Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction

TL;DR

This paper introduces a multi-scale wavelet domain residual learning method to effectively reduce artifacts in limited-angle CT images, preserving image details and structures.

Contribution

It proposes a novel multi-scale wavelet domain residual learning architecture specifically designed for artifact compensation in limited-angle CT reconstruction.

Findings

Effectively eliminates artifacts in limited-angle CT images.

Preserves edge and global structures of the images.

Outperforms existing methods in artifact reduction.

Abstract

Limited-angle computed tomography (CT) is often used in clinical applications such as C-arm CT for interventional imaging. However, CT images from limited angles suffers from heavy artifacts due to incomplete projection data. Existing iterative methods require extensive calculations but can not deliver satisfactory results. Based on the observation that the artifacts from limited angles have some directional property and are globally distributed, we propose a novel multi-scale wavelet domain residual learning architecture, which compensates for the artifacts. Experiments have shown that the proposed method effectively eliminates artifacts, thereby preserving edge and global structures of the image.