Automated Classification of Papillary Renal Cell Carcinoma and Chromophobe Renal Cell Carcinoma Based on a Small Computed Tomography Imaging Dataset Using Deep Learning

Teng Zuo; Yanhua Zheng; Lingfeng He; Tao Chen; Bin Zheng; Song Zheng; Jinghang You; Xiaoyan Li; Rong Liu; Junjie Bai; Shuxin Si; Yingying Wang; Shuyi Zhang; Lili Wang; Jianhui Chen

doi:10.3389/fonc.2021.746750

Automated Classification of Papillary Renal Cell Carcinoma and Chromophobe Renal Cell Carcinoma Based on a Small Computed Tomography Imaging Dataset Using Deep Learning

Front Oncol. 2021 Nov 18:11:746750. doi: 10.3389/fonc.2021.746750. eCollection 2021.

Authors

Teng Zuo¹, Yanhua Zheng¹, Lingfeng He², Tao Chen³, Bin Zheng⁴, Song Zheng¹, Jinghang You⁵, Xiaoyan Li⁶, Rong Liu¹, Junjie Bai¹, Shuxin Si¹, Yingying Wang⁷, Shuyi Zhang⁸, Lili Wang⁴, Jianhui Chen¹

Affiliations

¹ Department of Urology, Fujian Medical University Union Hospital, Fuzhou, China.
² Institute for Empirical Social Science Research, Xi'an Jiaotong University, Xi'an, China.
³ School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China.
⁴ School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, United States.
⁵ Department of Radiology, Fujian Medical University Union Hospital, Fuzhou, China.
⁶ Department of Pathology, Fujian Medical University Union Hospital, Fuzhou, China.
⁷ School of Medicine, Fujian Medical University, Fuzhou, China.
⁸ School of Medicine, Xiamen University, Xiamen, China.

Abstract

Objectives: This study was conducted in order to design and develop a framework utilizing deep learning (DL) to differentiate papillary renal cell carcinoma (PRCC) from chromophobe renal cell carcinoma (ChRCC) using convolutional neural networks (CNNs) on a small set of computed tomography (CT) images and provide a feasible method that can be applied to light devices.

Methods: Training and validation datasets were established based on radiological, clinical, and pathological data exported from the radiology, urology, and pathology departments. As the gold standard, reports were reviewed to determine the pathological subtype. Six CNN-based models were trained and validated to differentiate the two subtypes. A special test dataset generated with six new cases and four cases from The Cancer Imaging Archive (TCIA) was applied to validate the efficiency of the best model and of the manual processing by abdominal radiologists. Objective evaluation indexes [accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and area under the curve (AUC)] were calculated to assess model performance.

Results: The CT image sequences of 70 patients were segmented and validated by two experienced abdominal radiologists. The best model achieved 96.8640% accuracy (99.3794% sensitivity and 94.0271% specificity) in the validation set and 100% (case accuracy) and 93.3333% (image accuracy) in the test set. The manual classification achieved 85% accuracy (100% sensitivity and 70% specificity) in the test set.

Conclusions: This framework demonstrates that DL models could help reliably predict the subtypes of PRCC and ChRCC.

Keywords: CNN—convolutional neural network; ChRCC,·chromophobe-primary renal cell carcinoma; PRCC; cancer image classification; papillary renal cell carcinoma.