Efficient Computer-Aided Design of Dental Inlay Restoration: A Deep Adversarial Framework

Tian, Sukun; Wang, Miaohui; Dai, Ning; Sun, Yuchun; Xie, Weixin; Qin, Jing

doi:10.1109/tmi.2021.3077334

Cited by 28 publications

(27 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the running time of DLUP is longer than the other non-joint prediction methods in this paper. [21], [27] 1.579 0.21h Non-joint WGAN-FCNN [26], [27] 2.043 0.25h Non-joint DLUP [25], [27] 4.986 0.33h Non-joint LSGAN-MLR [25], [33] 2.062 0.2h…”

Section: B Comparison and Analysis Of Experimental Resultsmentioning

confidence: 99%

“…In [24], Classification Enhancement GAN (CEGAN) is pro-posed to solve the problem of data imbalance in classification, which enhances the accuracy of target prediction in the case of data imbalance. Wasserstein Generative Adversarial Network (WGAN) is used to repair broken teeth [26]. LSGAN adopts the least squares loss in G and D. The image quality generated by LSGAN is higher than that of GAN, and the learning process is also more stable [25].…”

Section: Related Workmentioning

confidence: 99%

“…SSF puts the preproportion raw materials into the fermentation tanks, and the a. Non-joint GAN-FCNN b. Non-joint WGAN-FCNN c. Non-joint DLUP d. Non-joint LSGAN-MLR Fig. 9: ALC prediction results based on the non-joint GAN-FCNN [21], [27], non-joint WGAN-FCNN [26], [27], nonjoint DLUP [25], [27], and non-joint LSGAN-MLR [25], [33]. fermentation process can not be controlled or changed any more.…”

Section: Engineering Applicationmentioning

confidence: 99%

See 2 more Smart Citations

DLUP: A Deep Learning Utility Prediction Scheme for Solid-State Fermentation Services in IIoT

Wang

Pang

Ding

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Section: B Comparison and Analysis Of Experimental Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Engineering Applicationmentioning

confidence: 99%

See 1 more Smart Citation

DLUP: A Deep Learning Utility Prediction Scheme for Solid-State Fermentation Services in IIoT

Wang

Pang

Ding

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

“…Therefore, this will provide basic conditions for the exploration of intelligent dental restoration technology. However, developing an intelligent dental restoration method is challenging: (1) it is lack of large-scale oral clinical database to train an intelligent network for defective teeth restoration [ 10 ]; (2) how to design a personalized dental prosthesis satisfying the normal mastication function of patient; and (3) the great difference in tooth morphology among individuals increases the difficulty of training the network model.…”

Section: Introductionmentioning

confidence: 99%

A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction

Tian

Huang

et al. 2022

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

Objective. Restoring the correct masticatory function of partially edentulous patient is a challenging task primarily due to the complex tooth morphology between individuals. Although some deep learning-based approaches have been proposed for dental restorations, most of them do not consider the influence of dental biological characteristics for the occlusal surface reconstruction. Description. In this article, we propose a novel dual discriminator adversarial learning network to address these challenges. In particular, this network architecture integrates two models: a dilated convolutional-based generative model and a dual global-local discriminative model. While the generative model adopts dilated convolution layers to generate a feature representation that preserves clear tissue structure, the dual discriminative model makes use of two discriminators to jointly distinguish whether the input is real or fake. While the global discriminator focuses on the missing teeth and adjacent teeth to assess whether it is coherent as a whole, the local discriminator aims only at the defective teeth to ensure the local consistency of the generated dental crown. Results. Experiments on 1000 real-world patient dental samples demonstrate the effectiveness of our method. For quantitative comparison, the image quality metrics are used to measure the similarity of the generated occlusal surface, and the root mean square between the generated result and the target crown calculated by our method is 0.114 mm. In qualitative analysis, the proposed approach can generate more reasonable dental biological morphology. Conclusion. The results demonstrate that our method significantly outperforms the state-of-the-art methods in occlusal surface reconstruction. Importantly, the designed occlusal surface has enough anatomical morphology of natural teeth and superior clinical application value.

show abstract

“…In addition, with the rapid development of artificial intelligence technology, machine learning has been widely used in various segmentation scenes (7)(8)(9) and provides a new impetus for the retinal vessel segmentation task. Various excellent machine learning-based automatic segmentation methods (10) have been designed, which can be divided into two categories (11): the unsupervised methods and the supervised methods.…”

Section: Introductionmentioning

confidence: 99%

A Few-Shot Learning-Based Retinal Vessel Segmentation Method for Assisting in the Central Serous Chorioretinopathy Laser Surgery

Shen

Wan

et al. 2022

Front. Med.

View full text Add to dashboard Cite

BackgroundThe location of retinal vessels is an important prerequisite for Central Serous Chorioretinopathy (CSC) Laser Surgery, which does not only assist the ophthalmologist in marking the location of the leakage point (LP) on the fundus color image but also avoids the damage of the laser spot to the vessel tissue, as well as the low efficiency of the surgery caused by the absorption of laser energy by retinal vessels. In acquiring an excellent intra- and cross-domain adaptability, the existing deep learning (DL)-based vessel segmentation scheme must be driven by big data, which makes the densely annotated work tedious and costly.MethodsThis paper aims to explore a new vessel segmentation method with a few samples and annotations to alleviate the above problems. Firstly, a key solution is presented to transform the vessel segmentation scene into the few-shot learning task, which lays a foundation for the vessel segmentation task with a few samples and annotations. Then, we improve the existing few-shot learning framework as our baseline model to adapt to the vessel segmentation scenario. Next, the baseline model is upgraded from the following three aspects: (1) A multi-scale class prototype extraction technique is designed to obtain more sufficient vessel features for better utilizing the information from the support images; (2) The multi-scale vessel features of the query images, inferred by the support image class prototype information, are gradually fused to provide more effective guidance for the vessel extraction tasks; and (3) A multi-scale attention module is proposed to promote the consideration of the global information in the upgraded model to assist vessel localization. Concurrently, the integrated framework is further conceived to appropriately alleviate the low performance of a single model in the cross-domain vessel segmentation scene, enabling to boost the domain adaptabilities of both the baseline and the upgraded models.ResultsExtensive experiments showed that the upgraded operation could further improve the performance of vessel segmentation significantly. Compared with the listed methods, both the baseline and the upgraded models achieved competitive results on the three public retinal image datasets (i.e., CHASE_DB, DRIVE, and STARE). In the practical application of private CSC datasets, the integrated scheme partially enhanced the domain adaptabilities of the two proposed models.

show abstract

Efficient Computer-Aided Design of Dental Inlay Restoration: A Deep Adversarial Framework

Cited by 28 publications

References 36 publications

DLUP: A Deep Learning Utility Prediction Scheme for Solid-State Fermentation Services in IIoT

DLUP: A Deep Learning Utility Prediction Scheme for Solid-State Fermentation Services in IIoT

A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction

A Few-Shot Learning-Based Retinal Vessel Segmentation Method for Assisting in the Central Serous Chorioretinopathy Laser Surgery

Contact Info

Product

Resources

About