Background: Recent changes to the standard of care for unresectable stage III NSCLC include chemoradiation followed by consolidative immunotherapy (IO). Pneumonitis is a well-known complication of radiotherapy (RT) and has been increasingly reported in association with IO. Although rare, pneumonitis can cause severe morbidity and possibly death in extreme cases. Differentiating RT and IO-induced pneumonitis (RTP vs IOP) is crucial for acute management and future considerations of individualized treatment. However, the clinical and radiological features of RTP and IOP may be similar and often indistinguishable on computed tomography (CT). Texture-based CT radiomics has previously been used to distinguish benign and malignant nodules on lung CT. In this study, we explore if radiomic features extracted from lung CT can distinguish between RTP and IOP. Methods: From 236 patients with stage III NSCLC who underwent chemoradiation followed by consolidative durvalumab, we identified 110 cases of treatment-related pneumonitis. IOP cases were identified through a retrospective review of electronic medical records and independently verified by a thoracic oncologist using features such as bilateral lung involvement, inflammatory changes outside the field of RT, temporal relationship to IO, and response to treatment. Inflammatory lesions were manually annotated using Slicer 3D. After excluding cases without discernible cause and non-identifiable lung lesions (n = 61), we included 49 cases in the study (RTP n = 20; IOP n = 29). A total of 555 features from Gabor, Laws, Laplace, and Haralick feature families were extracted on a pixel level from post-treatment CT images. A support vector machine (SVM) classifier was trained with the most discriminating features identified by Wilcoxon rank-sum test feature selection method. The classifier performance for distinguishing RTP vs. IOP was assessed by averaging the area under the receiver operating characteristic curve (AUC) values computed over 100 iterations of threefold cross-validation. Results: We identified the top 5 radiomic texture features distinguishing RTP from IOP including Haralick entropy, Haralick info, Laws median, and high- and low-frequency Gabor. Using 3-fold cross-validation, the SVM classifier model built on the radiomic features achieved an AUC of 0.83 (95% confidence interval, 0.78 - 0.86). Conclusions: Pneumonitis is a severe complication of both RT and IO that must be taken into consideration when evaluating future risks of IO-based therapies. The distinction between RTP and IOP remains challenging based on CT findings alone. Radiomic texture features analysis of post-treatment CT images can potentially differentiate RTP from IOP in stage III NSCLC patients who received RT followed by consolidative durvalumab. Additional multi-site independent validation of these quantitative image-based biomarkers is warranted.