Semantic Segmentation for Tooth Cracks Using Improved DeepLabv3+ Model

Overview

Journal Heliyon

Specialty Social Sciences

Date 2024 Feb 21

PMID 38380020

Authors

Zewen Xie

Qilin Lu

Juncheng Guo

Weiren Lin

Guanghua Ge

Yadong Tang

Damiano Pasini

Wenlong Wang

Affiliations

Soon will be listed here.

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.

References

Chu C, Zheng J, Zhou Y . Ultrasonic thyroid nodule detection method based on U-Net network. Comput Methods Programs Biomed. 2020; 199:105906. DOI: 10.1016/j.cmpb.2020.105906. View

Guo J, Wu Y, Chen L, Ge G, Tang Y, Wang W . Automatic Detection of Cracks in Cracked Tooth Based on Binary Classification Convolutional Neural Networks. Appl Bionics Biomech. 2022; 2022:9333406. PMC: 9553657. DOI: 10.1155/2022/9333406. View

Geurtsen W, Schwarze T, Gunay H . Diagnosis, therapy, and prevention of the cracked tooth syndrome. Quintessence Int. 2003; 34(6):409-17. View

Hu Z, Cao D, Hu Y, Wang B, Zhang Y, Tang R . Diagnosis of in vivo vertical root fracture using deep learning on cone-beam CT images. BMC Oral Health. 2022; 22(1):382. PMC: 9446797. DOI: 10.1186/s12903-022-02422-9. View

Zaror C, Pardo Y, Espinoza-Espinoza G, Pont A, Munoz-Millan P, Martinez-Zapata M . Assessing oral health-related quality of life in children and adolescents: a systematic review and standardized comparison of available instruments. Clin Oral Investig. 2018; 23(1):65-79. DOI: 10.1007/s00784-018-2406-1. View

Dumbryte I, Narbutis D, Vailionis A, Juodkazis S, Malinauskas M . Revelation of microcracks as tooth structural element by X-ray tomography and machine learning. Sci Rep. 2022; 12(1):22489. PMC: 9797571. DOI: 10.1038/s41598-022-27062-5. View

Zhang Y, Wang Z . Concrete Surface Crack Recognition Based on Coordinate Attention Neural Networks. Comput Intell Neurosci. 2022; 2022:7454746. PMC: 9388252. DOI: 10.1155/2022/7454746. View

Metska M, Aartman I, Wesselink P, Ozok A . Detection of vertical root fractures in vivo in endodontically treated teeth by cone-beam computed tomography scans. J Endod. 2012; 38(10):1344-7. DOI: 10.1016/j.joen.2012.05.003. View

Turp J, Gobetti J . The cracked tooth syndrome: an elusive diagnosis. J Am Dent Assoc. 1996; 127(10):1502-7. DOI: 10.14219/jada.archive.1996.0060. View

10.

Abbott P, Leow N . Predictable management of cracked teeth with reversible pulpitis. Aust Dent J. 2010; 54(4):306-15. DOI: 10.1111/j.1834-7819.2009.01155.x. View

11.

Sahin M, Ulutas H, Yuce E, Erkoc M . Detection and classification of COVID-19 by using faster R-CNN and mask R-CNN on CT images. Neural Comput Appl. 2023; 35(18):13597-13611. PMC: 10014413. DOI: 10.1007/s00521-023-08450-y. View

12.

Shelhamer E, Long J, Darrell T . Fully Convolutional Networks for Semantic Segmentation. IEEE Trans Pattern Anal Mach Intell. 2016; 39(4):640-651. DOI: 10.1109/TPAMI.2016.2572683. View

13.

Son D, Yoon Y, Kwon H, Lee S . Combined Deep Learning Techniques for Mandibular Fracture Diagnosis Assistance. Life (Basel). 2022; 12(11). PMC: 9697461. DOI: 10.3390/life12111711. View

14.

Hilton T, Funkhouser E, Ferracane J, Gordan V, Huff K, Barna J . Associations of types of pain with crack-level, tooth-level and patient-level characteristics in posterior teeth with visible cracks: Findings from the National Dental Practice-Based Research Network. J Dent. 2018; 70:67-73. PMC: 5939962. DOI: 10.1016/j.jdent.2017.12.014. View

15.

Vicory J, Chandradevan R, Hernandez-Cerdan P, Huang W, Fox D, Qdais L . Dental microfracture detection using wavelet features and machine learning. Proc SPIE Int Soc Opt Eng. 2022; 11596. PMC: 9059627. DOI: 10.1117/12.2580744. View

16.

Ruhrnschopf E, Klingenbeck K . A general framework and review of scatter correction methods in x-ray cone-beam computerized tomography. Part 1: Scatter compensation approaches. Med Phys. 2011; 38(7):4296-311. DOI: 10.1118/1.3599033. View

17.

Oguz C, Yaganoglu M . Detection of COVID-19 using deep learning techniques and classification methods. Inf Process Manag. 2022; 59(5):103025. PMC: 9263717. DOI: 10.1016/j.ipm.2022.103025. View

18.

Lubisich E, Hilton T, Ferracane J . Cracked teeth: a review of the literature. J Esthet Restor Dent. 2010; 22(3):158-67. PMC: 3870147. DOI: 10.1111/j.1708-8240.2010.00330.x. View

19.

Kamburoglu K, Murat S, Yuksel S, Cebeci A, Horasan S . Detection of vertical root fracture using cone-beam computerized tomography: an in vitro assessment. Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 2009; 109(2):e74-81. DOI: 10.1016/j.tripleo.2009.09.005. View

20.

Wang J, Lv P, Wang H, Shi C . SAR-U-Net: Squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography. Comput Methods Programs Biomed. 2021; 208:106268. DOI: 10.1016/j.cmpb.2021.106268. View