Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations

Abstract Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mingyu Kim, Sungchul Kim, Minjee Kim, Hyun-Jin Bae, Jae-Woo Park, Namkug Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6c379c130b4846fba9ba730e1fc708a4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6c379c130b4846fba9ba730e1fc708a4
record_format	dspace
spelling	oai:doaj.org-article:6c379c130b4846fba9ba730e1fc708a42021-12-02T17:39:53ZRealistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations10.1038/s41598-021-91965-y2045-2322https://doaj.org/article/6c379c130b4846fba9ba730e1fc708a42021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91965-yhttps://doaj.org/toc/2045-2322Abstract Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical vertebra, showed no statistically significant difference (t-test, p = 0.211). Second, the results of an image Turing test, conducted by non-orthodontists and orthodontists for 100 randomly chosen images, indicated that they had difficulty in distinguishing whether the image was real or synthesized. Third, cephalometric tracing with 42 landmark points detection, performed on real and synthesized images by two expert orthodontists, showed consistency with mean difference of 2.08 ± 1.02 mm. Furthermore, convolutional neural network-based classification tasks were used to classify skeletal patterns using a real dataset with class imbalance and a dataset balanced with synthesized images. The classification accuracy for the latter case was increased by 1.5%/3.3% at internal/external test sets, respectively. Thus, the cephalometric images generated by PGGAN are sufficiently realistic and have potential to application in various fields of dental medicine.Mingyu KimSungchul KimMinjee KimHyun-Jin BaeJae-Woo ParkNamkug KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mingyu Kim Sungchul Kim Minjee Kim Hyun-Jin Bae Jae-Woo Park Namkug Kim Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
description	Abstract Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical vertebra, showed no statistically significant difference (t-test, p = 0.211). Second, the results of an image Turing test, conducted by non-orthodontists and orthodontists for 100 randomly chosen images, indicated that they had difficulty in distinguishing whether the image was real or synthesized. Third, cephalometric tracing with 42 landmark points detection, performed on real and synthesized images by two expert orthodontists, showed consistency with mean difference of 2.08 ± 1.02 mm. Furthermore, convolutional neural network-based classification tasks were used to classify skeletal patterns using a real dataset with class imbalance and a dataset balanced with synthesized images. The classification accuracy for the latter case was increased by 1.5%/3.3% at internal/external test sets, respectively. Thus, the cephalometric images generated by PGGAN are sufficiently realistic and have potential to application in various fields of dental medicine.
format	article
author	Mingyu Kim Sungchul Kim Minjee Kim Hyun-Jin Bae Jae-Woo Park Namkug Kim
author_facet	Mingyu Kim Sungchul Kim Minjee Kim Hyun-Jin Bae Jae-Woo Park Namkug Kim
author_sort	Mingyu Kim
title	Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
title_short	Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
title_full	Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
title_fullStr	Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
title_full_unstemmed	Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
title_sort	realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/6c379c130b4846fba9ba730e1fc708a4
work_keys_str_mv	AT mingyukim realistichighresolutionlateralcephalometricradiographygeneratedbyprogressivegrowinggenerativeadversarialnetworkandqualityevaluations AT sungchulkim realistichighresolutionlateralcephalometricradiographygeneratedbyprogressivegrowinggenerativeadversarialnetworkandqualityevaluations AT minjeekim realistichighresolutionlateralcephalometricradiographygeneratedbyprogressivegrowinggenerativeadversarialnetworkandqualityevaluations AT hyunjinbae realistichighresolutionlateralcephalometricradiographygeneratedbyprogressivegrowinggenerativeadversarialnetworkandqualityevaluations AT jaewoopark realistichighresolutionlateralcephalometricradiographygeneratedbyprogressivegrowinggenerativeadversarialnetworkandqualityevaluations AT namkugkim realistichighresolutionlateralcephalometricradiographygeneratedbyprogressivegrowinggenerativeadversarialnetworkandqualityevaluations
_version_	1718379768137646080

Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations

Ejemplares similares