Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans

Wu, Tai-Hsien; Lee, Sang‐Hee; Pastewait, Matthew; Piers, Christian; Liu, Jie; Wang, Fang; Wang, Li; Jackson, Christina; Chao, Weilun; Shen, Dinggang; Ko, Ching‐Chang

doi:10.1109/tmi.2022.3180343

Cited by 42 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies that did apply deep learning for landmark detection on 3D meshes mostly focused on landmarking on intra-oral scans. Wu et al utilized a two-stage deep learning framework for the prediction of 44 dental landmarks and achieved a mean absolute error of 0.623 ± 0.718 mm 21 . DentalPointNet, consisting of two sub-networks; a region proposal network and a refinement network, as described by Lang et al 22 , achieved an average localization error of 0.24 mm for the detection of 68 landmarks.…”

Section: Discussionmentioning

confidence: 99%

Fully automated landmarking and facial segmentation on 3D photographs

Berends,

Bielevelt,

Schreurs

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Three-dimensional facial stereophotogrammetry provides a detailed representation of craniofacial soft tissue without the use of ionizing radiation. While manual annotation of landmarks serves as the current gold standard for cephalometric analysis, it is a time-consuming process and is prone to human error. The aim in this study was to develop and evaluate an automated cephalometric annotation method using a deep learning-based approach. Ten landmarks were manually annotated on 2897 3D facial photographs. The automated landmarking workflow involved two successive DiffusionNet models. The dataset was randomly divided into a training and test dataset. The precision of the workflow was evaluated by calculating the Euclidean distances between the automated and manual landmarks and compared to the intra-observer and inter-observer variability of manual annotation and a semi-automated landmarking method. The workflow was successful in 98.6% of all test cases. The deep learning-based landmarking method achieved precise and consistent landmark annotation. The mean precision of 1.69 ± 1.15 mm was comparable to the inter-observer variability (1.31 ± 0.91 mm) of manual annotation. Automated landmark annotation on 3D photographs was achieved with the DiffusionNet-based approach. The proposed method allows quantitative analysis of large datasets and may be used in diagnosis, follow-up, and virtual surgical planning.

show abstract

Section: Discussionmentioning

confidence: 99%

Fully automated landmarking and facial segmentation on 3D photographs

Berends,

Bielevelt,

Schreurs

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Recent studies have employed deep learning for automatic 3D tooth segmentation, 16 , 17 , 18 , 19 , 20 , 59 , 61 in which deep neural networks are used to conduct segmentation either on mesh or point clouds. The performance has been further boosted by methods that design specific neural network architectures for end-to-end tooth segmentation, such as MeshSegNet, 37 , 62 DCNet, 16 TSGCNet, 38 and Mask-MCNet.…”

Section: Discussionmentioning

confidence: 99%

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction

et al. 2023

View full text Add to dashboard Cite

“…In addition, Im et al proposed a dynamic-graph convolutional neural network (DGCNN) to automate tooth segmentation in digital models, achieving superior accuracy and reduced computational time compared to the other two commercially available pieces of software: OrthoAnalyzer (ver.1.7.1.3) and Autolign (ver.1.6.2.1) [79]. Beyond that, the accurate segmentation of teeth and the recognition of landmarks on teeth are crucial for automated dental analysis, and significant advancements have been consistently achieved in this domain, hopefully paving the way for further clinical applications [80][81][82][83][84].…”

Section: Dental Analysismentioning

confidence: 99%

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

Liu,

Zhang,

Shan

2023

Healthcare

View full text Add to dashboard Cite

In recent years, there has been the notable emergency of artificial intelligence (AI) as a transformative force in multiple domains, including orthodontics. This review aims to provide a comprehensive overview of the present state of AI applications in orthodontics, which can be categorized into the following domains: (1) diagnosis, including cephalometric analysis, dental analysis, facial analysis, skeletal-maturation-stage determination and upper-airway obstruction assessment; (2) treatment planning, including decision making for extractions and orthognathic surgery, and treatment outcome prediction; and (3) clinical practice, including practice guidance, remote care, and clinical documentation. We have witnessed a broadening of the application of AI in orthodontics, accompanied by advancements in its performance. Additionally, this review outlines the existing limitations within the field and offers future perspectives.

show abstract

Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans

Cited by 42 publications

References 30 publications

Fully automated landmarking and facial segmentation on 3D photographs

Fully automated landmarking and facial segmentation on 3D photographs

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

Contact Info

Product

Resources

About