Two-layer clustering-based sparsifying transform learning for low-dose CT reconstruction

TL;DR

This paper introduces a novel two-layer clustering-based sparsifying transform model for low-dose CT reconstruction, improving image quality by effectively removing artifacts through learned priors.

Contribution

It proposes a new two-layer clustering-based transform model (MCST2) for LDCT, incorporating learned sparsifying filters for better artifact removal.

Findings

Outperforms recent schemes in LDCT reconstruction

Demonstrates superior artifact removal and image quality

Validates effectiveness through experimental results

Abstract

Achieving high-quality reconstructions from low-dose computed tomography (LDCT) measurements is of much importance in clinical settings. Model-based image reconstruction methods have been proven to be effective in removing artifacts in LDCT. In this work, we propose an approach to learn a rich two-layer clustering-based sparsifying transform model (MCST2), where image patches and their subsequent feature maps (filter residuals) are clustered into groups with different learned sparsifying filters per group. We investigate a penalized weighted least squares (PWLS) approach for LDCT reconstruction incorporating learned MCST2 priors. Experimental results show the superior performance of the proposed PWLS-MCST2 approach compared to other related recent schemes.