Affine Transformation Edited and Refined Deep Neural Network for Quantitative Susceptibility Mapping
This work addresses a domain-specific problem for medical imaging researchers and clinicians by improving QSM reconstruction robustness and speed, though it is incremental as it builds on existing deep learning methods with novel architectural tweaks.
The paper tackled the problem of deep neural networks degrading in performance with mismatched sequence parameters like acquisition orientation and spatial resolution in Quantitative Susceptibility Mapping (QSM), proposing an AFTER-QSM network that achieved robust reconstruction up to 0.6 mm isotropic resolution, leading to best image quality in simulations and reduced artifacts in in-vivo experiments.
Deep neural networks have demonstrated great potential in solving dipole inversion for Quantitative Susceptibility Mapping (QSM). However, the performances of most existing deep learning methods drastically degrade with mismatched sequence parameters such as acquisition orientation and spatial resolution. We propose an end-to-end AFfine Transformation Edited and Refined (AFTER) deep neural network for QSM, which is robust against arbitrary acquisition orientation and spatial resolution up to 0.6 mm isotropic at the finest. The AFTER-QSM neural network starts with a forward affine transformation layer, followed by an Unet for dipole inversion, then an inverse affine transformation layer, followed by a Residual Dense Network (RDN) for QSM refinement. Simulation and in-vivo experiments demonstrated that the proposed AFTER-QSM network architecture had excellent generalizability. It can successfully reconstruct susceptibility maps from highly oblique and anisotropic scans, leading to the best image quality assessments in simulation tests and suppressed streaking artifacts and noise levels for in-vivo experiments compared with other methods. Furthermore, ablation studies showed that the RDN refinement network significantly reduced image blurring and susceptibility underestimation due to affine transformations. In addition, the AFTER-QSM network substantially shortened the reconstruction time from minutes using conventional methods to only a few seconds.