Computed Tomography Radiomics for Predicting Pathological Grade of Renal Cell Carcinoma

• Main Authors: 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
• Format: Article
• Language: English
• Published: Frontiers Media S.A. 2021-01-01
• Series: Frontiers in Oncology
• Subjects: radiomics; clear cell renal cell carcinoma; computed tomography (CT); machine learning; predictive modeling
• Online Access: https://www.frontiersin.org/articles/10.3389/fonc.2020.570396/full

BackgroundClear 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.MethodsPatients 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.ResultsA 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.ConclusionWe 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.