Advanced search
Add to list

Effect of lower third molar segmentations on automated tooth development staging using a convolutional neural network

(2020) JOURNAL OF FORENSIC SCIENCES. 65(2). p.481-486
Author
Organization
Abstract
Staging third molar development is commonly used for age estimation in subadults. Automated developmental stage allocation to the mandibular left third molar in panoramic radiographs has been examined in a pilot study. This method used an AlexNet Deep Convolutional Neural Network (CNN) approach to stage lower left third molars, which had been selected by manually drawn bounding boxes around them. This method (bounding box AlexNet = BA) still contained parts of surrounding structures which may have affected the automated stage allocation performance. We hypothesize that segmenting only the third molar could further improve the automated stage allocation performance. Therefore, the current study aimed to determine and validate the effect of lower third molar segmentations on automated tooth development staging. Retrospectively, 400 panoramic radiographs were collected, processed and segmented in three ways: bounding box (BB), rough (RS), and full (FS) tooth segmentation. A DenseNet201 CNN was used for automated stage allocation. Automated staging results were compared with reference stages - allocated by human observers - overall and per stage. FS rendered the best results with a stage allocation accuracy of 0.61, a mean absolute difference of 0.53 stages and a Cohen's linear kappa of 0.84. Misallocated stages were mostly neighboring stages, and DenseNet201 rendered better results than AlexNet by increasing the percentage of correctly allocated stages by 3% (BA compared to BB). FS increased the percentage of correctly allocated stages by 7% compared to BB. In conclusion, full tooth segmentation and a DenseNet CNN optimize automated dental stage allocation for age estimation.
Keywords
forensic science, forensic odontology, panoramic radiograph, machine learning, tooth segmentation, third molar, age estimation, AGE ESTIMATION, CALCIFICATION

Citation

Please use this url to cite or link to this publication:

MLA
Merdietio Boedi, Rizky, et al. “Effect of Lower Third Molar Segmentations on Automated Tooth Development Staging Using a Convolutional Neural Network.” JOURNAL OF FORENSIC SCIENCES, vol. 65, no. 2, 2020, pp. 481–86, doi:10.1111/1556-4029.14182.
APA
Merdietio Boedi, R., Banar, N., De Tobel, J., Bertels, J., Vandermeulen, D., & Thevissen, P. (2020). Effect of lower third molar segmentations on automated tooth development staging using a convolutional neural network. JOURNAL OF FORENSIC SCIENCES, 65(2), 481–486. https://doi.org/10.1111/1556-4029.14182
Chicago author-date
Merdietio Boedi, Rizky, Nikolay Banar, Jannick De Tobel, Jeroen Bertels, Dirk Vandermeulen, and Patrick Thevissen. 2020. “Effect of Lower Third Molar Segmentations on Automated Tooth Development Staging Using a Convolutional Neural Network.” JOURNAL OF FORENSIC SCIENCES 65 (2): 481–86. https://doi.org/10.1111/1556-4029.14182.
Chicago author-date (all authors)
Merdietio Boedi, Rizky, Nikolay Banar, Jannick De Tobel, Jeroen Bertels, Dirk Vandermeulen, and Patrick Thevissen. 2020. “Effect of Lower Third Molar Segmentations on Automated Tooth Development Staging Using a Convolutional Neural Network.” JOURNAL OF FORENSIC SCIENCES 65 (2): 481–486. doi:10.1111/1556-4029.14182.
Vancouver
1.
Merdietio Boedi R, Banar N, De Tobel J, Bertels J, Vandermeulen D, Thevissen P. Effect of lower third molar segmentations on automated tooth development staging using a convolutional neural network. JOURNAL OF FORENSIC SCIENCES. 2020;65(2):481–6.
IEEE
[1]
R. Merdietio Boedi, N. Banar, J. De Tobel, J. Bertels, D. Vandermeulen, and P. Thevissen, “Effect of lower third molar segmentations on automated tooth development staging using a convolutional neural network,” JOURNAL OF FORENSIC SCIENCES, vol. 65, no. 2, pp. 481–486, 2020.
@article{8629410,
  abstract     = {Staging third molar development is commonly used for age estimation in subadults. Automated developmental stage allocation to the mandibular left third molar in panoramic radiographs has been examined in a pilot study. This method used an AlexNet Deep Convolutional Neural Network (CNN) approach to stage lower left third molars, which had been selected by manually drawn bounding boxes around them. This method (bounding box AlexNet = BA) still contained parts of surrounding structures which may have affected the automated stage allocation performance. We hypothesize that segmenting only the third molar could further improve the automated stage allocation performance. Therefore, the current study aimed to determine and validate the effect of lower third molar segmentations on automated tooth development staging. Retrospectively, 400 panoramic radiographs were collected, processed and segmented in three ways: bounding box (BB), rough (RS), and full (FS) tooth segmentation. A DenseNet201 CNN was used for automated stage allocation. Automated staging results were compared with reference stages - allocated by human observers - overall and per stage. FS rendered the best results with a stage allocation accuracy of 0.61, a mean absolute difference of 0.53 stages and a Cohen's linear kappa of 0.84. Misallocated stages were mostly neighboring stages, and DenseNet201 rendered better results than AlexNet by increasing the percentage of correctly allocated stages by 3% (BA compared to BB). FS increased the percentage of correctly allocated stages by 7% compared to BB. In conclusion, full tooth segmentation and a DenseNet CNN optimize automated dental stage allocation for age estimation.},
  author       = {Merdietio Boedi, Rizky and Banar, Nikolay and De Tobel, Jannick and Bertels, Jeroen and Vandermeulen, Dirk and Thevissen, Patrick},
  issn         = {0022-1198},
  journal      = {JOURNAL OF FORENSIC SCIENCES},
  keywords     = {forensic science,forensic odontology,panoramic radiograph,machine learning,tooth segmentation,third molar,age estimation,AGE ESTIMATION,CALCIFICATION},
  language     = {eng},
  number       = {2},
  pages        = {481--486},
  title        = {Effect of lower third molar segmentations on automated tooth development staging using a convolutional neural network},
  url          = {http://dx.doi.org/10.1111/1556-4029.14182},
  volume       = {65},
  year         = {2020},
}

Altmetric
View in Altmetric
Web of Science
Times cited: