PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction
This work addresses the problem of reproducible tissue parameter measurement in MRI for medical imaging applications, representing an incremental improvement by better leveraging prior physics knowledge in learned methods.
The paper tackles the challenge of reconstructing quantitative MRI parameter maps from undersampled raw data by proposing PINQI, an end-to-end physics-informed neural network that integrates signal and acquisition models with learned regularization, achieving superior performance over existing methods in simulated and real-world datasets.
Quantitative Magnetic Resonance Imaging (qMRI) enables the reproducible measurement of biophysical parameters in tissue. The challenge lies in solving a nonlinear, ill-posed inverse problem to obtain the desired tissue parameter maps from acquired raw data. While various learned and non-learned approaches have been proposed, the existing learned methods fail to fully exploit the prior knowledge about the underlying MR physics, i.e. the signal model and the acquisition model. In this paper, we propose PINQI, a novel qMRI reconstruction method that integrates the knowledge about the signal, acquisition model, and learned regularization into a single end-to-end trainable neural network. Our approach is based on unrolled alternating optimization, utilizing differentiable optimization blocks to solve inner linear and non-linear optimization tasks, as well as convolutional layers for regularization of the intermediate qualitative images and parameter maps. This design enables PINQI to leverage the advantages of both the signal model and learned regularization. We evaluate the performance of our proposed network by comparing it with recently published approaches in the context of highly undersampled $T_1$-mapping, using both a simulated brain dataset, as well as real scanner data acquired from a physical phantom and in-vivo data from healthy volunteers. The results demonstrate the superiority of our proposed solution over existing methods and highlight the effectiveness of our method in real-world scenarios.