LightGAN-LD: Lightweight GAN for Low-Dose CT Reconstruction
Abstract
This repository contains the implementation of LightGAN-LD, a lightweight generative adversarial network for efficient low-dose CT reconstruction using sinogram encoding and edge-aware learning. The code supports training and evaluation on the LoDoPaB-CT and NIH-AAPM-Mayo datasets.
Fields of Study & Subjects
Medical Imaging Techniques and Applications
Image and Signal Denoising Methods
Generative Adversarial Networks and Image Synthesis
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 5 March 2026
- Language
- EN