Michael T. McCann, Michael Unser. Published online: January 11, 2019. arXiv:1901.03565 [eess.IV].
In this tutorial, we provide a unified introduction to biomedical image reconstruction, including system modeling and reconstruction via direct, variational, and learning-based methods. Imaging is a critical tool in biological research and medicine, and most imaging systems necessarily use an image-reconstruction algorithm to create an image. While these algorithms have been developed since at least the 1960s, the field has not converged to a single, universally-accepted approach to image reconstruction. In fact, algorithms both old and new have practical applications, and new algorithms often make use of old ones in surprising ways. So, while our introduction to this topic is organized chronologically, our goal is not to provide history; rather, we aim to introduce a toolbox of ideas and algorithms that are useful for working on modern image reconstruction problems.