Semantic segmentation for tooth cracks using improved DeepLabv3+ model

Zewen Xie; Qilin Lu; Juncheng Guo; Weiren Lin; Guanghua Ge; Yadong Tang; Damiano Pasini; Wenlong Wang

doi:10.1016/j.heliyon.2024.e25892

Semantic segmentation for tooth cracks using improved DeepLabv3+ model

Heliyon. 2024 Feb 10;10(4):e25892. doi: 10.1016/j.heliyon.2024.e25892. eCollection 2024 Feb 29.

Authors

Zewen Xie^{1

2}, Qilin Lu¹, Juncheng Guo¹, Weiren Lin¹, Guanghua Ge³, Yadong Tang⁴, Damiano Pasini⁵, Wenlong Wang^{1

5}

Affiliations

¹ School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, 510006, China.
² School of Physics and Material Science, Guangzhou University, Guangzhou, 510006, China.
³ Department of Dentistry, Hospital of Guangdong University of Technology, Guangdong University of Technology, Guangzhou, 510006, China.
⁴ School of Biomedical and Pharmaceutical Sciences, Guangdong University of Technology, Guangzhou, 510006, China.
⁵ Department of Mechanical Engineering, McGill University, 817 Sherbrooke Street West, Montreal, QC H3A 0C3, Canada.

Abstract

Objective: Accurate and prompt detection of cracked teeth plays a critical role for human oral health. The aim of this paper is to evaluate the performance of a tooth crack segmentation model (namely, FDB-DeepLabv3+) on optical microscopic images.

Method: The FDB-DeepLabv3+ model proposed here improves feature learning by replacing the backbone with ResNet50. Feature pyramid network (FPN) is introduced to fuse muti-level features. Densely linked atrous spatial pyramid pooling (Dense ASPP) is applied to achieve denser pixel sampling and wider receptive field. Bottleneck attention module (BAM) is embedded to enhance local feature extraction.

Results: Through testing on a self-made hidden cracked tooth dataset, the proposed method outperforms four classical networks (FCN, U-Net, SegNet, DeepLabv3+) on segmentation results in terms of mean pixel accuracy (MPA) and mean intersection over union (MIoU). The network achieves an increase of 11.41% in MPA and 12.14% in MIoU compared to DeepLabv3+. Ablation experiments shows that all the modifications are beneficial.

Conclusion: An improved network is designed for segmenting tooth surface cracks with good overall performance and robustness, which may hold significant potential in computer-aided diagnosis of cracked teeth.

Keywords: Cracked teeth; DeepLabv3+; Oral health; Semantic segmentation.