Human Tooth Crack Image Analysis with Multiple Deep Learning Approaches
Annals of Biomedical Engineering · 2025
DOI: 10.1007/s10439-024-03615-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of Biomedical Engineering, 2025. Verfasst von Zheng Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Division of Electrical and Computer Engineering, College of Engineering, Louisiana State University, Baton Rouge, LA, 70803, USA. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted, Tooth Fractures, Tooth. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: NIH HHS, NSF CAREER award, LSU Collaborative Cancer Research Initiative.
Abstract (Originalsprache)
Tooth cracks, one of the most common dental diseases, can result in the tooth falling apart without prompt treatment; dentists also have difficulty locating cracks, even with X-ray imaging. Indocyanine green (ICG) assisted near-infrared fluorescence (NIRF) dental imaging technique can solve this problem due to the deep penetration of NIR light and the excellent fluorescence characteristics of ICG. This study extracted 593 human cracked tooth images and 601 non-cracked tooth images from NIR imaging videos. Multiple imaging analysis methods such as classification, object detection, and super-resolution were applied to the dataset for cracked image analysis. Our results showed that machine learning methods could help analyze tooth crack efficiently: the tooth images with cracks and without cracks could be well classified with the pre-trained residual network and squeezenet1_1 models, with a classification accuracy of 88.2% and 94.25%, respectively; the single shot multi-box detector (SSD) was able to recognize cracks, even if the input image was at a different size from the original cracked image; the super-resolution (SR) model, SR-generative adversarial network demonstrated enhanced resolution of crack images using high-resolution concrete crack images as the training dataset. Overall, deep learning model-assisted human crack analysis improves crack identification; the combination of our NIR dental imaging system and deep learning models has the potential to assist dentists in crack diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Division of Electrical and Computer Engineering, College of Engineering, Louisiana State University, Baton Rouge, LA, 70803, USA.
- Section of Visual Computing and Creative Technology, School of Performance, Visualization, & Fine Art, Texas A & M University, College Station, TX, 77843, USA.
- Division of Computer Science & Engineering, College of Engineering, Louisiana State University, Baton Rouge, LA, 70803, USA.
- Oral and Maxillofacial Surgery, School of Dentistry, Louisiana State University Health Science Center, Baton Rouge, LA, 70808, USA.
- Department of Comparative Biomedical Science, School of Veterinary Medicine, Louisiana State University, Baton Rouge, LA, 70803, USA.
- Division of Electrical and Computer Engineering, College of Engineering, Louisiana State University, Baton Rouge, LA, 70803, USA. jianxu1@lsu.edu.
Förderung
- NIH HHS
- NSF CAREER award
- LSU Collaborative Cancer Research Initiative
- NIH
Zitieren
APA
Li, Z., Li, Z., Zhang, Y., Wang, H., Li, X., Zhang, J., Zaid, W., Yao, S., & Xu, J. (2025). Human Tooth Crack Image Analysis with Multiple Deep Learning Approaches. Annals of Biomedical Engineering. https://doi.org/10.1007/s10439-024-03615-9
Vancouver
Li Z, Li Z, Zhang Y, Wang H, Li X, Zhang J, et al. Human Tooth Crack Image Analysis with Multiple Deep Learning Approaches. Annals of Biomedical Engineering. 2025. doi:10.1007/s10439-024-03615-9
BibTeX
@article{Li2025,
author = {Li, Zheng and Li, Zhongqiang and Zhang, Ya and Wang, Huaizhi and Li, Xin and Zhang, Jian and Zaid, Waleed and Yao, Shaomian and Xu, Jian},
title = {Human Tooth Crack Image Analysis with Multiple Deep Learning Approaches},
journal = {Annals of Biomedical Engineering},
year = {2025},
doi = {10.1007/s10439-024-03615-9}
}
EUVIMED