The peritumoral region may harbor prognostically relevant information. Radiomics enables extraction of subtle imaging features beyond visual assessment, potentially improving outcome prediction in nasopharyngeal carcinoma (NPC). To investigate whether integrating peritumoral radiomic features—alongside intratumoral and clinical data—enhances prediction of overall survival (OS), progression-free survival (PFS), and distant metastasis-free survival (DMFS) in NPC. We retrospectively analyzed 252 NPC patients who received definitive chemoradiotherapy (2010-2019). Gross tumor volumes (GTVs) were manually contoured, and peritumoral regions were created by expanding the GTV boundary (5–20% of in-slice diameter). Radiomic features from both intra- and peritumoral regions were extracted using PyRadiomics. Clinical variables included age, gender, T/N stage, overall stage, and Epstein-Barr virus (EBV) DNA level. Feature selection used intraclass correlation coefficient (ICC), univariate Cox regression, and recursive feature elimination with cross-validation (RFECV). Prognostic models were built using multivariate Cox regression and evaluated with Harrell’s C-index. In EBV-included models, the clinical+intratumoral+peritumoral radiomics model yielded the best performance for OS (C-index = 0.776 ± 0.089; test = 0.729) and DMFS (0.768 ± 0.056; test = 0.654), outperforming clinical-only models (OS: 0.709 ± 0.112; DMFS: 0.733 ± 0.070; p < 0.05). For PFS, clinical+intratumoral radiomics was optimal. Without EBV, peritumoral-inclusive models still enhanced OS and DMFS prediction, while PFS prediction remained reliant on clinical+intratumoral features. Integrating peritumoral radiomics significantly improved NPC prognostication, especially for OS and DMFS, even in the absence of EBV, underscoring its potential for refining risk stratification. • Peritumoral radiomics improved prediction of OS and DMFS in NPC. • Prognostic models remain effective even without EBV data. • Combined clinical with intra-peritumoral models outperformed clinical-only models.
Khongwirotphan et al. (Sun,) studied this question.