Cargando…

Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study

Using super-resolution (SR) algorithms, an image with a low resolution can be converted into a high-quality image. Our objective was to compare deep learning-based SR models to a conventional approach for improving the resolution of dental panoramic radiographs. A total of 888 dental panoramic radio...

Descripción completa

Detalles Bibliográficos
Autores principales: Mohammad-Rahimi, Hossein, Vinayahalingam, Shankeeth, Mahmoudinia, Erfan, Soltani, Parisa, Bergé, Stefaan J., Krois, Joachim, Schwendicke, Falk
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10000385/
https://www.ncbi.nlm.nih.gov/pubmed/36900140
http://dx.doi.org/10.3390/diagnostics13050996
_version_ 1784903861971976192
author Mohammad-Rahimi, Hossein
Vinayahalingam, Shankeeth
Mahmoudinia, Erfan
Soltani, Parisa
Bergé, Stefaan J.
Krois, Joachim
Schwendicke, Falk
author_facet Mohammad-Rahimi, Hossein
Vinayahalingam, Shankeeth
Mahmoudinia, Erfan
Soltani, Parisa
Bergé, Stefaan J.
Krois, Joachim
Schwendicke, Falk
author_sort Mohammad-Rahimi, Hossein
collection PubMed
description Using super-resolution (SR) algorithms, an image with a low resolution can be converted into a high-quality image. Our objective was to compare deep learning-based SR models to a conventional approach for improving the resolution of dental panoramic radiographs. A total of 888 dental panoramic radiographs were obtained. Our study involved five state-of-the-art deep learning-based SR approaches, including SR convolutional neural networks (SRCNN), SR generative adversarial network (SRGAN), U-Net, Swin for image restoration (SwinIr), and local texture estimator (LTE). Their results were compared with one another and with conventional bicubic interpolation. The performance of each model was evaluated using the metrics of mean squared error (MSE), peak signal-to-noise ratio (PNSR), structural similarity index (SSIM), and mean opinion score by four experts (MOS). Among all the models evaluated, the LTE model presented the highest performance, with MSE, SSIM, PSNR, and MOS results of 7.42 ± 0.44, 39.74 ± 0.17, 0.919 ± 0.003, and 3.59 ± 0.54, respectively. Additionally, compared with low-resolution images, the output of all the used approaches showed significant improvements in MOS evaluation. A significant enhancement in the quality of panoramic radiographs can be achieved by SR. The LTE model outperformed the other models.
format Online
Article
Text
id pubmed-10000385
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100003852023-03-11 Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study Mohammad-Rahimi, Hossein Vinayahalingam, Shankeeth Mahmoudinia, Erfan Soltani, Parisa Bergé, Stefaan J. Krois, Joachim Schwendicke, Falk Diagnostics (Basel) Article Using super-resolution (SR) algorithms, an image with a low resolution can be converted into a high-quality image. Our objective was to compare deep learning-based SR models to a conventional approach for improving the resolution of dental panoramic radiographs. A total of 888 dental panoramic radiographs were obtained. Our study involved five state-of-the-art deep learning-based SR approaches, including SR convolutional neural networks (SRCNN), SR generative adversarial network (SRGAN), U-Net, Swin for image restoration (SwinIr), and local texture estimator (LTE). Their results were compared with one another and with conventional bicubic interpolation. The performance of each model was evaluated using the metrics of mean squared error (MSE), peak signal-to-noise ratio (PNSR), structural similarity index (SSIM), and mean opinion score by four experts (MOS). Among all the models evaluated, the LTE model presented the highest performance, with MSE, SSIM, PSNR, and MOS results of 7.42 ± 0.44, 39.74 ± 0.17, 0.919 ± 0.003, and 3.59 ± 0.54, respectively. Additionally, compared with low-resolution images, the output of all the used approaches showed significant improvements in MOS evaluation. A significant enhancement in the quality of panoramic radiographs can be achieved by SR. The LTE model outperformed the other models. MDPI 2023-03-06 /pmc/articles/PMC10000385/ /pubmed/36900140 http://dx.doi.org/10.3390/diagnostics13050996 Text en © 2023 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
Mohammad-Rahimi, Hossein
Vinayahalingam, Shankeeth
Mahmoudinia, Erfan
Soltani, Parisa
Bergé, Stefaan J.
Krois, Joachim
Schwendicke, Falk
Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study
title Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study
title_full Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study
title_fullStr Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study
title_full_unstemmed Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study
title_short Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study
title_sort super-resolution of dental panoramic radiographs using deep learning: a pilot study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10000385/
https://www.ncbi.nlm.nih.gov/pubmed/36900140
http://dx.doi.org/10.3390/diagnostics13050996
work_keys_str_mv AT mohammadrahimihossein superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy
AT vinayahalingamshankeeth superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy
AT mahmoudiniaerfan superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy
AT soltaniparisa superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy
AT bergestefaanj superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy
AT kroisjoachim superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy
AT schwendickefalk superresolutionofdentalpanoramicradiographsusingdeeplearningapilotstudy