Dingyue Chang

Dingyue Chang

Auto-generated profile, based on publicly available information

Dingyue Chang

China Academy of Engineering Physics, Institute of Materials, Mianyang, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 June 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
ZLZirong Li
Zirong Li
DCDingyue Chang
Dingyue Chang
ZZZhenxi Zhang
Zhenxi Zhang
FLFulin Luo
Fulin Luo
Qiegen LiuQiegen Liu
Qiegen Liu
WWWeiwen Wu
Weiwen Wu
The multi-source stationary CT, where both the detector and X-ray source are fixed, represents a novel imaging system with high temporal resolution that has garnered significant interest. Limited space within the system restricts the number of X-ray sources, leading to sparse-view CT imaging challenges. Recent diffusion models for reconstructing sparse-view CT have generally focused separately on sinogram or image domains. Sinogram-centric models effectively estimate missing projections but may introduce artifacts, lacking mechanisms to ensure image correctness. Conversely, image-domain models, while capturing detailed image features, often struggle with complex data distribution, leading to inaccuracies in projections. Addressing these issues, the Dual-domain Collaborative Diffusion Sampling (DCDS) model integrates sinogram and image domain diffusion processes for enhanced sparse-view reconstruction. This model combines the strengths of both domains in an optimized mathematical framework. A collaborative diffusion mechanism underpins this model, improving sinogram recovery and image generative capabilities. This mechanism facilitates feedback-driven image generation from the sinogram domain and uses image domain results to complete missing projections. Optimization of the DCDS model is further achieved through the alternative direction iteration method, focusing on data consistency updates. Extensive testing, including numerical simulations, real phantoms, and clinical cardiac datasets, demonstrates the DCDS model’s effectiveness. It consistently outperforms various state-of-the-art benchmarks, delivering exceptional reconstruction quality and precise sinogram.

6 November 2023 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
XGXiaodong Guo
Xiaodong Guo
YLYonghui Li
Yonghui Li
DCDingyue Chang
Dingyue Chang
PHPeng He
Peng He
PFPeng Feng
Peng Feng
WWWeiwen Wu
Weiwen Wu
Spectral computed tomography based on a photon-counting detector (PCD) attracts more and more attentions since it has the capability to provide more accurate identification and quantitative analysis for biomedical materials. The limited number of photons within narrow energy bins leads to imaging results of low signal-noise ratio. The existing supervised deep reconstruction networks for CT reconstruction are difficult to address these challenges because it is usually impossible to acquire noise-free clinical images with clear structures as references. In this paper, we propose an iterative deep reconstruction network to synergize unsupervised method and data priors into a unified framework, named as Spectral2Spectral. Our Spectral2Spectral employs an unsupervised deep training strategy to obtain high-quality images from noisy data in an end-to-end fashion. The structural similarity prior within image-spectral domain is refined as a regularization term to further constrain the network training. The weights of neural network are automatically updated to capture image features and structures within the iterative process. Three large-scale preclinical datasets experiments demonstrate that the Spectral2spectral reconstructs better image quality than other the state-of-the-art methods.

30 April 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
JZJianjia Zhang
Jianjia Zhang
HMHaiyang Mao
Haiyang Mao
DCDingyue Chang
Dingyue Chang
HYHengyong Yu
Hengyong Yu
WWWeiwen Wu
Weiwen Wu
DSDinggang Shen
Dinggang Shen
Metal artifact reduction (MAR) is important for clinical diagnosis with CT images. The existing state-of-the-art deep learning methods usually suppress metal artifacts in sinogram or image domains or both. However, their performance is limited by the inherent characteristics of the two domains, i.e., the errors introduced by local manipulations in the sinogram domain would propagate throughout the whole image during backprojection and lead to serious secondary artifacts, while it is difficult to distinguish artifacts from actual image features in the image domain. To alleviate these limitations, this study analyzes the desirable properties of wavelet transform in-depth and proposes to perform MAR in the wavelet domain. First, wavelet transform yields components that possess spatial correspondence with the image, thereby preventing the spread of local errors to avoid secondary artifacts. Second, using wavelet transform could facilitate identification of artifacts from image since metal artifacts are mainly high-frequency signals. Taking these advantages of the wavelet transform, this paper decomposes an image into multiple wavelet components and introduces multi-perspective regularizations into the proposed MAR model. To improve the transparency and validity of the model, all the modules in the proposed MAR model are designed to reflect their mathematical meanings. In addition, an adaptive wavelet module is also utilized to enhance the flexibility of the model. To optimize the model, an iterative algorithm is developed. The evaluation on both synthetic and real clinical datasets consistently confirms the superior performance of the proposed method over the competing methods.

25 July 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XGXiaodong Guo
Xiaodong Guo
WWWeiwen Wu
Weiwen Wu
XDXiaojiao Duan
Xiaojiao Duan
HYHaijun Yu
Haijun Yu
DCDingyue Chang
Dingyue Chang
KAKang An
Kang An
In practice, cone-beam computed tomography (CT) images are usually tarnished by ring artifacts. To address this problem, in this article, we proposed a ring-artifact removal technique based on the nonlinear deviation correction of pixel response for flat panel detector (FPD), named Nonlinear Deviation CorrecTion (NDCT). Our proposed NDCT is a two-point fitting correction method of the local response from mean projection images. Its advantages lie in the following three aspects. First, it obtains correction coefficients by solving the correction equations based on the mean projection images without additional scanning, which improves efficiency. Second, it corrects all pixels of FPD at the same time, which eliminates the inconsistency of adjacent pixels and then the ring artifact within the 3-D CT image can be corrected. Third, the calculation is very simple so the correction speed is fast, which further improves efficiency in practice. Both numerical and real experiments showed that our NDCT method achieved excellent performance and fast speed in ring-artifact removal.

1 July 2019 in Geophysics
Verified
Journal Article
Closed access
DCDingyue Chang
Dingyue Chang
CZCai Zhang
Cai Zhang
THTianyue Hu
Tianyue Hu
DWDan Wang
Dan Wang
Moveout correction for irregular topography has been a longstanding challenge in processing seismic exploration data. Irregular topography usually results in large moveout among traces, a low signal-to-noise ratio (S/N), and difficulty in modeling near-surface velocities. Conventional normal moveout (NMO) corrections and elevation static methods are imprecise and tend to introduce significant errors for large offsets. Over the past two decades, several multiparameter time corrections and stacking techniques to reduce noise and improve resolution have been proposed in place of the classic NMO and common-midpoint stack. These include the common-reflection-surface (CRS), common-offset CRS, nonhyperbolic CRS, implicit CRS, multifocusing (MF), irregular surface MF (IS-MF), spherical MF (SMF), and common-offset MF methods. Various CRS-type operators that consider the top-surface topography have been proposed. For MF-type operators, only IS-MF can be applied directly to the irregular topography with no elevation statics required. In this study, we have developed a new MF formulation, modifying the SMF method to consider nonzero elevations of sources and receivers and we corrected moveout of nonplanar data directly without prior elevation static corrections. The proposed extension combines the sensitivity to spherical reflectors of SMF with the applicability of the IS-MF method to irregular topography. We investigated the behavior of the new operator using a physical model data set and compared the results with those from the conventional IS-MF method. The results revealed that the new operator is more robust over a wide range of source and receiver elevations and has advantages on strongly curved interfaces. We also confirmed the potential of the proposed approach by comparing stacking results for a real-land data set with a low S/N.

2 April 2024 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
ZLZirong Li
Zirong Li
KAKang An
Kang An
HYHengyong Yu
Hengyong Yu
FLFulin Luo
Fulin Luo
JPJiayi Pan
Jiayi Pan
DCDingyue Chang
Dingyue Chang
Objective . Computed Tomography (CT) has been widely used in industrial high-resolution non-destructive testing. However, it is difficult to obtain high-resolution images for large-scale objects due to their physical limitations. The objective is to develop an improved super-resolution technique that preserves small structures and details while efficiently capturing high-frequency information. Approach . The study proposes a new deep learning based method called spectrum learning (SPEAR) network for CT images super-resolution. This approach leverages both global information in the image domain and high-frequency information in the frequency domain. The SPEAR network is designed to reconstruct high-resolution images from low-resolution inputs by considering not only the main body of the images but also the small structures and other details. The symmetric property of the spectrum is exploited to reduce weight parameters in the frequency domain. Additionally, a spectrum loss is introduced to enforce the preservation of both high-frequency components and global information. Main results . The network is trained using pairs of low-resolution and high-resolution CT images, and it is fine-tuned using additional low-dose and normal-dose CT image pairs. The experimental results demonstrate that the proposed SPEAR network outperforms state-of-the-art networks in terms of image reconstruction quality. The approach successfully preserves high-frequency information and small structures, leading to better results compared to existing methods. The network’s ability to generate high-resolution images from low-resolution inputs, even in cases of low-dose CT images, showcases its effectiveness in maintaining image quality. Significance . The proposed SPEAR network’s ability to simultaneously capture global information and high-frequency details addresses the limitations of existing methods, resulting in more accurate and informative image reconstructions. This advancement can have substantial implications for various industries and medical diagnoses relying on accurate imaging.