Weiliang Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weiliang Wu has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Hao Liu
The Central Laboratory Peking University School and Hospital of Stomatology Beijing China
2 shared publications - Ranli Gu
Department of Prosthodontics, Peking University School and Hospital of Stomatology, National Laboratory for Digital and Material Technology of Stomatology, Beijing Key Laboratory of Digital Stomatology, National Clinical Research Center for Oral Diseases, 22 Zhongguancun South Avenue, Beijing, 100081, People's Republic of China
2 shared publications - Yunsong Liu
Department of Prosthodontics, National Center of Stomatology & National Clinical Research Center for Oral Diseases & Research Center of Oral Biomaterials and Digital Medical Devices & Beijing Key Laboratory of Digital Stomatology & Beijing Key Laboratory for Intelligent Biomanufacturing and Regeneration of Craniofacial Tissues & NHC Key Laboratory of Digital Stomatology, Peking University School and Hospital of Stomatology, Beijing, China
2 shared publications Changfu Xie
Fujian Key Laboratory of Oral Diseases and Fujian Provincial Engineering Research Center of Oral Biomaterial and Stomatological Key laboratory of Fujian College and University, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, China
1 shared publication- Changfu Xie
Fujian Key Laboratory of Oral Diseases & Fujian Provincial Engineering Research Center of Oral Biomaterial & Stomatological Key Laboratory of Fujian College and University, School and Hospital of Stomatology, Fujian Medical University Fuzhou China
1 shared publication Dandan Xia
1 shared publication
Latest Publications
- Open Access
- 11 August 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (16) , 6225
MRI-Based Deep Learning Image Classification for Screening Temporomandibular Joint Degenerative Joint Disease
Background: This study aimed to develop and evaluate a deep learning (DL) algorithm based on magnetic resonance imaging (MRI) for the classification of temporomandibular joint degenerative joint disease (TMJDJD), thereby exploring its potential role in assisting cone-beam computed tomography (CBCT) examinations and minimizing patient radiation exposure. Methods: A retrospective analysis was conducted on 104 patients who had undergone both MRI and CBCT examinations of the temporomandibular joint. A total of 1769 sagittal and 1448 coronal MRI images were collected. After image preprocessing, the datasets were grouped according to different imaging features. Three DL frameworks—ResNet101, DenseNet201, and MobileNetV2—were developed to classify TMJDJD using various MRI image categories. The classification performance of these models was evaluated using accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), and the results were compared with classifications made by two senior clinical experts in a blinded image-level reader experiment. Results: DenseNet201 achieved the best performance in the sagittal (Sg) group, with an accuracy of 80.11%, precision of 80.26%, recall of 75.31%, and an MCC of 0.60. DenseNet201 achieved the best performance among the evaluated DL models, with higher overall performance metrics than ResNet101 and MobileNetV2. In a constrained image-level reader comparison, DenseNet201 demonstrated comparable overall agreement metrics to the two experts, although one expert achieved higher recall and a lower false-negative rate. t-Distributed Stochastic Neighbor Embedding (t-SNE) and training curve analyses confirmed that DenseNet201 demonstrated superior feature extraction capability and a more stable training process. Grouping MRI images, however, did not improve model accuracy. Conclusions: DenseNet201 showed preliminary potential for MRI-based TMJDJD classification, particularly on sagittal images. Based on image-level classification results, the model may provide preliminary support for identifying MRI findings associated with TMJDJD and assisting decisions regarding further CBCT evaluation.
- 11 August 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (16) , 6225
Open AccessMRI-Based Deep Learning Image Classification for Screening Temporomandibular Joint Degenerative Joint Disease
Background: This study aimed to develop and evaluate a deep learning (DL) algorithm based on magnetic resonance imaging (MRI) for the classification of temporomandibular joint degenerative joint disease (TMJDJD), thereby exploring its potential role in assisting cone-beam computed tomography (CBCT) examinations and minimizing patient radiation exposure. Methods: A retrospective analysis was conducted on 104 patients who had undergone both MRI and CBCT examinations of the temporomandibular joint. A total of 1769 sagittal and 1448 coronal MRI images were collected. After image preprocessing, the datasets were grouped according to different imaging features. Three DL frameworks—ResNet101, DenseNet201, and MobileNetV2—were developed to classify TMJDJD using various MRI image categories. The classification performance of these models was evaluated using accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), and the results were compared with classifications made by two senior clinical experts in a blinded image-level reader experiment. Results: DenseNet201 achieved the best performance in the sagittal (Sg) group, with an accuracy of 80.11%, precision of 80.26%, recall of 75.31%, and an MCC of 0.60. DenseNet201 achieved the best performance among the evaluated DL models, with higher overall performance metrics than ResNet101 and MobileNetV2. In a constrained image-level reader comparison, DenseNet201 demonstrated comparable overall agreement metrics to the two experts, although one expert achieved higher recall and a lower false-negative rate. t-Distributed Stochastic Neighbor Embedding (t-SNE) and training curve analyses confirmed that DenseNet201 demonstrated superior feature extraction capability and a more stable training process. Grouping MRI images, however, did not improve model accuracy. Conclusions: DenseNet201 showed preliminary potential for MRI-based TMJDJD classification, particularly on sagittal images. Based on image-level classification results, the model may provide preliminary support for identifying MRI findings associated with TMJDJD and assisting decisions regarding further CBCT evaluation.
- 3 January 2026
- Published by Springer Nature in Cellulose
- Vol. 33 (2) , 985-1000
ZIF-8 functionalized polysaccharide-based mushroom with water-triggered shape memory and antibacterial activity for noncompressible bleeding control
- 3 January 2026
- Published by Springer Nature in Cellulose
- Vol. 33 (2) , 985-1000
ZIF-8 functionalized polysaccharide-based mushroom with water-triggered shape memory and antibacterial activity for noncompressible bleeding control
- Open Access
- 1 April 2025
- Published by Elsevier in Regenerative Therapy
- Vol. 29, 262-270
Apoptotic vesicles inhibit bone marrow adiposity via wnt/β-catenin signaling
- 1 April 2025
- Published by Elsevier in Regenerative Therapy
- Vol. 29, 262-270
Open AccessApoptotic vesicles inhibit bone marrow adiposity via wnt/β-catenin signaling
- Open Access
- 1 April 2025
- Published by KEAI Publishing in Journal of Magnesium and Alloys
- Vol. 13 (4) , 1561-1578
Magnesium-reinforced sandwich structured composite membranes promote osteogenesis
- 1 April 2025
- Published by KEAI Publishing in Journal of Magnesium and Alloys
- Vol. 13 (4) , 1561-1578
Open AccessMagnesium-reinforced sandwich structured composite membranes promote osteogenesis
- 13 April 2023
- Published by Elsevier in Journal of Stomatology Oral and Maxillofacial Surgery
- Vol. 124 (6) , 101469
Dual-guide template–guided socket-shield preparation and immediate implantation in maxillary anterior region implant surgery
- 13 April 2023
- Published by Elsevier in Journal of Stomatology Oral and Maxillofacial Surgery
- Vol. 124 (6) , 101469
Dual-guide template–guided socket-shield preparation and immediate implantation in maxillary anterior region implant surgery
- Open Access
- 19 July 2019
- Published by Springer Nature in Stem Cell Research & Therapy
- Vol. 10 (1) , 1-14
Low concentration flufenamic acid enhances osteogenic differentiation of mesenchymal stem cells and suppresses bone loss by inhibition of the NF-κB signaling pathway
As the representative of fenamic acids, an important group of NSAIDs, flufenamic acid (FFA) has been used for anti-inflammation and analgesia in the clinic. Recently, researches have focused on the role of some members of NSAIDs in promoting osteogenesis. However, little attention has been paid to the subgroup of fenamic acids, and it remains unclear whether FFA and other fenamic acids could regulate mesenchymal stem cells’ (MSCs) lineage commitment and bone regeneration. Here we treated two kinds of human MSCs with FFA at different concentrations in vitro and examined the effect of FFA on osteogenic differentiation of human MSCs. This was followed by heterotopic bone formation assay in nude mice. In addition, ovariectomized and aged mice were used as osteoporotic models to test the effect of FFA on osteoporosis. Besides, activators and inhibitor of nuclear factor-κB (NF-κB) signaling pathway and western blot were used to clarify the mechanism of the promoting effect of low concentration FFA on osteogenesis. Our results indicated that low concentrations of FFA could significantly enhance osteogenic differentiation of human MSCs in vitro, as well as in vivo. In addition, FFA treatment suppressed bone loss in ovariectomized and aged mice. Mechanistically, FFA at low concentrations promoted osteogenesis differentiation of human MSCs by inhibition of the NF-κB signaling pathway. Collectively, our study suggested that low concentration FFA could be used in bone tissue engineering or osteoporosis by promoting osteogenic differentiation of human MSCs.
- 19 July 2019
- Published by Springer Nature in Stem Cell Research & Therapy
- Vol. 10 (1) , 1-14
Open AccessLow concentration flufenamic acid enhances osteogenic differentiation of mesenchymal stem cells and suppresses bone loss by inhibition of the NF-κB signaling pathway
As the representative of fenamic acids, an important group of NSAIDs, flufenamic acid (FFA) has been used for anti-inflammation and analgesia in the clinic. Recently, researches have focused on the role of some members of NSAIDs in promoting osteogenesis. However, little attention has been paid to the subgroup of fenamic acids, and it remains unclear whether FFA and other fenamic acids could regulate mesenchymal stem cells’ (MSCs) lineage commitment and bone regeneration. Here we treated two kinds of human MSCs with FFA at different concentrations in vitro and examined the effect of FFA on osteogenic differentiation of human MSCs. This was followed by heterotopic bone formation assay in nude mice. In addition, ovariectomized and aged mice were used as osteoporotic models to test the effect of FFA on osteoporosis. Besides, activators and inhibitor of nuclear factor-κB (NF-κB) signaling pathway and western blot were used to clarify the mechanism of the promoting effect of low concentration FFA on osteogenesis. Our results indicated that low concentrations of FFA could significantly enhance osteogenic differentiation of human MSCs in vitro, as well as in vivo. In addition, FFA treatment suppressed bone loss in ovariectomized and aged mice. Mechanistically, FFA at low concentrations promoted osteogenesis differentiation of human MSCs by inhibition of the NF-κB signaling pathway. Collectively, our study suggested that low concentration FFA could be used in bone tissue engineering or osteoporosis by promoting osteogenic differentiation of human MSCs.