Optimization-Based Deep learning methods for Magnetic Resonance Imaging Reconstruction and Synthesis
This work addresses MRI reconstruction and synthesis problems for medical imaging, with incremental extensions across multiple parts.
The dissertation tackled MRI reconstruction and synthesis by developing nonconvex variational models and optimization-based deep learning methods, resulting in improved accuracy and robustness for compressed sensing and calibration-free fast parallel MRI.
This dissertation is devoted to provide advanced nonconvex nonsmooth variational models of (Magnetic Resonance Image) MRI reconstruction, efficient learnable image reconstruction algorithms and parameter training algorithms that improve the accuracy and robustness of the optimization-based deep learning methods for compressed sensing MRI reconstruction and synthesis. The first part introduces a novel optimization based deep neural network whose architecture is inspired by proximal gradient descent for solving a variational model. The second part is a substantial extension of the preliminary work in the first part by solving the calibration-free fast pMRI reconstruction problem in a discrete-time optimal control framework. The third part aims at developing a generalizable Magnetic Resonance Imaging (MRI) reconstruction method in the meta-learning framework. The last part aims to synthesize target modality of MRI by using partially scanned k-space data from source modalities instead of fully scanned data that is used in the state-of-the-art multimodal synthesis.