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
大幅提高文件上传限制,最高150M (2024-4-1)

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
JamesPei应助冷静无声采纳,获得10
刚刚
1秒前
gj2221423发布了新的文献求助10
2秒前
SciGPT应助标致的乐驹采纳,获得10
2秒前
2秒前
222发布了新的文献求助20
3秒前
小二郎应助高兴的香薇采纳,获得10
3秒前
4秒前
丘比特应助司徒无剑采纳,获得10
4秒前
ruanyh发布了新的文献求助10
4秒前
思源应助黄老板采纳,获得10
4秒前
dui完成签到,获得积分10
5秒前
Orange应助淡定的往事采纳,获得10
6秒前
Yang22完成签到,获得积分10
6秒前
duan完成签到,获得积分10
6秒前
明理萃完成签到 ,获得积分10
6秒前
田様应助单薄的板凳采纳,获得10
7秒前
8秒前
香蕉觅云应助嗑瓜子传奇采纳,获得10
8秒前
9秒前
阿巴阿巴发布了新的文献求助10
9秒前
frap完成签到,获得积分10
9秒前
李健的小迷弟应助seusyy采纳,获得20
10秒前
小薇发布了新的文献求助10
11秒前
11秒前
yhr发布了新的文献求助10
11秒前
11秒前
月亮完成签到 ,获得积分10
12秒前
Ronggaz发布了新的文献求助10
12秒前
12秒前
14秒前
14秒前
cg完成签到 ,获得积分10
14秒前
Pyc完成签到 ,获得积分10
14秒前
四月胧完成签到,获得积分10
15秒前
华仔应助你还要猫怎样采纳,获得10
16秒前
16秒前
黄老板发布了新的文献求助10
18秒前
wt200001发布了新的文献求助10
19秒前
科研通AI2S应助TiO太阳采纳,获得10
19秒前
高分求助中
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Bayesian Models of Cognition:Reverse Engineering the Mind 888
Le dégorgement réflexe des Acridiens 800
Defense against predation 800
Very-high-order BVD Schemes Using β-variable THINC Method 568
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3134791
求助须知:如何正确求助?哪些是违规求助? 2785712
关于积分的说明 7773726
捐赠科研通 2441524
什么是DOI,文献DOI怎么找? 1297985
科研通“疑难数据库(出版商)”最低求助积分说明 625075
版权声明 600825