Learned Multi-layer Residual Sparsifying Transform Model for Low-dose CT Reconstruction
This work addresses improved image quality in low-dose CT scans for medical imaging applications, representing an incremental advancement over existing sparse representation methods.
The paper tackled low-dose CT reconstruction by proposing a Multi-layer Residual Sparsifying Transform (MRST) model that jointly sparsifies transform domain residuals across layers, and it outperformed conventional methods like FBP and PWLS with edge-preserving regularizers on Mayo Clinic data, especially in preserving subtle details.
Signal models based on sparse representation have received considerable attention in recent years. Compared to synthesis dictionary learning, sparsifying transform learning involves highly efficient sparse coding and operator update steps. In this work, we propose a Multi-layer Residual Sparsifying Transform (MRST) learning model wherein the transform domain residuals are jointly sparsified over layers. In particular, the transforms for the deeper layers exploit the more intricate properties of the residual maps. We investigate the application of the learned MRST model for low-dose CT reconstruction using Penalized Weighted Least Squares (PWLS) optimization. Experimental results on Mayo Clinic data show that the MRST model outperforms conventional methods such as FBP and PWLS methods based on edge-preserving (EP) regularizer and single-layer transform (ST) model, especially for maintaining some subtle details.