MRI and CT are the two most widely used medical imaging techniques. Often, doctors need images from both modalities to diagnose conditions accurately and plan treatments like radiation therapy. However, using both MRI and CT can be costly, and it often results in misaligned images. A practical alternative is to use computational methods to convert images from one modality to another—particularly converting MRI images into CT images. In this study, we explore a deep learning approach using diffusion models and score-matching techniques to address this challenge. Specifically, we adapt denoising diffusion probabilistic models and score-matching strategies, apply four different sampling methods, and compare their performance with that of traditional models like generative adversarial networks (GANs) and convolutional neural networks (CNNs). Our results show that diffusion and score-matching models generate synthetic CT images with higher quality than CNN and GAN approaches. We also assess the uncertainty in these models using Monte Carlo simulations and further improve the final image quality by averaging the Monte Carlo outputs. Overall, our research suggests that diffusion and score-matching models not only rival CNNs and GANs in generating cross-modality medical images but also offer a more mathematically grounded and reliable framework.