AI and Cancer Research ── Kidney ── 2026-10-20
Kidney cancer: treatment, trials and AI
- 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.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-09, retrieved 2026-10-10; not the official Clarivate IF)Reference: Liu Y, Wang K, Zhang Y, Liu J, Xi Z, Wang X, et al. Differentiating Xp11.2/TFE3 translocation renal cell carcinoma from clear cell carcinoma: performance of a radiomics model. BMC Cancer. 2026 Jul 22;26(1):1247. doi:10.1186/s12885-026-16463-8.Checked: Abstract only