BJU Int 95(7): 977-81.
Fenton JJ, Weiss NS (2004) Screening computed tomography: will it result in overdiagnosis of renal carcinoma. Cancer 100(5): 986-90.
Sohlberg EM, Metzner TJ, Leppert JT (2019) The Harms of Overdiagnosis and Overtreatment in Patients with Small Renal Masses: A Mini-review. Eur Urol Focus 5(6): 943-945.
Liu Z, Wang S, Dong D, Wei J, Fang C, Zhou X et al (2019) The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges Theranostics 9(5): 1303-1322.
Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin JC, Pujol S, et al (2012) 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging 30(9): 1323-41.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al (2011) Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12: 2825-2830.
Zwanenburg A, Leger S., Vallières M, Löck S (2016) Image biomarker standardisation initiative. arXiv preprint arXiv:161207003.
Olson RS, Urbanowicz RJ, Andrews PC, Lavender NA, Kidd LC, Moore JH (2016) Automating biomedical data science through tree-based pipeline optimization. arXiv preprint arXiv:1601.07925
Agresti A, Coull BA (1998) Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions. Am Stat 52: 119-126.
Scelo G, Larose TL (2018) Epidemiology and Risk Factors for Kidney Cancer. J Clin Oncol 36(36): 3574-81.
Ficarra V, Galfano A, Mancini M, Martignoni G, Artibani W (2007) TNM staging system for renal-cell carcinoma: current status and future perspectives. Lancet Oncol 8(6): 554-8.
Siemer S, Lehmann J, Loch A, Becker F, Stein U, Schneider G et al (2005) Current TNM classification of renal cell carcinoma evaluated: revising stage T3a. J Urol 173(1): 33-7.
Ficarra V, Martignoni G, Lohse C, Novara G, Pea M, Cavalleri S, Artibani W (2006) External Validation of the Mayo Clinic Stage, Size, Grade and Necrosis (SSIGN) Score to Predict Cancer Specific Survival Using a European Series of Conventional Renal Cell Carcinoma. J Urol 175(4): 1235-1239.
Fujii Y, Saito K, Limura Y, Sakai Y, Koga F, Kawakami S et al (2008) External validation of the Mayo Clinic cancer specific survival score in a Japanese series of clear cell renal cell carcinoma. J Urol 180(4): 1290-1295.
Zigeuner R, Hutterer G, Chromecki T, Imamovic A, Kampel-Kettner K, Rehak P et al (2010) External validation of the Mayo Clinic stage, size, grade, and necrosis (SSIGN) score for clear-cell renal cell carcinoma in a single European centre applying routine pathology. Eur Urol 57(1): 102-9.
Parker WP, Cheville JC, Frank I, Zaid HB, Lohse CM, Boorjian SA et al (2017) Application of the Stage, Size, Grade, and Necrosis (SSIGN) Score for Clear Cell Renal Cell Carcinoma in Contemporary Patients. Eur Urol 71(4): 665-673.
Zhao Y, Chang M, Wang R, Xi IL, Chang K, Huang RY et al (2020) Deep Learning Based on MRI for Differentiation of Low- and High-Grade in Low-Stage Renal Cell Carcinoma. J Magn Reson Imaging 52(5): 1542-1549.
Ding J, Xing Z, Jiang Z, Chen J, Pan L, Qiu J, Xing W (2018) CT-based radiomic model predicts high grade of clear cell renal cell carcinoma. Eur J Radiol 103: 51-56.
Shu J, Wen D, Xi Y, Xia Y, Cai Z, Xu W et al (2019) Clear cell renal cell carcinoma: Machine learning-based computed tomography radiomics analysis for the prediction of WHO/ISUP grade. Eur J Radiol 121: 108738.
Xi IL, Zhao Y, Wang R, Chang M, Purkayastha S, Chang K et al (2020) Deep learning to distinguish benign from malignant renal lesions based on routine MR imaging. Clin Cancer Res 26(8): 1944-1952.
Wang W, Cao K, Jin S, Zhu X, Ding J, Peng W (2020) Differentiation of renal cell carcinoma subtypes through MRI-based radiomics analysis. Eur Radiol 30(10): 5738-5747.
Said D, Hectors SJ, Wilck E, Rosen A, Stocker D, Bane O et al (2020) Characterization of solid renal neoplasms using MRI-based quantitative radiomics features. Abdom Radiol 45: 2840-2850.
Farhadi F, Nikpanah M, Paschall AK, Shafiei A, Tadayoni A, Ball MW et al (2020) Clear Cell Renal Cell Carcinoma Growth Correlates with Baseline Diffusion-weighted MRI in Von Hippel-Lindau Disease. Radiology 295(3): 583-590.
Funding
National Cancer Institute (NCI) of the National Institutes of Health (Award Number R03CA249554) and Research Scholar Grant by RSNA Research & Education Foundation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
The study was approved by the Institutional Review Boards from respective institutions.
Informed consent
The informed consent was waived.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Choi, J.W., Hu, R., Zhao, Y. et al. Preoperative prediction of the stage, size, grade, and necrosis score in clear cell renal cell carcinoma using MRI-based radiomics. Abdom Radiol 46, 2656–2664 (2021). https://doi.org/10.1007/s00261-020-02876-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00261-020-02876-x