A Reliable Prediction Model for Renal Cell Carcinoma Subtype Based on Radiomic Features from 3D Multiphase Enhanced CT Images

Haijie Zhang; Fu Yin; Menglin Chen; Anqi Qi; Zihao Lai; Liyang Yang; Ge Wen

doi:10.1155/2021/6595212

A Reliable Prediction Model for Renal Cell Carcinoma Subtype Based on Radiomic Features from 3D Multiphase Enhanced CT Images

J Oncol. 2021 Sep 21:2021:6595212. doi: 10.1155/2021/6595212. eCollection 2021.

Authors

Haijie Zhang^{1

2}, Fu Yin³, Menglin Chen¹, Anqi Qi¹, Zihao Lai¹, Liyang Yang¹, Ge Wen¹

Affiliations

¹ Medical Imaging Department, Nanfang Hospital, Southern Medical University, No. 1023, South Shatai Road, Baiyun District, Guangzhou 510515, China.
² PET/CT Center, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People's Hospital, No. 3002, West Sungang Road, Futian District, Shenzhen 518052, China.
³ College of Information Engineering, Shenzhen University, No. 3688, Nanhai Road, Nanshan District, Shenzhen 518052, China.

Abstract

Background: This study aimed to develop a prediction model to distinguish renal cell carcinoma (RCC) subtypes.

Methods: The radiomic features (RFs) from 5 different computed tomography (CT) phases were used in the prediction models: noncontrast phase (NCP), corticomedullary phase (CMP), nephrographic phase (NP), excretory phase (EP), and all-phase (ALL-P).

Results: For the ALL-P model, all of the RFs obtained from the 4 single-phase images were combined to 420 RFs. The ALL-P model performed the best of all models, with an accuracy of 0.80; the sensitivity and specificity for clear cell RCC (ccRCC) were 0.85 and 0.83; those for papillary RCC (pRCC) were 0.60 and 0.91; those for chromophobe RCC (cRCC) were 0.66 and 0.91, respectively. Binary classification experiments showed for distinguishing ccRCC vs. not-ccRCC that the area under the receiver operating characteristic curve (AUC) of the ALL-P and CMP models was 0.89, but the overall sensitivity/specificity/accuracy of the ALL-P model was better. For cRCC vs. non-cRCC, the ALL-P model had the best performance.

Conclusions: A reliable prediction model for RCC subtypes was constructed. The performance of the ALL-P prediction model was the best as compared to individual single-phase models and the traditional prediction model.