Deep learning-based segmentation and subtype prediction of renal cell carcinoma on contrast-enhanced CT
5 affiliations
- 1Department of Urology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- 2Department of Urology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
- 3Department of Pathology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- 4Department of Urology, The Fifth Affiliated Hospital of Guangzhou Medical University, Guangzhou, China
- 5Department of Urology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, China
Abstract
Accurate preoperative discrimination of renal cell carcinoma (RCC) subtypes is critical for treatment stratification. We aimed to develop and validate an automated deep learning system for simultaneous tumor segmentation and histopathological subtyping using multicenter contrast-enhanced CT (CECT) imaging. To this end, we constructed a two-stage system comprising separate segmentation and classification models. The segmentation model was trained on 245 scans from Nanfang Hospital and 210 from the KiTS19 public dataset. The classification model was developed and validated on a total of 750 patients, comprising an internal cohort from Nanfang Hospital (553 patients; 328 training, 112 validation, 113 testing) and two external validation cohorts: one from Beijing Tongren Hospital (n = 111) and another combined from two other centers (n = 86). The model demonstrated strong generalizability for discriminating clear cell RCC, with AUCs of 0.878 (internal validation), 0.892 (internal testing), 0.911 (external set Ⅰ), and 0.892 (external set Ⅱ). The model’s computational efficiency reached 0.24 s per file and reduced FLOPs by four times compared to conventional 3D CNNs. This study validates the efficiency and clinical applicability of the YOLOv11 framework for RCC subtyping. Future efforts should integrate prospective data and multimodal imaging to enhance sensitivity for small lesions.
Related
- Prediction of gross extrathyroidal extension in papillary thyroid carcinoma using a deep learning radiomics model based on post-processing techniques for multi-phase contrast-enhanced MRI images
- Interpretable machine learning for preoperative prediction of WHO/ISUP grade in clear cell renal cell carcinoma using contrast-enhanced CT–derived extracellular volume fraction
- Predicting microvascular invasion in hepatocellular carcinoma using contrast-enhanced CT-based deep learning models: a comparative study of transformer, CNN, and MIL
- Dynamic contrast-enhanced MRI deep learning model combined with clinical model for noninvasive differentiation of hepatocellular carcinoma from mass-forming intrahepatic cholangiocarcinoma
- AdaSwitch3D: Reliability-Aware Human-in-the-Loop Artificial Intelligence for Breast Tumor Segmentation in Dynamic Contrast-Enhanced MRI Across Unseen Centers
BibTeX
@article{chen2026deep,
title = {{Deep learning-based segmentation and subtype prediction of renal cell carcinoma on contrast-enhanced CT}},
author = {Xiaoliang Chen and Yingwei Xie and Zehai Huang and Bihong Xu and Fengjin Zhao and Wenbin Guo and Gan Mo and Haoxu Wu and Peidan Peng and Zhiyong Zhang and Xiangbo Zeng and Yuanchao Zhu and Jiawei Zhou and Yishan Zhang and Wanlong Tan and Hao Ping and Zaosong Zheng},
journal = {NPJ Precision Oncology},
year = {2026},
month = jul,
doi = {10.1038/s41698-026-01609-5},
url = {https://doi.org/10.1038/s41698-026-01609-5},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Deep learning-based segmentation and subtype prediction of renal cell carcinoma on contrast-enhanced CT
AU - Xiaoliang Chen
AU - Yingwei Xie
AU - Zehai Huang
AU - Bihong Xu
AU - Fengjin Zhao
AU - Wenbin Guo
AU - Gan Mo
AU - Haoxu Wu
AU - Peidan Peng
AU - Zhiyong Zhang
AU - Xiangbo Zeng
AU - Yuanchao Zhu
AU - Jiawei Zhou
AU - Yishan Zhang
AU - Wanlong Tan
AU - Hao Ping
AU - Zaosong Zheng
PY - 2026
DA - 2026/07/14
JO - NPJ Precision Oncology
DO - 10.1038/s41698-026-01609-5
UR - https://doi.org/10.1038/s41698-026-01609-5
AB - Accurate preoperative discrimination of renal cell carcinoma (RCC) subtypes is critical for treatment stratification. We aimed to develop and validate an automated deep learning system for simultaneous tumor segmentation and histopathological subtyping using multicenter contrast-enhanced CT (CECT) imaging. To this end, we constructed a two-stage system comprising separate segmentation and classification models. The segmentation model was trained on 245 scans from Nanfang Hospital and 210 from the KiTS19 public dataset. The classification model was developed and validated on a total of 750 patients, comprising an internal cohort from Nanfang Hospital (553 patients; 328 training, 112 validation, 113 testing) and two external validation cohorts: one from Beijing Tongren Hospital (n = 111) and another combined from two other centers (n = 86). The model demonstrated strong generalizability for discriminating clear cell RCC, with AUCs of 0.878 (internal validation), 0.892 (internal testing), 0.911 (external set Ⅰ), and 0.892 (external set Ⅱ). The model’s computational efficiency reached 0.24 s per file and reduced FLOPs by four times compared to conventional 3D CNNs. This study validates the efficiency and clinical applicability of the YOLOv11 framework for RCC subtyping. Future efforts should integrate prospective data and multimodal imaging to enhance sensitivity for small lesions.
SN - 2397-768X
ER -