This study aimed to predict therapeutic response to antifibrotic agents in patients with idiopathic pulmonary fibrosis (IPF) using radiomic analysis of high-resolution computed tomography (HRCT) images. Two cohorts of IPF patients were retrospectively analyzed, with training (n=26) and external validation (n=9) sets. Radiomic features were extracted from pretreatment HRCT images, and a predictive model for disease progression (PD) was developed. Univariate and multivariate analyses revealed that the sum entropy was an independent predictor of PD. A combined model using sum entropy and ground-glass opacity percentage (GGO%) improved predictive performance. The accuracy of the combined model was 88.46% in the training set and 66.67% in the validation set. This radiomics-based model shows promise in predicting therapeutic response in IPF patients, potentially aiding treatment decisions. Further research on larger datasets is warranted to validate these findings. The study utilized advanced computational algorithms and Coreline Soft's AI software, AVIEW, for automated analysis of CT images to enhance prediction accuracy.