Deep Multi-Scale Mesh Feature Learning for Automated Labeling of Raw Dental Surfaces From 3D Intraoral Scanners

人工智能 计算机科学 分割 计算机视觉 模式识别(心理学) 深度学习 实体造型 齿面 背景(考古学) 牙科 地质学 医学 古生物学
作者
Chunfeng Lian,Li Wang,Tai‐Hsien Wu,Fan Wang,Pew‐Thian Yap,Ching‐Chang Ko,Dinggang Shen
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:39 (7): 2440-2450 被引量:94
标识
DOI:10.1109/tmi.2020.2971730
摘要

Precisely labeling teeth on digitalized 3D dental surface models is the precondition for tooth position rearrangements in orthodontic treatment planning. However, it is a challenging task primarily due to the abnormal and varying appearance of patients' teeth. The emerging utilization of intraoral scanners (IOSs) in clinics further increases the difficulty in automated tooth labeling, as the raw surfaces acquired by IOS are typically low-quality at gingival and deep intraoral regions. In recent years, some pioneering end-to-end methods (e.g., PointNet) have been proposed in the communities of computer vision and graphics to consume directly raw surface for 3D shape segmentation. Although these methods are potentially applicable to our task, most of them fail to capture fine-grained local geometric context that is critical to the identification of small teeth with varying shapes and appearances. In this paper, we propose an end-to-end deep-learning method, called MeshSegNet, for automated tooth labeling on raw dental surfaces. Using multiple raw surface attributes as inputs, MeshSegNet integrates a series of graph-constrained learning modules along its forward path to hierarchically extract multi-scale local contextual features. Then, a dense fusion strategy is applied to combine local-to-global geometric features for the learning of higher-level features for mesh cell annotation. The predictions produced by our MeshSegNet are further post-processed by a graph-cut refinement step for final segmentation. We evaluated MeshSegNet using a real-patient dataset consisting of raw maxillary surfaces acquired by 3D IOS. Experimental results, performed 5-fold cross-validation, demonstrate that MeshSegNet significantly outperforms state-of-the-art deep learning methods for 3D shape segmentation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
qwe发布了新的文献求助10
1秒前
thy完成签到,获得积分10
3秒前
ding应助汪汪采纳,获得10
5秒前
6秒前
高高的天晴完成签到,获得积分10
7秒前
7秒前
8秒前
9秒前
菠菜发布了新的文献求助10
9秒前
篮球发布了新的文献求助10
11秒前
CodeCraft应助qwe采纳,获得10
11秒前
18062677029完成签到 ,获得积分10
11秒前
情怀应助隐形鱼采纳,获得10
12秒前
wcy发布了新的文献求助10
12秒前
cx111发布了新的文献求助10
12秒前
13秒前
coralreefx发布了新的文献求助30
13秒前
JamesPei应助lixoii采纳,获得10
14秒前
2213sss完成签到,获得积分10
14秒前
任娜完成签到,获得积分10
15秒前
果果发布了新的文献求助10
15秒前
15秒前
宫城发布了新的文献求助10
16秒前
稚鱼发布了新的文献求助10
17秒前
脑洞疼应助火桑花采纳,获得10
17秒前
XLL小绿绿发布了新的文献求助10
18秒前
19秒前
20秒前
认真晓灵完成签到,获得积分10
20秒前
20秒前
小蘑菇应助MrRen采纳,获得30
20秒前
能干忆霜完成签到,获得积分10
20秒前
东溟渔夫发布了新的文献求助10
21秒前
mnhkj发布了新的文献求助20
23秒前
23秒前
隐形鱼发布了新的文献求助10
26秒前
26秒前
桐桐应助飞翔的桃仔采纳,获得10
27秒前
27秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Effective Learning and Mental Wellbeing 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975986
求助须知:如何正确求助?哪些是违规求助? 3520289
关于积分的说明 11202025
捐赠科研通 3256778
什么是DOI,文献DOI怎么找? 1798453
邀请新用户注册赠送积分活动 877605
科研通“疑难数据库(出版商)”最低求助积分说明 806482