Artificial intelligence implementation in tooth identification from X-ray images

Banjsak, Luka; Milošević, Denis; Subašić, Marko; Brkić, Hrvoje; Vodanović, Marin

doi:10.1016/j.identj.2021.08.007

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a similar vein, [72] use Faster R-CNN with a dataset of 1250 panoramic dental x-ray images to achieve a tooth type determination accuracy between 71.5% and 91.7%. In our preliminary study, we achieved an accuracy between 91.13% and 97.83% for individual tooth x-ray images, for the 4, 8, 16 and 32 class approach [3].…”

Section: Related Workmentioning

confidence: 88%

“…Finally, our preliminary study for the determination of tooth type [3] has in this study been fully extended, constructing a model on a much broader toolset, and using a significantly larger dataset. This study also improves upon the analysis of all our previous work with the examination of the impact of tooth alteration on prediction performance.…”

Section: Related Workmentioning

confidence: 99%

“…In our initial studies [1]- [3], [68] some form of hyperparameter search was done, either directly or indirectly. The knowledge about the search space and sensible parameter ranges were learned from our initial study on sex assessment from panoramic dental x-ray images [1].…”

Section: Hyperparameter Searchmentioning

confidence: 99%

“…For sex assessment, we have evaluated an additional 256 experiments with grid search to complete the random search we have done in [68]. Tooth type determination in [3] was done on a smaller dataset, and the search consisted of 64 experiments. In this study, tooth type determination experiments were extended with a random search of 256 experiments and a random search of 128 experiments.…”

Section: Hyperparameter Searchmentioning

confidence: 99%

“…In this study, we examine the use of convolutional neural networks for the task of age estimation, sex assessment, and tooth type determination. While we have done some preliminary research [1]- [3], this study solely focuses on individual tooth x-ray images. Individual tooth images naturally contain less information, as the jaw bone and other surrounding tissue that can aid in age estimation is missing.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Comprehensive Exploration of Neural Networks for Forensic Analysis of Adult Single Tooth X-Ray Images

et al. 2022

Self Cite

View full text Add to dashboard Cite

Determining the demographic characteristics of a person post-mortem is a fundamental task for forensic experts, and the dental system is a crucial source of those information. Those characteristics, namely age and sex, can reliably be determined. The mandible and individual teeth survive even the harshest conditions, making them a prime target for forensic analysis. Current methods in forensic odontology rely on time-consuming manual measurements and reference tables, many of which rely on the correct determination of the tooth type. This study thoroughly explores the applicability of deep learning for sex assessment, age estimation, and tooth type determination from x-ray images of individual teeth. A series of models that use state-of-the-art feature extraction architectures and attention have been trained and evaluated. Their hyperparameters have been explored and optimized using a combination of grid and random search, totaling over a thousand experiments and 14076 hours of GPU compute time. Our dataset contains 86495 individual tooth x-ray image samples, with a subset of 7630 images having additional information about tooth alterations. The best-performing models are fine-tuned, the impact of tooth alterations is analyzed, and model performance is compared to current methods in forensic odontology literature. We achieve an accuracy of 76.41% for sex assessment, a median absolute error of 4.94 years for age estimation, and an accuracy of 87.24% to 99.15% for tooth type determination. The constructed models are fully automated and fast, their results are reproducible, and the performance is equal to or better than current state-of-the-art methods in forensic odontology.

show abstract

Section: Related Workmentioning

confidence: 88%

Section: Related Workmentioning

confidence: 99%