MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention

In the process of orthodontic treatment, it is a very important step to accurately segment each tooth and jaw model with computer assistance. The use of deep learning technology methods for tooth segmentation can not only save a lot of manual interaction and time cost but also improve the treatment...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanqing Hu, Zhengxun Li, Weichao Gao
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10063862/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850246024028749824
author Hanqing Hu
Zhengxun Li
Weichao Gao
author_facet Hanqing Hu
Zhengxun Li
Weichao Gao
author_sort Hanqing Hu
collection DOAJ
description In the process of orthodontic treatment, it is a very important step to accurately segment each tooth and jaw model with computer assistance. The use of deep learning technology methods for tooth segmentation can not only save a lot of manual interaction and time cost but also improve the treatment effect. 3D tooth segmentation is a hot topic of interest for international related scholars, and some end-to-end tooth segmentation methods based on dental mesh scanning models have been emerging in recent years. Due to the limited variety of existing models, they are not well suited for different 3D segmentation scenarios, and the feature extraction capability and segmentation effect of these models still need to be improved. In this paper, we propose a novel end-to-end tooth segmentation method, MPCNet, which adds multi-scale mesh density information to the input layer, uses position encoding and channel attention mechanism to improve MeshSegNet, and uses graph-cut post-processing to perform 3D tooth segmentation in real scenes. The effectiveness of MPCNet is evaluated on a real 3D scanned tooth segmentation dataset, which significantly outperforms the current mainstream segmentation methods.
format Article
id doaj-art-e247e84c87374164bd53739d7d49b3c1
institution OA Journals
issn 2169-3536
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e247e84c87374164bd53739d7d49b3c12025-08-20T01:59:17ZengIEEEIEEE Access2169-35362023-01-0111233262333410.1109/ACCESS.2023.325420610063862MPCNet: Improved MeshSegNet Based on Position Encoding and Channel AttentionHanqing Hu0Zhengxun Li1https://orcid.org/0000-0002-2898-1758Weichao Gao2School of Economics and Management, Beijing Information Science & Technology University, Beijing, ChinaSchool of Economics and Management, Beijing Information Science & Technology University, Beijing, ChinaSchool of Economics and Management, Beijing Information Science & Technology University, Beijing, ChinaIn the process of orthodontic treatment, it is a very important step to accurately segment each tooth and jaw model with computer assistance. The use of deep learning technology methods for tooth segmentation can not only save a lot of manual interaction and time cost but also improve the treatment effect. 3D tooth segmentation is a hot topic of interest for international related scholars, and some end-to-end tooth segmentation methods based on dental mesh scanning models have been emerging in recent years. Due to the limited variety of existing models, they are not well suited for different 3D segmentation scenarios, and the feature extraction capability and segmentation effect of these models still need to be improved. In this paper, we propose a novel end-to-end tooth segmentation method, MPCNet, which adds multi-scale mesh density information to the input layer, uses position encoding and channel attention mechanism to improve MeshSegNet, and uses graph-cut post-processing to perform 3D tooth segmentation in real scenes. The effectiveness of MPCNet is evaluated on a real 3D scanned tooth segmentation dataset, which significantly outperforms the current mainstream segmentation methods.https://ieeexplore.ieee.org/document/10063862/Tooth segmentation3D deep learningvirtual orthodontics3D semantic segmentationattention mechanism
spellingShingle Hanqing Hu
Zhengxun Li
Weichao Gao
MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention
IEEE Access
Tooth segmentation
3D deep learning
virtual orthodontics
3D semantic segmentation
attention mechanism
title MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention
title_full MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention
title_fullStr MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention
title_full_unstemmed MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention
title_short MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention
title_sort mpcnet improved meshsegnet based on position encoding and channel attention
topic Tooth segmentation
3D deep learning
virtual orthodontics
3D semantic segmentation
attention mechanism
url https://ieeexplore.ieee.org/document/10063862/
work_keys_str_mv AT hanqinghu mpcnetimprovedmeshsegnetbasedonpositionencodingandchannelattention
AT zhengxunli mpcnetimprovedmeshsegnetbasedonpositionencodingandchannelattention
AT weichaogao mpcnetimprovedmeshsegnetbasedonpositionencodingandchannelattention