A Green Learning Approach to LDCT Image Restoration

TL;DR

This paper introduces a green learning approach for LDCT image restoration that achieves high performance with greater efficiency and transparency compared to traditional deep learning methods.

Contribution

The paper presents a novel green learning methodology for LDCT image restoration, emphasizing transparency, efficiency, and competitive performance over existing deep learning techniques.

Findings

State-of-the-art restoration performance achieved

Smaller model size and lower inference complexity

High transparency and computational efficiency

Abstract

This work proposes a green learning (GL) approach to restore medical images. Without loss of generality, we use low-dose computed tomography (LDCT) images as examples. LDCT images are susceptible to noise and artifacts, where the imaging process introduces distortion. LDCT image restoration is an important preprocessing step for further medical analysis. Deep learning (DL) methods have been developed to solve this problem. We examine an alternative solution using the Green Learning (GL) methodology. The new restoration method is characterized by mathematical transparency, computational and memory efficiency, and high performance. Experiments show that our GL method offers state-of-the-art restoration performance at a smaller model size and with lower inference complexity.