Model Augmented Deep Neural Networks for Medical Image Reconstruction Problems

Abstract

Solving an ill-posed inverse problem is difficult because it doesn't have a unique solution. In practice, for some important inverse problems, the conventional methods, e.g. ordinary least squares and iterative methods, cannot provide a good estimate. For example, for single image super-resolution and CT reconstruction, the results of these conventional methods cannot satisfy the requirements of these applications. While having more computational resources and high-quality data, researchers try to use machine-learning-based methods, especially deep learning to solve these ill-posed problems. In this dissertation, a model augmented recursive neural network is proposed as a general inverse problem method to solve these difficult problems. In the dissertation, experiments show the satisfactory performance of the proposed method for single image super-resolution, CT reconstruction, and metal artifact reduction.