Differentiating Xp11.2/TFE3 translocation renal cell carcinoma from clear cell carcinoma: performance of a radiomics model.
5 affiliations
- 1Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, China.
- 2Beijing Smart Tree Medical Technology Co., Ltd, 24, Huangsi Avenue, Xicheng District, Beijing, 100035, China.
- 3Department of Urology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, China.
- 4Institute of Urology, Beijing Key Laboratory of Urogenital Diseases (Male) Molecular Diagnosis and Treatment Center, Peking University, National Urological Cancer Center, No. 8 Xishiku Street., Xicheng District, Beijing, 100034, China.
- 5Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, China. [email protected].
Abstract
Purpose
This study aims to assess the computed tomography (CT) features of transcription factor E3 gene fusion renal cell carcinoma (TFE3-RCC) and develop a radiomics-based model for preoperative discrimination between TFE3-RCCs and clear cell renal cell carcinomas (ccRCCs).Methods
A total of 34 pathologically confirmed TFE3-RCC and 98 ccRCC cases with preoperative renal CT were enrolled. Subjective image analysis was performed to determine the CT parameters that can distinguish TFE3-RCCs from ccRCCs. A random forest classifier was evaluated through 5-fold cross-validation to establish the radiomics model. Diagnostic performance was assessed using receiver operating characteristic (ROC) curve analysis.Results
Patients with TFE3-RCC were significantly younger (36.2 ± 14.4 vs. 56.8 ± 13.5 years, P < 0.001). Ten of the 34 TFE3-RCCs had calcification, whereas only four in the ccRCC group did (29.4% vs. 4.1%, P < 0.001). Additionally, the TOC enhancement ratio in the corticomedullary phase were significantly lower in the TFE3-RCC group compared with the ccRCC group (0.61 ± 0.11 vs. 0.90 ± 0.13, p < 0.001). The random forest classifier achieved stable performance with robust cross-validation metrics (AUC = 0.82 ± 0.17, accuracy = 85% ± 13%).Conclusion
The CT radiomics model exhibits favorable diagnostic performance for noninvasively differentiating TFE3-RCC from ccRCC, supporting its potential utility in preoperative personalized management of renal masses.
Related
- A multimodal MRI radiomics sonata for differentiating small renal masses: a two-center retrospective study.
- TFE3 fusions drive expression of CD44 and SPP1 in Translocation Renal Cell Carcinoma
- Development and validation of a multiphase CT radiomics-based machine learning model for prognostic prediction in sarcomatoid renal cell carcinoma
- Multimodal CT radiomics and 2.5D deep learning for preoperative grading of clear cell renal cell carcinoma in older patients: a multicenter study
- Multiparametric MRI-based radiomics for differentiating HER2-negative, HER2-low, and HER2-positive breast cancer
BibTeX
@article{liu2026differentiating,
title = {{Differentiating Xp11.2/TFE3 translocation renal cell carcinoma from clear cell carcinoma: performance of a radiomics model.}},
author = {Yi Liu and Kexin Wang and Yaofeng Zhang and Jiangtao Liu and Zuqiang Xi and Xiangpeng Wang and Yanfei Yu and Xiaoying Wang},
journal = {BMC cancer},
year = {2026},
month = jul,
doi = {10.1186/s12885-026-16463-8},
url = {https://europepmc.org/article/MED/42894154},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Differentiating Xp11.2/TFE3 translocation renal cell carcinoma from clear cell carcinoma: performance of a radiomics model.
AU - Yi Liu
AU - Kexin Wang
AU - Yaofeng Zhang
AU - Jiangtao Liu
AU - Zuqiang Xi
AU - Xiangpeng Wang
AU - Yanfei Yu
AU - Xiaoying Wang
PY - 2026
DA - 2026/07/01
JO - BMC cancer
DO - 10.1186/s12885-026-16463-8
UR - https://europepmc.org/article/MED/42894154
AB - Purpose This study aims to assess the computed tomography (CT) features of transcription factor E3 gene fusion renal cell carcinoma (TFE3-RCC) and develop a radiomics-based model for preoperative discrimination between TFE3-RCCs and clear cell renal cell carcinomas (ccRCCs).Methods A total of 34 pathologically confirmed TFE3-RCC and 98 ccRCC cases with preoperative renal CT were enrolled. Subjective image analysis was performed to determine the CT parameters that can distinguish TFE3-RCCs from ccRCCs. A random forest classifier was evaluated through 5-fold cross-validation to establish the radiomics model. Diagnostic performance was assessed using receiver operating characteristic (ROC) curve analysis.Results Patients with TFE3-RCC were significantly younger (36.2 ± 14.4 vs. 56.8 ± 13.5 years, P < 0.001). Ten of the 34 TFE3-RCCs had calcification, whereas only four in the ccRCC group did (29.4% vs. 4.1%, P < 0.001). Additionally, the TOC enhancement ratio in the corticomedullary phase were significantly lower in the TFE3-RCC group compared with the ccRCC group (0.61 ± 0.11 vs. 0.90 ± 0.13, p < 0.001). The random forest classifier achieved stable performance with robust cross-validation metrics (AUC = 0.82 ± 0.17, accuracy = 85% ± 13%).Conclusion The CT radiomics model exhibits favorable diagnostic performance for noninvasively differentiating TFE3-RCC from ccRCC, supporting its potential utility in preoperative personalized management of renal masses.
SN - 1471-2407
ER -