Paper_v4.pdf (1.53 MB)
Teeth category classification via seven-layer deep convolutional neural network with max pooling and global average pooling
journal contribution
posted on 2020-03-26, 15:31 authored by Zhi Li, Shui-Hua Wang, Rui-Rui Fan, Gang Cao, Yu-Dong Zhang, Ting GuoAccurately classify teeth category is important in further dental diagnosis. Analyzing huge dental data, that is, identifying the teeth category, is often a hard task. Current automatic methods are based on computer vision and deep learning approaches. In this study, we aimed to classify the teeth category into four classes: incisor, canine, premolar, and molar. Cone beam computed tomography was used to collect the data. We proposed a seven-layer deep convolutional neural network with global average pooling to identify teeth category. Data augmentation method was used to enlarge the size of training dataset. The results showed the sensitivities of incisor, canine, premolar, and molar teeth are 88%, 86%, 84%, and 90%, respectively. The average sensitivity is 87.0%. We validated max pooling gives better results than average pooling. Our method is better than three state-of-the-art approaches.
History
Citation
Int J Imaging Syst Technol. 2019;29:577–583Author affiliation
Department of InformaticsVersion
- AM (Accepted Manuscript)
Published in
International Journal of Imaging Systems and TechnologyVolume
29Issue
4Pagination
577 - 583 (7)Publisher
WILEYissn
0899-9457eissn
1098-1098Acceptance date
2019-05-02Copyright date
2019Available date
2019-05-21Publisher DOI
Publisher version
https://onlinelibrary.wiley.com/doi/full/10.1002/ima.22337Language
EnglishUsage metrics
Categories
Keywords
Science & TechnologyTechnologyPhysical SciencesEngineering, Electrical & ElectronicOpticsImaging Science & Photographic TechnologyEngineeringcone beam computed tomographyconvolutional neural networkdata augmentationdeep convolutional neural networkdeep learningglobal average poolingmax poolingREPRESENTATIONIMAGES
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC