Kexiong Ouyang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kexiong Ouyang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Huangan Liao
School and Hospital of Stomatology, Guangdong Engineering Research Center of Oral Restoration and Reconstruction, Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou Medical University, Guangzhou, China
2 shared publicationsHaoran Zheng
Guangzhou Panyu Polytechnic, Guangzhou, China
1 shared publicationHuibin Ma
Hospital of Stomatology Shantou University Medical College, Shantou, China
1 shared publicationJanak Lal Pathak
School and Hospital of Stomatology, Guangdong Engineering Research Center of Oral Restoration and Reconstruction, Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou Medical University, Guangzhou, China
1 shared publicationJi Jie
Network & Information Center of Shantou University, Shantou, China
1 shared publicationJieying Huang
Department of Oral Implantology, School and Hospital of Stomatology, Guangdong Engineering Research Center of Oral Restoration and Reconstruction & Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou Medical University, Guangzhou, China
1 shared publication
Latest Publications
- Open Access
- 29 October 2025
- Published by Springer Nature in BMC Oral Health
- Vol. 25 (1) , 1-10
Deep learning for automated mandibular canal segmentation in CBCT scans
This study aims to develop a framework for automated mandibular canal segmentation in cone beam computed tomography (CBCT) scans. The dataset, source code, and trained models are publicly accessible, allowing for reproducibility and further development by the research community. A total of 236 CBCT scans were collected from the Stomatology Hospital of the Shantou University Medical College, and the mandibular canals in these scans were manually annotated with fine granularity. A custom-designed 3D U-Net, named ManCan_ResU-Net, along with two commonly used 3D U-Net models, was employed as candidate models. The soft Dice Similarity Coefficient (DSC) loss was used as the loss function. During inference, a post-processing step involving connected components analysis and removal of small disconnected objects was applied to refine the segmentation results. Model performance was evaluated using following metrics: voxel accuracy (ACC), sensitivity (SEN), specificity (SPE), DSC, Hausdorff distance (HD), 95th percentile Hausdorff distance (HD95), average surface distance (ASD), and average symmetric surface distance (ASSD). The MCSTU dataset, which contains a development dataset (218 CBCT images) and an independent test dataset (18 CBCT images) with fine-grained annotations, has been made publicly available. The validation loss of ManCan_ResU-Net was lower than those of two commonly used models. Incorporating post-processing significantly improved model performance, particularly by reducing the HD metric. On the hold-out test dataset, the ManCan_ResU-Net model achieved ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.86 (0.83–0.87), 1 (1–1), 0.85 (0.83–0.86), 10.1 (8.67–13.6), 1.8 (1.6–2.2), 0.69 (0.58–0.85), and 0.72 (0.6–0.83), respectively. On the test dataset, the ManCan_ResU-Net model obtained ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.93 (0.91–0.95), 1 (1–1), 0.80 (0.79–0.81), 21.3 (11.7–53.9), 2.59 (2.33–3), 1 (0.96–1.21), and 0.92 (0.861–1), respectively. Both the code and trained models are publicly available. The proposed segmentation framework achieved strong performance on both the hold-out and independent test datasets. In the future, after further validation of the model’s generalization ability, it may be applied in real clinical settings for oral surgery planning.
- 29 October 2025
- Published by Springer Nature in BMC Oral Health
- Vol. 25 (1) , 1-10
Open AccessDeep learning for automated mandibular canal segmentation in CBCT scans
This study aims to develop a framework for automated mandibular canal segmentation in cone beam computed tomography (CBCT) scans. The dataset, source code, and trained models are publicly accessible, allowing for reproducibility and further development by the research community. A total of 236 CBCT scans were collected from the Stomatology Hospital of the Shantou University Medical College, and the mandibular canals in these scans were manually annotated with fine granularity. A custom-designed 3D U-Net, named ManCan_ResU-Net, along with two commonly used 3D U-Net models, was employed as candidate models. The soft Dice Similarity Coefficient (DSC) loss was used as the loss function. During inference, a post-processing step involving connected components analysis and removal of small disconnected objects was applied to refine the segmentation results. Model performance was evaluated using following metrics: voxel accuracy (ACC), sensitivity (SEN), specificity (SPE), DSC, Hausdorff distance (HD), 95th percentile Hausdorff distance (HD95), average surface distance (ASD), and average symmetric surface distance (ASSD). The MCSTU dataset, which contains a development dataset (218 CBCT images) and an independent test dataset (18 CBCT images) with fine-grained annotations, has been made publicly available. The validation loss of ManCan_ResU-Net was lower than those of two commonly used models. Incorporating post-processing significantly improved model performance, particularly by reducing the HD metric. On the hold-out test dataset, the ManCan_ResU-Net model achieved ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.86 (0.83–0.87), 1 (1–1), 0.85 (0.83–0.86), 10.1 (8.67–13.6), 1.8 (1.6–2.2), 0.69 (0.58–0.85), and 0.72 (0.6–0.83), respectively. On the test dataset, the ManCan_ResU-Net model obtained ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.93 (0.91–0.95), 1 (1–1), 0.80 (0.79–0.81), 21.3 (11.7–53.9), 2.59 (2.33–3), 1 (0.96–1.21), and 0.92 (0.861–1), respectively. Both the code and trained models are publicly available. The proposed segmentation framework achieved strong performance on both the hold-out and independent test datasets. In the future, after further validation of the model’s generalization ability, it may be applied in real clinical settings for oral surgery planning.
- Open Access
- 6 August 2025
- Published by Springer Nature in BMC Oral Health
- Vol. 25 (1) , 1-15
Assessing the spatial relationship between mandibular third molars and the inferior alveolar canal using a deep learning-based approach: a proof-of-concept study
The distance between the mandibular third molar (M3) and the mandibular canal (MC) is a key factor in assessing the risk of injury to the inferior alveolar nerve (IAN). However, existing deep learning systems have not yet been able to accurately quantify the M3-MC distance in 3D space. The aim of this study was to develop and validate a deep learning-based system for accurate measurement of M3-MC spatial relationships in cone-beam computed tomography (CBCT) images and to evaluate its accuracy against conventional methods. We propose an innovative approach for low-resource environments, using DeeplabV3 + for semantic segmentation of CBCT-extracted 2D images, followed by multi-category 3D reconstruction and visualization. Based on the reconstruction model, we applied the KD-Tree algorithm to measure the spatial minimum distance between M3 and MC. Through internal validation with randomly selected CBCT images, we compared the differences between the AI system, conventional measurement methods on the CBCT, and the gold standard measured by senior experts. Statistical analysis was performed using one-way ANOVA with Tukey HSD post-hoc tests (p < 0.05), employing multiple error metrics for comprehensive evaluation. One-way ANOVA revealed significant differences among measurement methods. Subsequent Tukey HSD post-hoc tests showed significant differences between the AI reconstruction model and conventional methods. The measurement accuracy of the AI system compared to the gold standard was 0.19 for mean error (ME), 0.18 for mean absolute error (MAE), 0.69 for mean square error (MSE), 0.83 for root mean square error (RMSE), and 0.96 for coefficient of determination (R2) (p < 0.01). These results indicate that the proposed AI system is highly accurate and reliable in M3-MC distance measurement and provides a powerful tool for preoperative risk assessment of M3 extraction.
- 6 August 2025
- Published by Springer Nature in BMC Oral Health
- Vol. 25 (1) , 1-15
Open AccessAssessing the spatial relationship between mandibular third molars and the inferior alveolar canal using a deep learning-based approach: a proof-of-concept study
The distance between the mandibular third molar (M3) and the mandibular canal (MC) is a key factor in assessing the risk of injury to the inferior alveolar nerve (IAN). However, existing deep learning systems have not yet been able to accurately quantify the M3-MC distance in 3D space. The aim of this study was to develop and validate a deep learning-based system for accurate measurement of M3-MC spatial relationships in cone-beam computed tomography (CBCT) images and to evaluate its accuracy against conventional methods. We propose an innovative approach for low-resource environments, using DeeplabV3 + for semantic segmentation of CBCT-extracted 2D images, followed by multi-category 3D reconstruction and visualization. Based on the reconstruction model, we applied the KD-Tree algorithm to measure the spatial minimum distance between M3 and MC. Through internal validation with randomly selected CBCT images, we compared the differences between the AI system, conventional measurement methods on the CBCT, and the gold standard measured by senior experts. Statistical analysis was performed using one-way ANOVA with Tukey HSD post-hoc tests (p < 0.05), employing multiple error metrics for comprehensive evaluation. One-way ANOVA revealed significant differences among measurement methods. Subsequent Tukey HSD post-hoc tests showed significant differences between the AI reconstruction model and conventional methods. The measurement accuracy of the AI system compared to the gold standard was 0.19 for mean error (ME), 0.18 for mean absolute error (MAE), 0.69 for mean square error (MSE), 0.83 for root mean square error (RMSE), and 0.96 for coefficient of determination (R2) (p < 0.01). These results indicate that the proposed AI system is highly accurate and reliable in M3-MC distance measurement and provides a powerful tool for preoperative risk assessment of M3 extraction.
- Open Access
- 26 October 2024
- Published by Springer Nature in Molecular Medicine
- Vol. 30 (1) , 1-14
CHRDL1 inhibits OSCC metastasis via MAPK signaling-mediated inhibition of MED29
Background: CHRDL1 belongs to a novel class of mRNA molecules. Nonetheless, the specific biological functions and underlying mechanisms of CHRDL1 in oral squamous cell carcinoma (OSCC) remain largely unexplored. Methods: RT-qPCR and immunohistochemical staining were employed to assess the mRNA and protein expression levels of the MED29 gene in clinical samples of OSCC. Additionally, RT-qPCR and Western Blot analyses were conducted to investigate the mRNA and protein expression levels of the MED29 gene specifically in OSCC. The impact of MED29 on epithelial-mesenchymal transition (EMT), invasion, and migration of OSCC was evaluated through scratch assay, transwell assay, and immunofluorescence staining. Furthermore, wound healing assay and Transwell assay were utilized to examine whether CHRDL1 influences the malignant behavior of OSCC by modulating MED29 in vitro. The regulatory role of CHRDL1 on MED29 was further elucidated in vivo through a tail vein lung metastasis model in nude mice. Results: MED29 expression was elevated in tumor tissues of OSCC patients compared with adjacent cancer tissues. Moreover, in CAL27 and SCC25 cell lines, MED29 was upregulated and associated with increased cell migration and invasion abilities. Overexpression of MED29 facilitated EMT in OSCC cell lines, whereas knockdown of MED29 impeded EMT, resulting in diminished cell migration and invasion capacities. CHRDL1 exerted inhibitory effects on the expression of MED29, thereby suppressing EMT progression and consequently restraining the invasion and migration of OSCC cells. Furthermore, CHRDL1 mediated the inhibition of migration of OSCC cell lines to the OSCC through its regulation of MED29. Conclusions: MED29 facilitated the epithelial-mesenchymal transition process in OSCC, thereby promoting migration and invasion. On the other hand, CHRDL1 exerted inhibitory effects on the invasion and metastasis of OSCC by suppressing MED29 through the inhibition of the MAPK signaling pathway.
- 26 October 2024
- Published by Springer Nature in Molecular Medicine
- Vol. 30 (1) , 1-14
Open AccessCHRDL1 inhibits OSCC metastasis via MAPK signaling-mediated inhibition of MED29
Background: CHRDL1 belongs to a novel class of mRNA molecules. Nonetheless, the specific biological functions and underlying mechanisms of CHRDL1 in oral squamous cell carcinoma (OSCC) remain largely unexplored. Methods: RT-qPCR and immunohistochemical staining were employed to assess the mRNA and protein expression levels of the MED29 gene in clinical samples of OSCC. Additionally, RT-qPCR and Western Blot analyses were conducted to investigate the mRNA and protein expression levels of the MED29 gene specifically in OSCC. The impact of MED29 on epithelial-mesenchymal transition (EMT), invasion, and migration of OSCC was evaluated through scratch assay, transwell assay, and immunofluorescence staining. Furthermore, wound healing assay and Transwell assay were utilized to examine whether CHRDL1 influences the malignant behavior of OSCC by modulating MED29 in vitro. The regulatory role of CHRDL1 on MED29 was further elucidated in vivo through a tail vein lung metastasis model in nude mice. Results: MED29 expression was elevated in tumor tissues of OSCC patients compared with adjacent cancer tissues. Moreover, in CAL27 and SCC25 cell lines, MED29 was upregulated and associated with increased cell migration and invasion abilities. Overexpression of MED29 facilitated EMT in OSCC cell lines, whereas knockdown of MED29 impeded EMT, resulting in diminished cell migration and invasion capacities. CHRDL1 exerted inhibitory effects on the expression of MED29, thereby suppressing EMT progression and consequently restraining the invasion and migration of OSCC cells. Furthermore, CHRDL1 mediated the inhibition of migration of OSCC cell lines to the OSCC through its regulation of MED29. Conclusions: MED29 facilitated the epithelial-mesenchymal transition process in OSCC, thereby promoting migration and invasion. On the other hand, CHRDL1 exerted inhibitory effects on the invasion and metastasis of OSCC by suppressing MED29 through the inhibition of the MAPK signaling pathway.