Cargando…

Texture-Based Neural Network Model for Biometric Dental Applications

Background: The aim is to classify dentition using a novel texture-based automated convolutional neural network (CNN) for forensic and prosthetic applications. Methods: Natural human teeth (n = 600) were classified, cleaned, and inspected for exclusion criteria. The teeth were scanned with an intrao...

Descripción completa

Detalles Bibliográficos
Autores principales: Saleh, Omnia, Nozaki, Kosuke, Matsumura, Mayuko, Yanaka, Wataru, Miura, Hiroyuki, Fueki, Kenji
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9781388/
https://www.ncbi.nlm.nih.gov/pubmed/36556175
http://dx.doi.org/10.3390/jpm12121954
_version_ 1784857061865029632
author Saleh, Omnia
Nozaki, Kosuke
Matsumura, Mayuko
Yanaka, Wataru
Miura, Hiroyuki
Fueki, Kenji
author_facet Saleh, Omnia
Nozaki, Kosuke
Matsumura, Mayuko
Yanaka, Wataru
Miura, Hiroyuki
Fueki, Kenji
author_sort Saleh, Omnia
collection PubMed
description Background: The aim is to classify dentition using a novel texture-based automated convolutional neural network (CNN) for forensic and prosthetic applications. Methods: Natural human teeth (n = 600) were classified, cleaned, and inspected for exclusion criteria. The teeth were scanned with an intraoral scanner and identified using a texture-based CNN in three steps. First, through preprocessing, teeth images were segmented by extracting the front-facing region of the teeth. Then, texture features were extracted from the segmented teeth images using the discrete wavelet transform (DWT) method. Finally, deep learning-based enhanced CNN models were used to identify these images. Several experiments were conducted using five different CNN models with various batch sizes and epochs, with and without augmented data. Results: Based on experiments with five different CNN models, the highest accuracy achieved was 0.8 and the precision was 0.8 with a loss value of 0.9, a batch size of 32, and 250 epochs. A comparison of deep learning models with different parameters showed varied accuracy between the different classes of teeth. Conclusion: The accuracy of the point-based CNN method was promising. This texture-identification method will pave the way for many forensic and prosthodontic applications and will potentially help improve the precision of dental biometrics.
format Online
Article
Text
id pubmed-9781388
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97813882022-12-24 Texture-Based Neural Network Model for Biometric Dental Applications Saleh, Omnia Nozaki, Kosuke Matsumura, Mayuko Yanaka, Wataru Miura, Hiroyuki Fueki, Kenji J Pers Med Article Background: The aim is to classify dentition using a novel texture-based automated convolutional neural network (CNN) for forensic and prosthetic applications. Methods: Natural human teeth (n = 600) were classified, cleaned, and inspected for exclusion criteria. The teeth were scanned with an intraoral scanner and identified using a texture-based CNN in three steps. First, through preprocessing, teeth images were segmented by extracting the front-facing region of the teeth. Then, texture features were extracted from the segmented teeth images using the discrete wavelet transform (DWT) method. Finally, deep learning-based enhanced CNN models were used to identify these images. Several experiments were conducted using five different CNN models with various batch sizes and epochs, with and without augmented data. Results: Based on experiments with five different CNN models, the highest accuracy achieved was 0.8 and the precision was 0.8 with a loss value of 0.9, a batch size of 32, and 250 epochs. A comparison of deep learning models with different parameters showed varied accuracy between the different classes of teeth. Conclusion: The accuracy of the point-based CNN method was promising. This texture-identification method will pave the way for many forensic and prosthodontic applications and will potentially help improve the precision of dental biometrics. MDPI 2022-11-25 /pmc/articles/PMC9781388/ /pubmed/36556175 http://dx.doi.org/10.3390/jpm12121954 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Saleh, Omnia
Nozaki, Kosuke
Matsumura, Mayuko
Yanaka, Wataru
Miura, Hiroyuki
Fueki, Kenji
Texture-Based Neural Network Model for Biometric Dental Applications
title Texture-Based Neural Network Model for Biometric Dental Applications
title_full Texture-Based Neural Network Model for Biometric Dental Applications
title_fullStr Texture-Based Neural Network Model for Biometric Dental Applications
title_full_unstemmed Texture-Based Neural Network Model for Biometric Dental Applications
title_short Texture-Based Neural Network Model for Biometric Dental Applications
title_sort texture-based neural network model for biometric dental applications
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9781388/
https://www.ncbi.nlm.nih.gov/pubmed/36556175
http://dx.doi.org/10.3390/jpm12121954
work_keys_str_mv AT salehomnia texturebasedneuralnetworkmodelforbiometricdentalapplications
AT nozakikosuke texturebasedneuralnetworkmodelforbiometricdentalapplications
AT matsumuramayuko texturebasedneuralnetworkmodelforbiometricdentalapplications
AT yanakawataru texturebasedneuralnetworkmodelforbiometricdentalapplications
AT miurahiroyuki texturebasedneuralnetworkmodelforbiometricdentalapplications
AT fuekikenji texturebasedneuralnetworkmodelforbiometricdentalapplications