An Improved Iterative Neural Network for High-Quality Image-Domain Material Decomposition in Dual-Energy CT

  title={An Improved Iterative Neural Network for High-Quality Image-Domain Material Decomposition in Dual-Energy CT},
  author={Zhipeng Li and Yong Long and Il Yong Chun},
  journal={Medical physics},
PURPOSE Dual-energy computed tomography (DECT) has been widely used in many applications that need material decomposition. Image-domain methods directly decompose material images from high- and low-energy attenuation images, and thus, are susceptible to noise and artifacts on attenuation images. The purpose of this study is to develop an improved iterative neural network (INN) for high-quality image-domain material decomposition in DECT, and to study its properties. METHODS We propose a new… 

Figures and Tables from this paper



Image-Domain Material Decomposition Using an Iterative Neural Network for Dual-Energy CT

Experiments show that the proposed INN architecture for DECT material decomposition greatly improves image decomposition quality compared to a conventional MBID method using an edge-preserving hyperbola regularizer and a state-of-the-art learnedMBID method that uses different pre-learned sparsifying transforms for different materials.

Image Decomposition Algorithm for Dual-Energy Computed Tomography via Fully Convolutional Network

A deep neural net, consisting of a fully convolutional net (FCN) and a fully connected net, is proposed to solve the material decomposition problem and results have shown the strong function fitting ability of the deep neural network.

Pseudo dual energy CT imaging using deep learning-based framework: basic material estimation

A deep learning-based framework to obtain basic material images directly form single energy CT images via cascade deep convolutional neural networks (CD-ConvNet) can help to improve research utility of CT in quantitative imaging, especially in single energyCT.

Momentum-Net for Low-Dose CT Image Reconstruction

Experimental results show that the proposed Momentum-Net architecture significantly improves image reconstruction accuracy, compared to a state-of-the-art noniterative image denoising deep neural network (NN), WavResNet (in LDCT).

Image domain dual material decomposition for dual-energy CT using butterfly network.

A model-based Butterfly network is developed to perform image domain material decomposition for DECT and the decomposition results of digital phantom validate its capability of decomposing two basis materials from DECT images.

DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering

A new method is proposed that combines conventional penalized weighted-least squares (PWLS) estimation with regularization based on a mixed union of learned transforms (MULTRA) model that provides superior material image quality and decomposition accuracy compared to other competing methods.

Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior

An iterative one-step inversion material decomposition algorithm with a Noise2Noise prior that performs promisingly on noise suppression and structure detail recovery is proposed.

Dictionary learning based image-domain material decomposition for spectral CT

The numerical mouse, physical phantom and preclinical experiments are performed to evaluate the performance of the proposed DLIMD in material decomposition accuracy, material image edge preservation and feature recovery.

Image-Domain Material Decomposition for Spectral CT Using a Generalized Dictionary Learning

Both physical phantom and tissue-synthetic phantom experiments demonstrate the proposed GDLIMD method outperforms the DLIMD and direct inversion (DI) methods.

Multi-energy CT decomposition using convolutional neural networks

This work develops CNN-based methods for material decomposition in spectral CT that inherently better exploits spatial and spectral correlations and performs a more robust spectral micro-CT decomposition.