A Green Learning Approach to LDCT Image Restoration

2026-02-23

AI Summary

This work addresses the challenge of low-dose computed tomography (LDCT) image degradation caused by noise and artifacts, which significantly impairs clinical diagnosis. To overcome this, the authors propose a lightweight image restoration framework grounded in Green Learning (GL), eschewing the heavy reliance of conventional deep learning on large-scale parameters and extensive computational resources. The proposed method emphasizes mathematical interpretability, efficient inference, and minimal memory consumption while maintaining state-of-the-art restoration performance. By substantially reducing model size and accelerating inference speed, the framework achieves a unified balance between high energy efficiency and transparent, interpretable modeling—offering a practical and sustainable solution for medical image enhancement in resource-constrained settings.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• LDCT
• image restoration
• noise
• artifacts
• medical image

Innovation

• Green Learning
• LDCT image restoration
• computational efficiency
• mathematical transparency
• lightweight model