Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning

Accurate tooth segmentation is an essential step for reconstructing the three-dimensional tooth models used in various clinical applications. In this paper, we propose a convolutional neural network (CNN) based method for fully-automatic tooth segmentation with multi-phase training and preprocessing...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	S. Lee, S. Woo, J. Yu, J. Seo, J. Lee, C. Lee
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Cone-beam computed tomography convolutional neural network network regularization posterior probability tooth segmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/9201217d06c044709e92399ac5079d48
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9201217d06c044709e92399ac5079d48
record_format	dspace
spelling	oai:doaj.org-article:9201217d06c044709e92399ac5079d482021-11-19T00:02:59ZAutomated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning2169-353610.1109/ACCESS.2020.2975826https://doaj.org/article/9201217d06c044709e92399ac5079d482020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9007457/https://doaj.org/toc/2169-3536Accurate tooth segmentation is an essential step for reconstructing the three-dimensional tooth models used in various clinical applications. In this paper, we propose a convolutional neural network (CNN) based method for fully-automatic tooth segmentation with multi-phase training and preprocessing. For multi-phase training, we defined and used sub-volumes of different sizes to produce stable and fast convergence. To deal with the cone-beam computed tomography (CBCT) images from various CBCT scanners, we used a histogram-based method as a preprocessing step to estimate the average gray density level of the bone and tooth regions. Also, we developed a posterior probability function. Regularizing the CNN models with spatial dropout layers and replacing the convolutional layers with dense convolution blocks further improved the segmentation performance. Experimental results showed that the proposed method compared favorably with existing methods.S. LeeS. WooJ. YuJ. SeoJ. LeeC. LeeIEEEarticleCone-beam computed tomographyconvolutional neural networknetwork regularizationposterior probabilitytooth segmentationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 50507-50518 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cone-beam computed tomography convolutional neural network network regularization posterior probability tooth segmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Cone-beam computed tomography convolutional neural network network regularization posterior probability tooth segmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971 S. Lee S. Woo J. Yu J. Seo J. Lee C. Lee Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning
description	Accurate tooth segmentation is an essential step for reconstructing the three-dimensional tooth models used in various clinical applications. In this paper, we propose a convolutional neural network (CNN) based method for fully-automatic tooth segmentation with multi-phase training and preprocessing. For multi-phase training, we defined and used sub-volumes of different sizes to produce stable and fast convergence. To deal with the cone-beam computed tomography (CBCT) images from various CBCT scanners, we used a histogram-based method as a preprocessing step to estimate the average gray density level of the bone and tooth regions. Also, we developed a posterior probability function. Regularizing the CNN models with spatial dropout layers and replacing the convolutional layers with dense convolution blocks further improved the segmentation performance. Experimental results showed that the proposed method compared favorably with existing methods.
format	article
author	S. Lee S. Woo J. Yu J. Seo J. Lee C. Lee
author_facet	S. Lee S. Woo J. Yu J. Seo J. Lee C. Lee
author_sort	S. Lee
title	Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning
title_short	Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning
title_full	Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning
title_fullStr	Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning
title_full_unstemmed	Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning
title_sort	automated cnn-based tooth segmentation in cone-beam ct for dental implant planning
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/9201217d06c044709e92399ac5079d48
work_keys_str_mv	AT slee automatedcnnbasedtoothsegmentationinconebeamctfordentalimplantplanning AT swoo automatedcnnbasedtoothsegmentationinconebeamctfordentalimplantplanning AT jyu automatedcnnbasedtoothsegmentationinconebeamctfordentalimplantplanning AT jseo automatedcnnbasedtoothsegmentationinconebeamctfordentalimplantplanning AT jlee automatedcnnbasedtoothsegmentationinconebeamctfordentalimplantplanning AT clee automatedcnnbasedtoothsegmentationinconebeamctfordentalimplantplanning
_version_	1718420679927267328

Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning

Ejemplares similares