Xing Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xing Zhao has a total of 94 co-authors. Here are the top co-authors by number of shared publications:
Huitao Zhang
School of Mathematical Sciences, Capital Normal University, Beijing, 100048, China
7 shared publications- Ping Yang
Institute of Nuclear and New Energy Technology, Collaborative Innovation Center of Advanced Nuclear Energy Technology, Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education, Tsinghua University, Beijing, China
7 shared publications - Yining Zhu
School of Mathematical Sciences, Capital Normal University, Beijing, China
7 shared publications Shusen Zhao
National Center for Applied Mathematics Shenzhen, Southern University of Science and Technology, China
6 shared publications- Genwei Ma
Capital Normal University
5 shared publications - Ligen Shi
School of Mathematical Sciences, Capital Normal University, Beijing, China
5 shared publications
Latest Publications
- 17 June 2026
- Published by Elsevier in Applied Mathematical Modelling
- Vol. 161
SMEC: A Synergistic Method for Spectral CT Basis Material Decomposition
- 17 June 2026
- Published by Elsevier in Applied Mathematical Modelling
- Vol. 161
SMEC: A Synergistic Method for Spectral CT Basis Material Decomposition
- 6 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (5) , 2088-2101
Physics-Guided Multistage Segmentation for Structural Characterization of TRISO Fuel Particles in X-Ray CT Imaging
Accurate structural analysis of coated fuel particles is essential for assessing the performance and quality of advanced nuclear fuels. X-ray computed tomography (CT) provides a non-destructive means to visualize the multilayer structure of TRISO fuel particles. However, accurate layer segmentation remains challenging due to low interlayer contrast, imaging noise, and limited labeled data. This paper proposes a physics-guided multistage segmentation network (PMSNet) for automatic multilayer segmentation of TRISO fuel particle CT images. PMSNet integrates prior knowledge of the particle’s spherical geometry and coating hierarchy into a deep learning framework, and consists of three key components: axial-aware position encoding with layer-specific spatial priors, a multiscale perturbation strategy to enhance generalization, and a prior-guided conditional fusion mechanism to enforce interlayer consistency. Experiments on synthetic and real TRISO CT datasets demonstrate that PMSNet achieves mean Dice coefficients above 0.98 and mean IoU values exceeding 0.97 across multiple coating layers. Compared with state-of-the-art methods, PMSNet improves Dice scores by 3–8 percentage points on challenging layers and achieves boundary F1 scores close to 1.0 for key interfaces. While the primary focus of this study is TRISO fuel particle segmentation, additional evaluations are performed to examine the general applicability of the proposed framework. Results on medical CT datasets further confirm its robustness and adaptability to radiation-based imaging tasks. The proposed method contributes a physics-based AI segmentation framework, enables accurate and fully automatic multilayer segmentation of TRISO fuel particles, and provides a practical solution for more efficient and reliable non-destructive nuclear fuel inspection.
- 6 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (5) , 2088-2101
Physics-Guided Multistage Segmentation for Structural Characterization of TRISO Fuel Particles in X-Ray CT Imaging
Accurate structural analysis of coated fuel particles is essential for assessing the performance and quality of advanced nuclear fuels. X-ray computed tomography (CT) provides a non-destructive means to visualize the multilayer structure of TRISO fuel particles. However, accurate layer segmentation remains challenging due to low interlayer contrast, imaging noise, and limited labeled data. This paper proposes a physics-guided multistage segmentation network (PMSNet) for automatic multilayer segmentation of TRISO fuel particle CT images. PMSNet integrates prior knowledge of the particle’s spherical geometry and coating hierarchy into a deep learning framework, and consists of three key components: axial-aware position encoding with layer-specific spatial priors, a multiscale perturbation strategy to enhance generalization, and a prior-guided conditional fusion mechanism to enforce interlayer consistency. Experiments on synthetic and real TRISO CT datasets demonstrate that PMSNet achieves mean Dice coefficients above 0.98 and mean IoU values exceeding 0.97 across multiple coating layers. Compared with state-of-the-art methods, PMSNet improves Dice scores by 3–8 percentage points on challenging layers and achieves boundary F1 scores close to 1.0 for key interfaces. While the primary focus of this study is TRISO fuel particle segmentation, additional evaluations are performed to examine the general applicability of the proposed framework. Results on medical CT datasets further confirm its robustness and adaptability to radiation-based imaging tasks. The proposed method contributes a physics-based AI segmentation framework, enables accurate and fully automatic multilayer segmentation of TRISO fuel particles, and provides a practical solution for more efficient and reliable non-destructive nuclear fuel inspection.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 660-672
Feature Decoupling Through Random Sampling for High-Fidelity Flow Matching-Based Artifact Removal
This paper introduces a novel framework for high-fidelity ring artifact removal in computed tomography (CT) by integrating projection-domain localization and image-domain refinement. Traditional methods struggle to balance artifact suppression with structural preservation due to the global nature of ring artifacts originating from detector response inconsistencies. To address this, we propose a dual-domain approach: First, a random sampling strategy in the projection domain decouples global artifacts into localized features. This involves neighborhood-based pixel shuffling with Gaussian-distributed randomness and continuity constraints, effectively disrupting vertical streaks while minimizing discontinuities. The process generates auxiliary projections (maximum, minimum, average) to supplement lost information during shuffling. Second, an image-domain flow matching model refines reconstructions by learning conditional probability paths between artifact-corrupted inputs and clean outputs. Experiments on the AAPM Mayo dataset demonstrate superior performance, achieving a PSNR of 32.952 dB and RMSE of 38.222 HU, outperforming traditional methods (e.g. wavelet-FFT, total variation) and network baselines by 2 dB. Our code is available at https://github.com/GM0322/RSFMforRingArtifacts.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 660-672
Feature Decoupling Through Random Sampling for High-Fidelity Flow Matching-Based Artifact Removal
This paper introduces a novel framework for high-fidelity ring artifact removal in computed tomography (CT) by integrating projection-domain localization and image-domain refinement. Traditional methods struggle to balance artifact suppression with structural preservation due to the global nature of ring artifacts originating from detector response inconsistencies. To address this, we propose a dual-domain approach: First, a random sampling strategy in the projection domain decouples global artifacts into localized features. This involves neighborhood-based pixel shuffling with Gaussian-distributed randomness and continuity constraints, effectively disrupting vertical streaks while minimizing discontinuities. The process generates auxiliary projections (maximum, minimum, average) to supplement lost information during shuffling. Second, an image-domain flow matching model refines reconstructions by learning conditional probability paths between artifact-corrupted inputs and clean outputs. Experiments on the AAPM Mayo dataset demonstrate superior performance, achieving a PSNR of 32.952 dB and RMSE of 38.222 HU, outperforming traditional methods (e.g. wavelet-FFT, total variation) and network baselines by 2 dB. Our code is available at https://github.com/GM0322/RSFMforRingArtifacts.
- 26 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Ring Artifacts Correction Based on Global–Local Feature Interaction Guidance in the Projection Domain
Ring artifacts frequently arise in CT imaging due to the inconsistent responses of detector units to X-rays. This effect is further exacerbated in photon-counting detectors, resulting in stripe artifacts in the sinogram. Under circular scanning, such artifacts manifest as concentric ring artifacts radiating from the center of rotation, severely degrading image quality. Based on the properties of the Radon transform and the inherent ray conjugacy in fan-beam CT systems, ideal sinograms exhibit smoothness and global correlation. Influenced by various physical factors and object properties during practical data acquisition, stripe artifacts exhibit localized high-frequency characteristics along both the detector and angular directions, with their intensities correlated with the projection values. Therefore, we propose a ring artifacts correction method based on the interaction guidance between global and local features in the projection domain. Applying the discrete wavelet transform, the sinogram is decomposed into low-frequency sub-bands that predominantly capture global feature and high-frequency sub-bands that primarily represent local feature, each corrected independently. To address the challenge of decoupling global and local feature within the sub-band images, we propose a global-local feature interaction guidance module to achieve precise correction of stripe artifacts. Extensive experimental results demonstrate that the proposed method consistently outperforms existing approaches in quantitative metrics and visual artifacts suppression, highlighting its robustness and clinical applicability.
- 26 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Ring Artifacts Correction Based on Global–Local Feature Interaction Guidance in the Projection Domain
Ring artifacts frequently arise in CT imaging due to the inconsistent responses of detector units to X-rays. This effect is further exacerbated in photon-counting detectors, resulting in stripe artifacts in the sinogram. Under circular scanning, such artifacts manifest as concentric ring artifacts radiating from the center of rotation, severely degrading image quality. Based on the properties of the Radon transform and the inherent ray conjugacy in fan-beam CT systems, ideal sinograms exhibit smoothness and global correlation. Influenced by various physical factors and object properties during practical data acquisition, stripe artifacts exhibit localized high-frequency characteristics along both the detector and angular directions, with their intensities correlated with the projection values. Therefore, we propose a ring artifacts correction method based on the interaction guidance between global and local features in the projection domain. Applying the discrete wavelet transform, the sinogram is decomposed into low-frequency sub-bands that predominantly capture global feature and high-frequency sub-bands that primarily represent local feature, each corrected independently. To address the challenge of decoupling global and local feature within the sub-band images, we propose a global-local feature interaction guidance module to achieve precise correction of stripe artifacts. Extensive experimental results demonstrate that the proposed method consistently outperforms existing approaches in quantitative metrics and visual artifacts suppression, highlighting its robustness and clinical applicability.
- 27 August 2025
- Published by Elsevier in Applied Mathematical Modelling
- Vol. 150
Practical multi-material decomposition method for variable threshold micro-focus photon-counting cone-beam CT
- 27 August 2025
- Published by Elsevier in Applied Mathematical Modelling
- Vol. 150
Practical multi-material decomposition method for variable threshold micro-focus photon-counting cone-beam CT
- Open Access
Dual-Domain Joint Learning Reconstruction Method (JLRM) Combined with Physical Process for Spectral Computed Tomography (SCT)
Spectral computed tomography (SCT) enables material decomposition, artifact reduction, and contrast enhancement, leveraging symmetry principles across its technical framework to enhance material differentiation and image quality. However, its nonlinear data acquisition process involving noise and scatter leads to a highly ill-posed inverse problem. To address this, we propose a dual-domain iterative reconstruction network that combines joint learning reconstruction with physical process modeling, which also uses the symmetric complementary properties of the two domains for optimization. A dedicated physical module models the SCT forward process to ensure stability and accuracy, while a residual-to-residual strategy reduces the computational burden of model-based iterative reconstruction (MBIR). Our method, which won the AAPM DL-Spectral CT Challenge, achieves high-accuracy material decomposition. Extensive evaluations also demonstrate its robustness under varying noise levels, confirming the method’s generalizability. This integrated approach effectively combines the strengths of physical modeling, MBIR, and deep learning.
Open AccessDual-Domain Joint Learning Reconstruction Method (JLRM) Combined with Physical Process for Spectral Computed Tomography (SCT)
Spectral computed tomography (SCT) enables material decomposition, artifact reduction, and contrast enhancement, leveraging symmetry principles across its technical framework to enhance material differentiation and image quality. However, its nonlinear data acquisition process involving noise and scatter leads to a highly ill-posed inverse problem. To address this, we propose a dual-domain iterative reconstruction network that combines joint learning reconstruction with physical process modeling, which also uses the symmetric complementary properties of the two domains for optimization. A dedicated physical module models the SCT forward process to ensure stability and accuracy, while a residual-to-residual strategy reduces the computational burden of model-based iterative reconstruction (MBIR). Our method, which won the AAPM DL-Spectral CT Challenge, achieves high-accuracy material decomposition. Extensive evaluations also demonstrate its robustness under varying noise levels, confirming the method’s generalizability. This integrated approach effectively combines the strengths of physical modeling, MBIR, and deep learning.
- 24 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 4080-4091
Ring Artifacts Removal Based on Implicit Neural Representation of Sinogram Data
Inconsistent responses of X-ray detector elements lead to stripe artifacts within the sinogram data, which subsequently manifest as ring artifacts in the reconstructed computed tomography (CT) images, severely degrading image quality. This paper presents a novel method for correcting stripe artifacts in the sinogram data by separating the sinogram into an Ideal Sinogram (IS) and Stripe Artifacts (SA), with both components parameterized through Implicit Neural Representations (INR). The proposed method leverages INR to correct defective pixel response values using implicit continuous functions while simultaneously learning stripe features in the angular direction of the sinogram data. These two components, IS and SA, are combined within an optimization constraint framework, achieving unsupervised iterative correction of stripe artifacts in the projection domain. Experimental results demonstrate that the proposed method significantly outperforms current state-of-the-art techniques in effectively removing ring artifacts while maintaining the clarity and fidelity of CT images, thereby enhancing the overall diagnostic quality of CT imaging.
- 24 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 4080-4091
Ring Artifacts Removal Based on Implicit Neural Representation of Sinogram Data
Inconsistent responses of X-ray detector elements lead to stripe artifacts within the sinogram data, which subsequently manifest as ring artifacts in the reconstructed computed tomography (CT) images, severely degrading image quality. This paper presents a novel method for correcting stripe artifacts in the sinogram data by separating the sinogram into an Ideal Sinogram (IS) and Stripe Artifacts (SA), with both components parameterized through Implicit Neural Representations (INR). The proposed method leverages INR to correct defective pixel response values using implicit continuous functions while simultaneously learning stripe features in the angular direction of the sinogram data. These two components, IS and SA, are combined within an optimization constraint framework, achieving unsupervised iterative correction of stripe artifacts in the projection domain. Experimental results demonstrate that the proposed method significantly outperforms current state-of-the-art techniques in effectively removing ring artifacts while maintaining the clarity and fidelity of CT images, thereby enhancing the overall diagnostic quality of CT imaging.
- 9 June 2025
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 28 (3) , 1-14
Contour-Aware contrastive learning for 3D knee segmentation from MR images
- 9 June 2025
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 28 (3) , 1-14
Contour-Aware contrastive learning for 3D knee segmentation from MR images