Accuracy of advanced deep learning with tensorflow and keras for classifying teeth developmental stages in digital panoramic imaging
Background: This study aims to propose the combinations of image processing and machine learning model to segment the maturity development of the mandibular premolars using a Keras-based deep learning convolutional neural networks (DCNN) model. Methods: A dataset consisting of 240 images (20 image...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
BioMed Central Ltd
2022
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/46017/1/s12880-022-00794-6.pdf http://ir.unimas.my/id/eprint/46017/ https://bmcmedimaging.biomedcentral.com/articles/10.1186/s12880-022-00794-6 https://doi.org/10.1186/s12880-022-00794-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Background: This study aims to propose the combinations of image processing and machine learning model to segment the maturity development of the mandibular premolars using a Keras-based deep learning convolutional neural
networks (DCNN) model.
Methods: A dataset consisting of 240 images (20 images per stage per sex) of retrospect digital dental panoramic
imaging of patients between 5 and 14 years of age was retrieved. In image preprocessing, abounding box with a
dimension of 250×250 pixels was assigned to the left mandibular frst (P1) and second (P2) permanent premolars.
The implementation of dynamic programming of active contour (DP-AC) and convolutions neural network on images
that require the procedure of image fltration using Python TensorFlow and Keras libraries were performed in image
segmentation and classifcation, respectively.
Results: Image segmentation using the DP-AC algorithm enhanced the visibility of the image features in the
region of interest while suppressing the image’s background noise. The proposed model has an accuracy of 97.74%,
96.63% and 78.13% on the training, validation, and testing set, respectively. In addition, moderate agreement (Kappa
value=0.58) between human observer and computer were identifed. Nonetheless, a robust DCNN model was
achieved as there is no sign of the model’s over-or under-ftting upon the learning process.
Conclusions: The application of digital imaging and deep learning techniques used by the DP-AC and convolutions
neural network algorithms to segment and identify premolars provides promising results for semi-automated forensic
dental staging in the future |
|---|