Yongning Zou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yongning Zou has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Jue Wang
Affiliations Key Laboratory of Optoelectronic Technology and System of the Education Ministry, Chongqing University, Chongqing, China, Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry, Chongqing University, Chongqing, China
3 shared publicationsGongjie Yao
Affiliations Key Laboratory of Optoelectronic Technology and System of the Education Ministry, Chongqing University, Chongqing, China, Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry, Chongqing University, Chongqing, China
2 shared publications- Ying Chen2 shared publications
Changjian Sun
Affiliation Medical Image Processing Group, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America
1 shared publicationDrew A. Torigian
Affiliations Medical Image Processing Group, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America, Lymphoma Program, Abramson Cancer Center, Perelman Center for Advanced Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America
1 shared publicationEmeline Chong
Affiliation Lymphoma Program, Abramson Cancer Center, Perelman Center for Advanced Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America
1 shared publication
Latest Publications
- Open Access
- 5 August 2026
- Published by Elsevier in SSRN Electronic Journal
Sparse-Point Initialization and Decaying Opacity Perturbation for Sparse-View CT Reconstruction with 3D Gaussian Splatting
Sparse-view computed tomography (CT) reduces radiation dose and acquisition time, but the limited number of projections makes the reconstruction problem highly underdetermined, leading to streak artifacts and structural degradation. Existing 3D Gaussian Splatting (3DGS)-based CT reconstruction methods typically initialize Gaussian primitives from full FDK point clouds, causing streak artifacts and beam-hardening responses in sparse-view FDK reconstructions to be inherited by the initial Gaussian distribution. Moreover, limited projection supervision tends to drive Gaussian primitives into fixed co-adaptation relationships, resulting in needle-like artifacts during optimization. To address these issues, we propose a sparse-view CT reconstruction method that combines Sparse-Point Initialization (SPI) with Decaying Opacity Perturbation (DOP). SPI selects representative structural points from the FDK reconstruction through joint density-gradient scoring and improves spatial coverage using Adaptive Boundary Expansion (ABE), thereby reducing artifact contamination in the initial Gaussian distribution. DOP applies iteration-decaying multiplicative Laplace noise to Gaussian opacities during training, continuously modulating Gaussian contributions to suppress fixed co-adaptation. Experiments on the public FIPS dataset and self-built industrial CT datasets demonstrate that the proposed method improves PSNR by up to 1.132~dB and SSIM by up to 0.023 over the R2-Gaussian baseline under 25-view reconstruction, while effectively reducing the Co-Adaptation Score (CA).
- 5 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSparse-Point Initialization and Decaying Opacity Perturbation for Sparse-View CT Reconstruction with 3D Gaussian Splatting
Sparse-view computed tomography (CT) reduces radiation dose and acquisition time, but the limited number of projections makes the reconstruction problem highly underdetermined, leading to streak artifacts and structural degradation. Existing 3D Gaussian Splatting (3DGS)-based CT reconstruction methods typically initialize Gaussian primitives from full FDK point clouds, causing streak artifacts and beam-hardening responses in sparse-view FDK reconstructions to be inherited by the initial Gaussian distribution. Moreover, limited projection supervision tends to drive Gaussian primitives into fixed co-adaptation relationships, resulting in needle-like artifacts during optimization. To address these issues, we propose a sparse-view CT reconstruction method that combines Sparse-Point Initialization (SPI) with Decaying Opacity Perturbation (DOP). SPI selects representative structural points from the FDK reconstruction through joint density-gradient scoring and improves spatial coverage using Adaptive Boundary Expansion (ABE), thereby reducing artifact contamination in the initial Gaussian distribution. DOP applies iteration-decaying multiplicative Laplace noise to Gaussian opacities during training, continuously modulating Gaussian contributions to suppress fixed co-adaptation. Experiments on the public FIPS dataset and self-built industrial CT datasets demonstrate that the proposed method improves PSNR by up to 1.132~dB and SSIM by up to 0.023 over the R2-Gaussian baseline under 25-view reconstruction, while effectively reducing the Co-Adaptation Score (CA).
- 5 June 2025
- Published by Optica Publishing Group in Optics Express
- Vol. 33 (12) , 25415-25435
Truncated projection CL reconstruction based on TS-FBP
X-ray computed laminography (CL), a widely employed nondestructive testing technique, holds significant potential for detecting micro-faults in laminated structure thin-plate parts (LSTP). However, thin plate components frequently exceed the field of view (FOV) of CL systems due to detector size constraints, leading to truncation artifacts as X-rays fail to encompass the entire imaging target. While projection weighting algorithms have been proven effective in recovering high-quality reconstructions for local computed tomography (CT) scans, their applicability to CL reconstruction from truncated projections remains underexplored. This paper proposes a novel two-step weighted filtered back-projection (TS-FBP) algorithm for CL truncation reconstruction. The methodology integrates the FBP algorithm with a cosine-weighted projection scheme, addressing projection edge discontinuities through smooth truncation to meet FBP reconstruction requirements without modifying the original scanning geometry. Additionally, a post-filtering quadratic weighting mechanism is implemented for image intensity normalization. Comprehensive validation through numerical simulations and physical experiments demonstrates that the proposed approach achieves artifact-suppressed cross-sectional reconstruction with high computational efficiency, while guaranteeing sufficient quality.
- 5 June 2025
- Published by Optica Publishing Group in Optics Express
- Vol. 33 (12) , 25415-25435
Truncated projection CL reconstruction based on TS-FBP
X-ray computed laminography (CL), a widely employed nondestructive testing technique, holds significant potential for detecting micro-faults in laminated structure thin-plate parts (LSTP). However, thin plate components frequently exceed the field of view (FOV) of CL systems due to detector size constraints, leading to truncation artifacts as X-rays fail to encompass the entire imaging target. While projection weighting algorithms have been proven effective in recovering high-quality reconstructions for local computed tomography (CT) scans, their applicability to CL reconstruction from truncated projections remains underexplored. This paper proposes a novel two-step weighted filtered back-projection (TS-FBP) algorithm for CL truncation reconstruction. The methodology integrates the FBP algorithm with a cosine-weighted projection scheme, addressing projection edge discontinuities through smooth truncation to meet FBP reconstruction requirements without modifying the original scanning geometry. Additionally, a post-filtering quadratic weighting mechanism is implemented for image intensity normalization. Comprehensive validation through numerical simulations and physical experiments demonstrates that the proposed approach achieves artifact-suppressed cross-sectional reconstruction with high computational efficiency, while guaranteeing sufficient quality.
- Open Access
- 21 July 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (7) , e0282573
Prediction of lymphoma response to CAR T cells by deep learning-based image analysis
Clinical prognostic scoring systems have limited utility for predicting treatment outcomes in lymphomas. We therefore tested the feasibility of a deep-learning (DL)-based image analysis methodology on pre-treatment diagnostic computed tomography (dCT), low-dose CT (lCT), and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) images and rule-based reasoning to predict treatment response to chimeric antigen receptor (CAR) T-cell therapy in B-cell lymphomas. Pre-treatment images of 770 lymph node lesions from 39 adult patients with B-cell lymphomas treated with CD19-directed CAR T-cells were analyzed. Transfer learning using a pre-trained neural network model, then retrained for a specific task, was used to predict lesion-level treatment responses from separate dCT, lCT, and FDG-PET images. Patient-level response analysis was performed by applying rule-based reasoning to lesion-level prediction results. Patient-level response prediction was also compared to prediction based on the international prognostic index (IPI) for diffuse large B-cell lymphoma. The average accuracy of lesion-level response prediction based on single whole dCT slice-based input was 0.82+0.05 with sensitivity 0.87+0.07, specificity 0.77+0.12, and AUC 0.91+0.03. Patient-level response prediction from dCT, using the “Majority 60%” rule, had accuracy 0.81, sensitivity 0.75, and specificity 0.88 using 12-month post-treatment patient response as the reference standard and outperformed response prediction based on IPI risk factors (accuracy 0.54, sensitivity 0.38, and specificity 0.61 (p = 0.046)). Prediction of treatment outcome in B-cell lymphomas from pre-treatment medical images using DL-based image analysis and rule-based reasoning is feasible. This approach can potentially provide clinically useful prognostic information for decision-making in advance of initiating CAR T-cell therapy.
- 21 July 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (7) , e0282573
Open AccessPrediction of lymphoma response to CAR T cells by deep learning-based image analysis
Clinical prognostic scoring systems have limited utility for predicting treatment outcomes in lymphomas. We therefore tested the feasibility of a deep-learning (DL)-based image analysis methodology on pre-treatment diagnostic computed tomography (dCT), low-dose CT (lCT), and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) images and rule-based reasoning to predict treatment response to chimeric antigen receptor (CAR) T-cell therapy in B-cell lymphomas. Pre-treatment images of 770 lymph node lesions from 39 adult patients with B-cell lymphomas treated with CD19-directed CAR T-cells were analyzed. Transfer learning using a pre-trained neural network model, then retrained for a specific task, was used to predict lesion-level treatment responses from separate dCT, lCT, and FDG-PET images. Patient-level response analysis was performed by applying rule-based reasoning to lesion-level prediction results. Patient-level response prediction was also compared to prediction based on the international prognostic index (IPI) for diffuse large B-cell lymphoma. The average accuracy of lesion-level response prediction based on single whole dCT slice-based input was 0.82+0.05 with sensitivity 0.87+0.07, specificity 0.77+0.12, and AUC 0.91+0.03. Patient-level response prediction from dCT, using the “Majority 60%” rule, had accuracy 0.81, sensitivity 0.75, and specificity 0.88 using 12-month post-treatment patient response as the reference standard and outperformed response prediction based on IPI risk factors (accuracy 0.54, sensitivity 0.38, and specificity 0.61 (p = 0.046)). Prediction of treatment outcome in B-cell lymphomas from pre-treatment medical images using DL-based image analysis and rule-based reasoning is feasible. This approach can potentially provide clinically useful prognostic information for decision-making in advance of initiating CAR T-cell therapy.
- Open Access
- 14 October 2021
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (10) , e0258463
Research on 3D crack segmentation of CT images of oil rock core
In this paper, we propose a framework for CT image segmentation of oil rock core. According to the characteristics of CT image of oil rock core, the existing level set segmentation algorithm is improved. Firstly, an algorithm of Chan-Vese (C-V) model is carried out to segment rock core from image background. Secondly the gray level of image background region is replaced by the average gray level of rock core, so that image background does not affect the binary segmentation. Next, median filtering processing is carried out. Finally, an algorithm of local binary fitting (LBF) model is executed to obtain the crack region. The proposed algorithm has been applied to oil rock core CT images with promising results.
- 14 October 2021
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (10) , e0258463
Open AccessResearch on 3D crack segmentation of CT images of oil rock core
In this paper, we propose a framework for CT image segmentation of oil rock core. According to the characteristics of CT image of oil rock core, the existing level set segmentation algorithm is improved. Firstly, an algorithm of Chan-Vese (C-V) model is carried out to segment rock core from image background. Secondly the gray level of image background region is replaced by the average gray level of rock core, so that image background does not affect the binary segmentation. Next, median filtering processing is carried out. Finally, an algorithm of local binary fitting (LBF) model is executed to obtain the crack region. The proposed algorithm has been applied to oil rock core CT images with promising results.
- 1 January 2019
- Published by SAGE Publications in Journal of X-Ray Science and Technology
- Vol. 27 (6) , 1101-1119
Fully automated registration of 3D CT data to CAD model for surface deviation measurement
The aim of this study is to present a fully automated registration algorithm that allows for alignment and errors analysis of the 3D surface model obtained from industrial computed tomography (CT) images with the computer-aided design (CAD) model. First, two pre-processing steps are executed by the algorithm namely, CAD model subdivision and representing models. Next, two improved registration procedures are applied including covariance descriptors-based coarse registration with a novel and automatic calibration, followed by a fine registration technique that utilizes an improved iterative closest points (ICP) algorithm, which is what we proposed with a novel estimation method for registration error. Finally, using a novel strategy that we proposed for error display, the quantitative data analysis results can simultaneously estimate both positive and negative deviation of the surface registration errors more precisely and fully expressed. Comparing to the original ICP algorithm, the quantitative data of experimental results demonstrate that the average registration errors of carburetors and valves are reduced by 0.80 millimeter at least. Therefore, this study demonstrates that the proposed new algorithm is not only capable of fully automating the registration of 3D surface model to a CAD model but also beneficial for quantitatively determining the surface manufacturing error more precisely.
- 1 January 2019
- Published by SAGE Publications in Journal of X-Ray Science and Technology
- Vol. 27 (6) , 1101-1119
Fully automated registration of 3D CT data to CAD model for surface deviation measurement
The aim of this study is to present a fully automated registration algorithm that allows for alignment and errors analysis of the 3D surface model obtained from industrial computed tomography (CT) images with the computer-aided design (CAD) model. First, two pre-processing steps are executed by the algorithm namely, CAD model subdivision and representing models. Next, two improved registration procedures are applied including covariance descriptors-based coarse registration with a novel and automatic calibration, followed by a fine registration technique that utilizes an improved iterative closest points (ICP) algorithm, which is what we proposed with a novel estimation method for registration error. Finally, using a novel strategy that we proposed for error display, the quantitative data analysis results can simultaneously estimate both positive and negative deviation of the surface registration errors more precisely and fully expressed. Comparing to the original ICP algorithm, the quantitative data of experimental results demonstrate that the average registration errors of carburetors and valves are reduced by 0.80 millimeter at least. Therefore, this study demonstrates that the proposed new algorithm is not only capable of fully automating the registration of 3D surface model to a CAD model but also beneficial for quantitatively determining the surface manufacturing error more precisely.
- 1 January 2013
- Published by SAGE Publications in Journal of X-Ray Science and Technology
- Vol. 21 (4) , 545-556
3D defect segmentation on CT volume data using morphology and resample techniques
Segmentation of CT volume data is important and useful in non-destructive testing and evaluating. To eliminate the artifacts influence, we propose a new approach of 3D defect segmentation using two steps. First of all, an initial segmentation using 3
- 1 January 2013
- Published by SAGE Publications in Journal of X-Ray Science and Technology
- Vol. 21 (4) , 545-556
3D defect segmentation on CT volume data using morphology and resample techniques
Segmentation of CT volume data is important and useful in non-destructive testing and evaluating. To eliminate the artifacts influence, we propose a new approach of 3D defect segmentation using two steps. First of all, an initial segmentation using 3