Qiucheng Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiucheng Sun has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Fanhua Yu
Changchun Normal University
3 shared publications Changbo Gao
ChangChun Normal University, Changchun, China
2 shared publications- Chunyan Wang
Changchun Normal University
2 shared publications - Dong Zhao
Qinghai Normal University
2 shared publications - Guangjie Liu
Nanjing University of Information Science and Technology
2 shared publications - Jinlong Zhu
Huazhong University of Science and Technology
2 shared publications
Latest Publications
- Open Access
- 24 September 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (9) , e0359153
scLTF: A self-training clustering framework for large-scale single-cell RNA-Seq data
Single-cell RNA sequencing (scRNA-seq) technology has rapidly advanced in recent years, driving significant breakthroughs in developmental biology, cancer research, immunology, and other related fields. However, existing clustering methods still face performance bottlenecks when handling large-scale scRNA-seq data. To address this challenge, we propose a self-training clustering method for large-scale single-cell RNA-seq data, termed scLTF (Single-cell Louvain-Transformer Framework for Large-scale Clustering). This method first generates preliminary clusters using a fast Louvain algorithm and then selects key cells based on a custom “Cluster Representativeness Index”. Subsequently, a Transformer model is employed for iterative representation learning and optimization to optimize the final clustering results. Experiments on multiple real-world datasets demonstrate that scLTF achieves overall superior or comparable performance in clustering accuracy compared with several state-of-the-art deep clustering methods, with evaluation metrics (ARI, NMI, and ACC) improving on average by approximately 3.9%–24.1%; meanwhile, its runtime is only about 6.7%–43.9% of existing deep learning-based methods. scLTF integrates the advantages of traditional graph-based clustering and deep learning models, achieving both high clustering performance and computational efficiency, thus providing a practical and reliable tool for biomedical research and cellular analysis.
- 24 September 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (9) , e0359153
Open AccessscLTF: A self-training clustering framework for large-scale single-cell RNA-Seq data
Single-cell RNA sequencing (scRNA-seq) technology has rapidly advanced in recent years, driving significant breakthroughs in developmental biology, cancer research, immunology, and other related fields. However, existing clustering methods still face performance bottlenecks when handling large-scale scRNA-seq data. To address this challenge, we propose a self-training clustering method for large-scale single-cell RNA-seq data, termed scLTF (Single-cell Louvain-Transformer Framework for Large-scale Clustering). This method first generates preliminary clusters using a fast Louvain algorithm and then selects key cells based on a custom “Cluster Representativeness Index”. Subsequently, a Transformer model is employed for iterative representation learning and optimization to optimize the final clustering results. Experiments on multiple real-world datasets demonstrate that scLTF achieves overall superior or comparable performance in clustering accuracy compared with several state-of-the-art deep clustering methods, with evaluation metrics (ARI, NMI, and ACC) improving on average by approximately 3.9%–24.1%; meanwhile, its runtime is only about 6.7%–43.9% of existing deep learning-based methods. scLTF integrates the advantages of traditional graph-based clustering and deep learning models, achieving both high clustering performance and computational efficiency, thus providing a practical and reliable tool for biomedical research and cellular analysis.
- Open Access
- 2 July 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (4)
scGGC: a two-stage strategy for single-cell clustering through cellular gene pathway construction
In the last few years, there has been great advancement in the field of single-cell data investigation, particularly in the development of clustering methods. The advanced research is increased for the development of clustering algorithms tailored for single-cell RNA sequencing data. Conventional methods primarily focus on local relationships among cells or genes, while overlooking the global cell-gene interactions. As a result, the high dimensionality, noise, and sparsity of the data continue to pose significant challenges to clustering accuracy. To address the challenges of single-cell clustering analysis, we propose a novel single-cell clustering model, scGGC, which integrates graph autoencoders and generative adversarial network techniques. The innovations of scGGC include two components: (i) construction of an adjacency matrix that incorporates cell–cell and cell-gene relationships to capture complex interactions in a graph structure, enabling nonlinear dimensionality reduction and initial clustering via a graph autoencoder; (ii) enhancement of clustering performance by selecting high-confidence samples from the initial clusters for adversarial neural network training. A comprehensive evaluation on nine publicly available scRNA-seq datasets demonstrates that scGGC outperforms eight comparison methods. For example, on datasets such as MHC3K, the Adjusted Rand Index increases by an average of 10.1%. Furthermore, marker gene identification and cell type annotation further confirm the biological relevance of scGGC, with marker gene overlap rates exceeding 70% across multiple datasets. We conclude that scGGC not only improves the accuracy of single-cell data clustering but also enhances the identification of cell-type-specific marker genes. The scGGC code is available at https://github.com/Zhi1002/scGGC.
- 2 July 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (4)
Open AccessscGGC: a two-stage strategy for single-cell clustering through cellular gene pathway construction
In the last few years, there has been great advancement in the field of single-cell data investigation, particularly in the development of clustering methods. The advanced research is increased for the development of clustering algorithms tailored for single-cell RNA sequencing data. Conventional methods primarily focus on local relationships among cells or genes, while overlooking the global cell-gene interactions. As a result, the high dimensionality, noise, and sparsity of the data continue to pose significant challenges to clustering accuracy. To address the challenges of single-cell clustering analysis, we propose a novel single-cell clustering model, scGGC, which integrates graph autoencoders and generative adversarial network techniques. The innovations of scGGC include two components: (i) construction of an adjacency matrix that incorporates cell–cell and cell-gene relationships to capture complex interactions in a graph structure, enabling nonlinear dimensionality reduction and initial clustering via a graph autoencoder; (ii) enhancement of clustering performance by selecting high-confidence samples from the initial clusters for adversarial neural network training. A comprehensive evaluation on nine publicly available scRNA-seq datasets demonstrates that scGGC outperforms eight comparison methods. For example, on datasets such as MHC3K, the Adjusted Rand Index increases by an average of 10.1%. Furthermore, marker gene identification and cell type annotation further confirm the biological relevance of scGGC, with marker gene overlap rates exceeding 70% across multiple datasets. We conclude that scGGC not only improves the accuracy of single-cell data clustering but also enhances the identification of cell-type-specific marker genes. The scGGC code is available at https://github.com/Zhi1002/scGGC.
- Open Access
- 27 May 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-15
A robust multi-scale clustering framework for single-cell RNA-seq data analysis
Recent advancements in single-cell RNA sequencing (scRNA-seq) technology have unlocked novel opportunities for deep exploration of gene expression patterns. However, the inherent high dimensionality, sparsity, and noise in scRNA-seq data pose significant challenges for existing clustering methods, especially in accurately identifying and classifying diverse cell types. To address these challenges, we introduce a new method, single-cell Multi-Scale Clustering Framework (scMSCF), which combines multi-dimensional PCA for dimensionality reduction, K-means clustering, and a weighted ensemble meta-clustering approach, enhanced by a self-attention-driven Transformer model to optimize clustering performance. scMSCF constructs an initial clustering framework using a multi-layer dimensionality reduction strategy to establish a robust consensus on clustering structure. A voting mechanism within the meta-clustering process selects high-confidence cells from the initial clustering results to provide precise training labels for the Transformer model. This approach enables the model to capture complex dependencies in gene expression data, thereby enhancing clustering accuracy. Comprehensive testing across eight single-cell RNA sequencing datasets demonstrates that scMSCF surpasses existing methods, achieving on average 10-15% higher ARI, NMI, and ACC scores. For example, on the PBMC5k dataset, scMSCF improves ARI from 0.72 to 0.86, demonstrating its ability to accurately identify diverse cell populations. The source code for our algorithm is publicly available at https://github.com/DEREKJ24/scMSCF.
- 27 May 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-15
Open AccessA robust multi-scale clustering framework for single-cell RNA-seq data analysis
Recent advancements in single-cell RNA sequencing (scRNA-seq) technology have unlocked novel opportunities for deep exploration of gene expression patterns. However, the inherent high dimensionality, sparsity, and noise in scRNA-seq data pose significant challenges for existing clustering methods, especially in accurately identifying and classifying diverse cell types. To address these challenges, we introduce a new method, single-cell Multi-Scale Clustering Framework (scMSCF), which combines multi-dimensional PCA for dimensionality reduction, K-means clustering, and a weighted ensemble meta-clustering approach, enhanced by a self-attention-driven Transformer model to optimize clustering performance. scMSCF constructs an initial clustering framework using a multi-layer dimensionality reduction strategy to establish a robust consensus on clustering structure. A voting mechanism within the meta-clustering process selects high-confidence cells from the initial clustering results to provide precise training labels for the Transformer model. This approach enables the model to capture complex dependencies in gene expression data, thereby enhancing clustering accuracy. Comprehensive testing across eight single-cell RNA sequencing datasets demonstrates that scMSCF surpasses existing methods, achieving on average 10-15% higher ARI, NMI, and ACC scores. For example, on the PBMC5k dataset, scMSCF improves ARI from 0.72 to 0.86, demonstrating its ability to accurately identify diverse cell populations. The source code for our algorithm is publicly available at https://github.com/DEREKJ24/scMSCF.
- Open Access
- 12 February 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
MBS-NeRF: reconstruction of sharp neural radiance fields from motion-blurred sparse images
The recent advance in Neural Radiance Fields (NeRF), which utilizes Multilayer Perceptrons (MLP) for implicit scene representation, enables the synthesis of realistic views from new perspectives. However, degradation in the quantity and quality of input images can lead to failure in scene reconstruction and difficulty in synthesizing high-quality views. To address these limitations, this paper presents a NeRF-based framework (MBS-NeRF), which can reconstruct sharp NeRF from a limited number of motion-blurred input images for high-quality view synthesis. The framework integrates depth information as a constraint to counter the lack of sufficient view information and introduces a Motion Blur Simulation Module (MBSM) to simulate the physical formation process of motion blur. We further introduce camera trajectory optimization during the exposure process to robust the incorrect camera position. MBS-NeRF is thoroughly trained considering photometric consistency and depth supervision. Comprehensive experiments on synthetic and real datasets validate the effectiveness of the model in reconstructing sharp NeRF and achieving high-quality view synthesis from sparse, motion-blurred inputs.
- 12 February 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
Open AccessMBS-NeRF: reconstruction of sharp neural radiance fields from motion-blurred sparse images
The recent advance in Neural Radiance Fields (NeRF), which utilizes Multilayer Perceptrons (MLP) for implicit scene representation, enables the synthesis of realistic views from new perspectives. However, degradation in the quantity and quality of input images can lead to failure in scene reconstruction and difficulty in synthesizing high-quality views. To address these limitations, this paper presents a NeRF-based framework (MBS-NeRF), which can reconstruct sharp NeRF from a limited number of motion-blurred input images for high-quality view synthesis. The framework integrates depth information as a constraint to counter the lack of sufficient view information and introduces a Motion Blur Simulation Module (MBSM) to simulate the physical formation process of motion blur. We further introduce camera trajectory optimization during the exposure process to robust the incorrect camera position. MBS-NeRF is thoroughly trained considering photometric consistency and depth supervision. Comprehensive experiments on synthetic and real datasets validate the effectiveness of the model in reconstructing sharp NeRF and achieving high-quality view synthesis from sparse, motion-blurred inputs.
- Open Access
- 31 October 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-17
A three-dimensional vision measurement method based on double-line combined structured light
In this paper, a structured light vision measurement method using a scanning laser line and a positioning laser line is proposed. The novel method enables the scanning laser plane to slide along a slide rail while maintaining intersection with the positioning laser plane, eliminating the need to determine the scanning direction and moving step. During the measurement process, the laser plane equations need to be recalibrated for each new position, so a real-time calibration method is given. Initially, the geometric barycenter method is employed to detect the subpixel coordinates of the light stripe intersection point. Subsequently, these coordinates are projected into the camera coordinate system using the initial equations of the positioning laser plane. Finally, leveraging the normal information of the initial equation of the scanning laser plane and the three-dimensional coordinates of the light stripe intersection point, the real-time calibration of the scanning laser plane equations can be accomplished. The proposed method enables the three-dimensional reconstruction of objects, and its accuracy is verified through measurements on gauge blocks. Experimental results demonstrate that this method achieves precise and stable three-dimensional reconstruction of object surface shape.
- 31 October 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-17
Open AccessA three-dimensional vision measurement method based on double-line combined structured light
In this paper, a structured light vision measurement method using a scanning laser line and a positioning laser line is proposed. The novel method enables the scanning laser plane to slide along a slide rail while maintaining intersection with the positioning laser plane, eliminating the need to determine the scanning direction and moving step. During the measurement process, the laser plane equations need to be recalibrated for each new position, so a real-time calibration method is given. Initially, the geometric barycenter method is employed to detect the subpixel coordinates of the light stripe intersection point. Subsequently, these coordinates are projected into the camera coordinate system using the initial equations of the positioning laser plane. Finally, leveraging the normal information of the initial equation of the scanning laser plane and the three-dimensional coordinates of the light stripe intersection point, the real-time calibration of the scanning laser plane equations can be accomplished. The proposed method enables the three-dimensional reconstruction of objects, and its accuracy is verified through measurements on gauge blocks. Experimental results demonstrate that this method achieves precise and stable three-dimensional reconstruction of object surface shape.
- Open Access
- 1 January 2023
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 75 (2) , 3957-3970
An Improved Calibration Method of Grating Projection Measurement System
In the traditional fringe projection profilometry system, the projector and the camera light center are both spatially virtual points. The spatial position relationships specified in the model are not easy to obtain, leading to inaccurate system parameters and affecting measurement accuracy. This paper proposes a method for solving the system parameters of the fringe projection profilometry system, and the spatial position of the camera and projector can be adjusted in accordance with the obtained calibration parameters. The steps are as follows: First, in accordance with the conversion relationship of the coordinate system in the calibration process, the calculation formula of the vertical distance from the camera light center to the reference plane and the calculation formula of the distance between the projector and the camera light center are given respectively. Secondly, according to the projector calibration principle, the position of the projector light axis perpendicular to the reference plane is gained by comparing the parallel relationship between the reference plane coordinate system and the projector coordinate system’s Z-axis. Then, in order to fulfill the position restriction that the line between the projector light center and the camera light center must be parallel to the reference plane, the camera’s spatial location is adjusted so that the vertical distance between it and the reference plane tends to that between the projector light center and the reference plane. And finally, the three-dimensional (3D) reconstruction of the target object can be finished using the phase height model’s system parameters once the aforementioned position limitations are put into practice. Experimental results demonstrate that the method improves the measurement accuracy, and verifies that it is effective and available in 3D shape measurement.
- 1 January 2023
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 75 (2) , 3957-3970
Open AccessAn Improved Calibration Method of Grating Projection Measurement System
In the traditional fringe projection profilometry system, the projector and the camera light center are both spatially virtual points. The spatial position relationships specified in the model are not easy to obtain, leading to inaccurate system parameters and affecting measurement accuracy. This paper proposes a method for solving the system parameters of the fringe projection profilometry system, and the spatial position of the camera and projector can be adjusted in accordance with the obtained calibration parameters. The steps are as follows: First, in accordance with the conversion relationship of the coordinate system in the calibration process, the calculation formula of the vertical distance from the camera light center to the reference plane and the calculation formula of the distance between the projector and the camera light center are given respectively. Secondly, according to the projector calibration principle, the position of the projector light axis perpendicular to the reference plane is gained by comparing the parallel relationship between the reference plane coordinate system and the projector coordinate system’s Z-axis. Then, in order to fulfill the position restriction that the line between the projector light center and the camera light center must be parallel to the reference plane, the camera’s spatial location is adjusted so that the vertical distance between it and the reference plane tends to that between the projector light center and the reference plane. And finally, the three-dimensional (3D) reconstruction of the target object can be finished using the phase height model’s system parameters once the aforementioned position limitations are put into practice. Experimental results demonstrate that the method improves the measurement accuracy, and verifies that it is effective and available in 3D shape measurement.
- Open Access
A Three-Dimensional Structured Light Vision System by Using a Combination of Single-Line and Three-Line Lasers
A multi-line structured light measurement method that combines a single-line and a three-line laser, in which precision sliding rails and displacement measurement equipment are not required, is proposed in this paper. During the measurement, the single-line structured light projects onto the surface of an object and the three-line structured light remains fixed. The single-line laser is moved and intersects with the three-line laser to form three intersection points. The single-line light plane can be solved using the camera coordinates of three intersection points, thus completing the real-time calibration of the scanned light plane. The single-line laser can be scanned at any angle to determine the overall complete three-dimensional (3D) shape of the object during the process. Experimental results show that this method overcomes the difficulty of obtaining information about certain angles and locations and can effectively recover the 3D shape of the object. The measurement system’s repetition error is under 0.16 mm, which is sufficient to measure the 3D shapes of complicated workpieces.
Open AccessA Three-Dimensional Structured Light Vision System by Using a Combination of Single-Line and Three-Line Lasers
A multi-line structured light measurement method that combines a single-line and a three-line laser, in which precision sliding rails and displacement measurement equipment are not required, is proposed in this paper. During the measurement, the single-line structured light projects onto the surface of an object and the three-line structured light remains fixed. The single-line laser is moved and intersects with the three-line laser to form three intersection points. The single-line light plane can be solved using the camera coordinates of three intersection points, thus completing the real-time calibration of the scanned light plane. The single-line laser can be scanned at any angle to determine the overall complete three-dimensional (3D) shape of the object during the process. Experimental results show that this method overcomes the difficulty of obtaining information about certain angles and locations and can effectively recover the 3D shape of the object. The measurement system’s repetition error is under 0.16 mm, which is sufficient to measure the 3D shapes of complicated workpieces.
- Open Access
- 11 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 153540-153547
A Method of Camera Calibration Based on Kriging Interpolation
The basis of visual measurement is camera calibration. In the traditional calibration method, the radial and tangential distortion models usually are adopted. Because of the randomness of lens distortion, the above fixed form distortion model cannot accurately express the distortion distribution. To solve the above problems, a calibration method with a new distortion model is presented in the paper. First, an exact linear model is obtained, using only the corner coordinates of the image center region; then, using this model, the projection deviation of all corner points in the pixel plane can be obtained, that is, the point cloud of projection deviation distribution; finally, the Kriging interpolation method is used to obtain a continuous projection deviation distribution function which can accurately express lens distortion in the pixel plane. Using this function and the corresponding linear model, all two-dimensional image points can be accurately projected into three-dimensional space. To compare with the traditional method, the mean error of projection and measurement error are calculated in the experiment, and the experimental results show that the calibration method is more accurate and more suitable for measuring requirements.
- 11 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 153540-153547
Open AccessA Method of Camera Calibration Based on Kriging Interpolation
The basis of visual measurement is camera calibration. In the traditional calibration method, the radial and tangential distortion models usually are adopted. Because of the randomness of lens distortion, the above fixed form distortion model cannot accurately express the distortion distribution. To solve the above problems, a calibration method with a new distortion model is presented in the paper. First, an exact linear model is obtained, using only the corner coordinates of the image center region; then, using this model, the projection deviation of all corner points in the pixel plane can be obtained, that is, the point cloud of projection deviation distribution; finally, the Kriging interpolation method is used to obtain a continuous projection deviation distribution function which can accurately express lens distortion in the pixel plane. Using this function and the corresponding linear model, all two-dimensional image points can be accurately projected into three-dimensional space. To compare with the traditional method, the mean error of projection and measurement error are calculated in the experiment, and the experimental results show that the calibration method is more accurate and more suitable for measuring requirements.
- 13 April 2019
- Published by Springer Nature
- p. 425-433
Face Recognition Algorithm Based on Nonlinear Principal Component Feature Extraction Neural Network
- 13 April 2019
- Published by Springer Nature
- p. 425-433
Face Recognition Algorithm Based on Nonlinear Principal Component Feature Extraction Neural Network
- 13 April 2019
- Published by Springer Nature
- p. 513-519
The Hot Spots Components from Drawings of Subway Using Template Matching
- 13 April 2019
- Published by Springer Nature
- p. 513-519
The Hot Spots Components from Drawings of Subway Using Template Matching