Quantitative susceptibility mapping (QSM) involves acquisition and reconstruction of a series of images at multi-echo time points to estimate tissue field, which prolongs scan time and requires specific reconstruction technique. In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM. Our approach involves optimizing a Cartesian multi-echo k-space sampling pattern with a deep reconstruction network. Next, this optimized sampling pattern was implemented in an mGRE sequence using Cartesian fan-beam k-space segmenting and ordering for prospective scans. Furthermore, we propose to insert a recurrent temporal feature fusion module into the reconstruction network to capture signal redundancies along echo time. Our ablation studies show that both the optimized sampling pattern and proposed reconstruction strategy help improve the quality of the multi-echo image reconstructions. Generalization experiments show that LARO is robust on the test data with new pathologies and different sequence parameters. Our code is available at https://github.com/Jinwei1209/LARO-QSM.git.
Background/Objectives: Liver fibrosis, if left untreated, can lead to cirrhosis and cancer. The current standard liver biopsy for fibrosis staging is invasive and prone to risks of complication. The objective of this study was to develop a new noninvasive method to quantify fibrosis using diamagnetic susceptibility sources generated from multi-echo gradient echo (mGRE) data with both magnitude decay R2* modeling and phase QSM modeling. Methods: mGRE data of ex vivo liver explants was processed with fat–water separation and then susceptibility source separation. Negative susceptibility was used to measure diamagnetic fibrosis. In 20 formalin-fixed liver explant sections, negative susceptibility maps were compared with other MRI parameters against pathology for fibrosis staging. Results: The correlation between the negative susceptibility sources and the fibrosis stages was evaluated with Spearman coefficients. Negative susceptibility differentiated (i) no or mild fibrosis (stages F0 to F1) from moderate-to-advanced fibrosis (stages F2 to F3; p = 0.0025), (ii) stages F2 to F3 from cirrhosis (stage F4; p = 0.021), and (iii) no-to-moderate fibrosis (stages F0 to F2) from advanced fibrosis or cirrhosis (stages F3 to F4) with a sensitivity of 90%, a specificity of 90%, and a 0.88 Receiver Operating Characteristic Area Under the Curve (AUC) (p = 0.0017). Conclusions: For staging fibrosis, negative susceptibility was superior to other MRI parameters, including R2*, QSM, and PDFF. Negative susceptibility sources were positively correlated with the fibrosis stage (r = 0.60). Negative susceptibility could be valuable for MRI staging in liver fibrosis.