Fulai Yuan
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
Fulai Yuan has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Bei Zhang
College of Science, Chongqing University of Technology, Chongqing, China
3 shared publications - Ning Dai
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
2 shared publications Qing Yu
Nanjing Stomatological Hospital, Medical School of Nanjing University, Nanjing, People's Republic of China
2 shared publications- Yuchun Sun
Chinese Academy of Medical Sciences & NMPA Key Laboratory for Dental Materials
2 shared publications Hao Liu
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
1 shared publicationHualiang Xiao
Department of Pathology, Daping Hospital, Army Medical University, Chongqing, China
1 shared publication
Latest Publications
- 27 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-15
DCA-DAFFNet: An End-to-End Network With Deformable Fusion Attention and Deep Adaptive Feature Fusion for Laryngeal Tumor Grading From Histopathology Images
Laryngeal Tumor Grading is a challenge task for computer-aided clinical diagnosis (CACD), mainly because the nuclei in histopathological images have large differences in shape and distribution, and the complex spatial relationship between nuclei. However, the existing CNN-based tumor grading models cannot adaptively represent the nuclei with variable morphology, and lack of effective modeling for the semantic information of nuclear spatial location. Therefore, we propose an end-to-end network (DCA-DAFFNet) with deformable convolution guided attention block (DCAB) and deep adaptive feature fusion (DAFF) to improve the grading ability. Specifically, a novel DCAB is designed to represent variable nuclei adaptively with more flexible receptive fields of deformable convolution. Besides, to solve the problem of poor semantic information modeling ability of nuclear spatial location, the vision transformer (ViT) block is incorporated into the attention-based CNN models to construct DCA-DAFFNet with powerful global information representation capability. Furthermore, a DAFF method containing multi-kernel max mean discrepancy (MK-MMD) and adaptive fusion block is proposed to solve the problem of negative fusion in DCA-DAFFNet. Extensive experiments results demonstrate the effectiveness of DCA-DAFFNet, and its average grading accuracy is increased to 90.78% ( ↑ 11.80%). By comparing visualization results, our proposed DCA-DAFFNet can pay more attention to the heterogeneous nuclei (polymorphic-nucleus, mega-nucleus, etc.) concerned by pathologists, which shows that our method more interpretable and human-computer interactive.
- 27 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-15
DCA-DAFFNet: An End-to-End Network With Deformable Fusion Attention and Deep Adaptive Feature Fusion for Laryngeal Tumor Grading From Histopathology Images
Laryngeal Tumor Grading is a challenge task for computer-aided clinical diagnosis (CACD), mainly because the nuclei in histopathological images have large differences in shape and distribution, and the complex spatial relationship between nuclei. However, the existing CNN-based tumor grading models cannot adaptively represent the nuclei with variable morphology, and lack of effective modeling for the semantic information of nuclear spatial location. Therefore, we propose an end-to-end network (DCA-DAFFNet) with deformable convolution guided attention block (DCAB) and deep adaptive feature fusion (DAFF) to improve the grading ability. Specifically, a novel DCAB is designed to represent variable nuclei adaptively with more flexible receptive fields of deformable convolution. Besides, to solve the problem of poor semantic information modeling ability of nuclear spatial location, the vision transformer (ViT) block is incorporated into the attention-based CNN models to construct DCA-DAFFNet with powerful global information representation capability. Furthermore, a DAFF method containing multi-kernel max mean discrepancy (MK-MMD) and adaptive fusion block is proposed to solve the problem of negative fusion in DCA-DAFFNet. Extensive experiments results demonstrate the effectiveness of DCA-DAFFNet, and its average grading accuracy is increased to 90.78% ( ↑ 11.80%). By comparing visualization results, our proposed DCA-DAFFNet can pay more attention to the heterogeneous nuclei (polymorphic-nucleus, mega-nucleus, etc.) concerned by pathologists, which shows that our method more interpretable and human-computer interactive.
- 10 February 2020
- Published by Wiley in International Journal for Numerical Methods in Biomedical Engineering
- Vol. 36 (5) , e3321
Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks
The tooth defect is a frequently occurring disease within the field of dental clinic. However, the traditional manual restoration for the defective tooth needs an especially long treatment time, and dental computer aided design and manufacture (CAD/CAM) systems fail to restore the personalized anatomical features of natural teeth. Aiming to address the shortcomings of existed methods, this article proposes an intelligent network model for designing tooth crown surface based on conditional generative adversarial networks. Then, the data set for training the network model is constructed via generating depth maps of 3D tooth models scanned by the intraoral. Through adversarial training, the network model is able to generate tooth occlusal surface under the constraint of the space occlusal relationship, the perceptual loss, and occlusal groove filter loss. Finally, we carry out the assessment experiments for the quality of the occlusal surface and the occlusal relationship with the opposing tooth. The experimental results demonstrate that our method can automatically reconstruct the personalized anatomical features on occlusal surface and shorten the treatment time while restoring the full functionality of the defective tooth.
- 10 February 2020
- Published by Wiley in International Journal for Numerical Methods in Biomedical Engineering
- Vol. 36 (5) , e3321
Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks
The tooth defect is a frequently occurring disease within the field of dental clinic. However, the traditional manual restoration for the defective tooth needs an especially long treatment time, and dental computer aided design and manufacture (CAD/CAM) systems fail to restore the personalized anatomical features of natural teeth. Aiming to address the shortcomings of existed methods, this article proposes an intelligent network model for designing tooth crown surface based on conditional generative adversarial networks. Then, the data set for training the network model is constructed via generating depth maps of 3D tooth models scanned by the intraoral. Through adversarial training, the network model is able to generate tooth occlusal surface under the constraint of the space occlusal relationship, the perceptual loss, and occlusal groove filter loss. Finally, we carry out the assessment experiments for the quality of the occlusal surface and the occlusal relationship with the opposing tooth. The experimental results demonstrate that our method can automatically reconstruct the personalized anatomical features on occlusal surface and shorten the treatment time while restoring the full functionality of the defective tooth.
- 22 July 2019
- Published by Wiley in International Journal for Numerical Methods in Biomedical Engineering
- Vol. 35 (10) , e3241
The extraction method of tooth preparation margin line based on S‐Octree CNN
The tooth preparation margin line has a significant impact on the marginal fitness for dental restoration. Among the previous methods, the extraction of margin line mainly relies on manual interaction, which is complicated and inefficient. Therefore, we propose a method to extract the margin line with the convolutional neural network based on sparse octree (S‐Octree) structure. First, the dental preparations are rotated to augment the dataset. Second, the preparation models are treated as the sparse point cloud with labels through the spatial partition method of the S‐Octree. Then, based on the feature line, the dental preparation point cloud is automatically divided into two regions by the convolutional neural network (CNN). Third, in order to obtain the margin line, we adopt some methods such as the dense condition random field (dense CRF), point cloud reconstruction, and back projection to the original dental preparation model. Finally, based on the measurement indicators of accuracy, sensitivity, and specificity, the average accuracy of the label predicted by the network model can reach 97.43%. The experimental results show that our method can automatically accomplish the extraction of the tooth preparation margin line.
- 22 July 2019
- Published by Wiley in International Journal for Numerical Methods in Biomedical Engineering
- Vol. 35 (10) , e3241
The extraction method of tooth preparation margin line based on S‐Octree CNN
The tooth preparation margin line has a significant impact on the marginal fitness for dental restoration. Among the previous methods, the extraction of margin line mainly relies on manual interaction, which is complicated and inefficient. Therefore, we propose a method to extract the margin line with the convolutional neural network based on sparse octree (S‐Octree) structure. First, the dental preparations are rotated to augment the dataset. Second, the preparation models are treated as the sparse point cloud with labels through the spatial partition method of the S‐Octree. Then, based on the feature line, the dental preparation point cloud is automatically divided into two regions by the convolutional neural network (CNN). Third, in order to obtain the margin line, we adopt some methods such as the dense condition random field (dense CRF), point cloud reconstruction, and back projection to the original dental preparation model. Finally, based on the measurement indicators of accuracy, sensitivity, and specificity, the average accuracy of the label predicted by the network model can reach 97.43%. The experimental results show that our method can automatically accomplish the extraction of the tooth preparation margin line.