Key points are not available for this paper at this time.
PURPOSE: This study aims to develop an integrated model based on dual-energy CT (DECT) radiomic features to predict vascular maturity and progression-free survival (PFS) in patients with clear cell renal cell carcinoma (ccRCC). METHODS: A total of 87 ccRCC patients who underwent resection were randomly divided into training (n = 60) and validation (n = 27) groups at a 7:3 ratio. Radiomics models (single/multi-energy sequences), a clinical model, and a combined model were developed to predict vascular maturity (CD34+/α-SMA+ cells). Additionally, 17 patients were recruited from Center II as an external validation cohort for the multi-energy sequence models. A nomogram combining the radiomic score (Rad-score) and clinical features was constructed to visually predict patients’ PFS. Kaplan-Meier survival analysis assessed PFS differences between high and low CD34+/α-SMA+ cell groups. RESULTS: The median values of CD34+/α-SMA+ cells served as the cutoff for vascular maturity classification. The combined model demonstrated excellent performance, achieving an AUC of 0.967 in the validation set and 0.764 in the external validation set. Among the radiomics models, the multi-energy sequences model performed best, with an AUC of 0.833 in the validation set and 0.736 in the external validation set. Kaplan-Meier survival analysis revealed statistically significant PFS differences between CD34+/α-SMA+ cell groups. CONCLUSIONS: The combined model integrating Rad-score and clinical features showed promising predictive ability for assessing vascular maturity and PFS between CD34+/α-SMA+ groups in patients with ccRCC.
Li et al. (Mon,) studied this question.