A material decomposition method for dual-energy CT via dual interactive Wasserstein generative adversarial networks

TL;DR

This paper introduces a novel dual interactive Wasserstein GAN approach to enhance material decomposition in dual-energy CT, effectively reducing noise and artifacts for clearer, more accurate material-specific images.

Contribution

The study presents a data-driven, dual-generator GAN framework with specialized loss functions and a selector to improve material decomposition accuracy in dual-energy CT.

Findings

Significant noise and artifact suppression demonstrated in simulations and real data.

Enhanced preservation of textures and edges in decomposed images.

Outperforms existing methods in accuracy and image quality.

Abstract

Dual-energy computed tomography has great potential in material characterization and identification, whereas the reconstructed material-specific images always suffer from magnified noise and beam hardening artifacts. In this study, a data-driven approach using dual interactive Wasserstein generative adversarial networks is proposed to improve the material decomposition accuracy. Specifically, two interactive generators are used to synthesize the corresponding material images and different loss functions for training the decomposition model are incorporated to preserve texture and edges in the generated images. Besides, a selector is employed to ensure the modelling ability of two generators. The results from both the simulation phantoms and real data demonstrate the advantages of this method in suppressing the noise and beam hardening artifacts.