Accurate segmentation of the prostate gland in magnetic resonance imaging (MRI) is important for the early detection and treatment of prostate cancer. Manual segmentation is time-consuming and prone to interobserver variability. This study evaluates and compares two deep learning models, U-Net and E-Net, for automated prostate segmentation using axial T2-weighted MRI scans. Both models were trained and validated using a five-fold cross-validation approach, and tested on a hold-out dataset. Performance was assessed using metrics such as Dice Similarity Coefficient (DSC), precision, recall, and surface distance measures. E-Net achieved superior results with a mean DSC of 81.61%, outperforming U-Net’s 77.53%, while also demonstrating significantly lower computational complexity and faster inference times. Despite the performance gap, testing showed statistically significant difference between the models. These findings highlight the potential of lightweight deep learning architectures, particularly E-Net, for accurate and efficient prostate segmentation in clinical settings.