Radiomics enables the extraction of hidden data from medical images that cannot be detected through a visual examination and, through the development of classification models using machine learning or deep learning techniques seeks to provide diagnosis and treatment prognoses. The use of radiomics to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARCs) using magnetic resonance imaging (MRI) images can support the radiation oncologist's decision-making process to identify patients who may or may not benefit from total mesorectum excision (TME) surgery[1]. While radiomics is based on clinical images acquired at a single time point, delta radiomics studies the temporal variation of radiomic features extracted from a set of images acquired at different times during the course of treatment[2, 3]. This study aims to assess the feasibility of using delta radiomics in a short course of radiotherapy (SCRT) with MR-Linac, as a predictive tool to determine the pCR of LARC patients after neoadjuvant chemoradiotherapy (nCRT).