Meta-Learning Based Interactively Connected Clique U-Net for Quantitative Susceptibility Mapping

Quantitative susceptibility mapping (QSM) is a phase-based magnetic resonance imaging (MRI) technique that quantitatively estimates magnetic susceptibility values of tissues and has shown great potential in clinical practice. However, the ill-posed dipole inversion greatly affects the estimation accuracy of the susceptibility values. In this work, an interactively connected clique U-Net (named ICCU-Net) is proposed to perform the nonlinear mapping from single-echo phase maps to QSM maps. The interactive connection provides hierarchical feature fusions and multi-scale representations for the recovery of detailed tissue and edges, while the embedded clique block further promotes the gradients and information flow. Besides, the time-consuming data acquisition results in small amounts of in-vivo data, which degrades the performance of the deep Learning (DL) based QSM reconstruction algorithm. A novel two-stage meta-learning strategy is further proposed for the ICCU-Net to promote the reconstruction quality with limited in-vivo data. Benefiting from large quantities of self-generated synthetic data, the ICCU-Net effectively learns the nonlinear mapping through multiple meta-tasks as the prior knowledge in the first-stage meta-learning. The learned model is then further improved on the in-vivo data through the second-stage meta-learning instead of being directly applied on them to reduce the distribution differences between the in-vivo and synthetic data. This novel two-stage procedure alleviates the issue of insufficient in-vivo data and provides more accurate reconstructed QSM maps. The experimental results demonstrate that the proposed algorithm outperforms other conventional and DL-based QSM reconstruction algorithms.