Recent Advances in Functional MRI to Predict Treatment Response for Locally Advanced Rectal Cancer

Early response prediction for locally advanced rectal cancer (LARC) provides an opportunity for response-tailored treatment management. The goal of this review is to summarize recent advances in applying functional MRI, such as diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), to predict treatment response for LARC patients, as well as to discuss the associated limitations and future directions. Many recent studies incorporated advanced data analysis methods, such as radiomics and deep learning, to enhance prediction performance. Multi-parametric imaging has also become a trend that utilizes complementary information from each technique. However, there are wide variations in patient enrollment, imaging time points, scan parameters, and treatment response endpoint definitions, which leads to a range of findings among these studies. Moreover, small sample size and lack of independent validation of most studies also weaken conclusions. Functional MRI has been shown as a potential early biomarker for rectal cancer treatment response estimation. To incorporate functional MRI into clinical workflow, future work with large standardized data are warranted.