Quantitative salivary gland SPECT/CT using deep convolutional neural networks

Abstract Quantitative single-photon emission computed tomography/computed tomography (SPECT/CT) using Tc-99m pertechnetate aids in evaluating salivary gland function. However, gland segmentation and quantitation of gland uptake is challenging. We develop a salivary gland SPECT/CT with automated segm...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Junyoung Park, Jae Sung Lee, Dongkyu Oh, Hyun Gee Ryoo, Jeong Hee Han, Won Woo Lee
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f3a8bc3ffdf945d9a14af105a526b01b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f3a8bc3ffdf945d9a14af105a526b01b
record_format	dspace
spelling	oai:doaj.org-article:f3a8bc3ffdf945d9a14af105a526b01b2021-12-02T14:15:53ZQuantitative salivary gland SPECT/CT using deep convolutional neural networks10.1038/s41598-021-87497-02045-2322https://doaj.org/article/f3a8bc3ffdf945d9a14af105a526b01b2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87497-0https://doaj.org/toc/2045-2322Abstract Quantitative single-photon emission computed tomography/computed tomography (SPECT/CT) using Tc-99m pertechnetate aids in evaluating salivary gland function. However, gland segmentation and quantitation of gland uptake is challenging. We develop a salivary gland SPECT/CT with automated segmentation using a deep convolutional neural network (CNN). The protocol comprises SPECT/CT at 20 min, sialagogue stimulation, and SPECT at 40 min post-injection of Tc-99m pertechnetate (555 MBq). The 40-min SPECT was reconstructed using the 20-min CT after misregistration correction. Manual salivary gland segmentation for %injected dose (%ID) by human experts proved highly reproducible, but took 15 min per scan. An automatic salivary segmentation method was developed using a modified 3D U-Net for end-to-end learning from the human experts (n = 333). The automatic segmentation performed comparably with human experts in voxel-wise comparison (mean Dice similarity coefficient of 0.81 for parotid and 0.79 for submandibular, respectively) and gland %ID correlation (R 2 = 0.93 parotid, R 2 = 0.95 submandibular) with an operating time less than 1 min. The algorithm generated results that were comparable to the reference data. In conclusion, with the aid of a CNN, we developed a quantitative salivary gland SPECT/CT protocol feasible for clinical applications. The method saves analysis time and manual effort while reducing patients’ radiation exposure.Junyoung ParkJae Sung LeeDongkyu OhHyun Gee RyooJeong Hee HanWon Woo LeeNature 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 Junyoung Park Jae Sung Lee Dongkyu Oh Hyun Gee Ryoo Jeong Hee Han Won Woo Lee Quantitative salivary gland SPECT/CT using deep convolutional neural networks
description	Abstract Quantitative single-photon emission computed tomography/computed tomography (SPECT/CT) using Tc-99m pertechnetate aids in evaluating salivary gland function. However, gland segmentation and quantitation of gland uptake is challenging. We develop a salivary gland SPECT/CT with automated segmentation using a deep convolutional neural network (CNN). The protocol comprises SPECT/CT at 20 min, sialagogue stimulation, and SPECT at 40 min post-injection of Tc-99m pertechnetate (555 MBq). The 40-min SPECT was reconstructed using the 20-min CT after misregistration correction. Manual salivary gland segmentation for %injected dose (%ID) by human experts proved highly reproducible, but took 15 min per scan. An automatic salivary segmentation method was developed using a modified 3D U-Net for end-to-end learning from the human experts (n = 333). The automatic segmentation performed comparably with human experts in voxel-wise comparison (mean Dice similarity coefficient of 0.81 for parotid and 0.79 for submandibular, respectively) and gland %ID correlation (R 2 = 0.93 parotid, R 2 = 0.95 submandibular) with an operating time less than 1 min. The algorithm generated results that were comparable to the reference data. In conclusion, with the aid of a CNN, we developed a quantitative salivary gland SPECT/CT protocol feasible for clinical applications. The method saves analysis time and manual effort while reducing patients’ radiation exposure.
format	article
author	Junyoung Park Jae Sung Lee Dongkyu Oh Hyun Gee Ryoo Jeong Hee Han Won Woo Lee
author_facet	Junyoung Park Jae Sung Lee Dongkyu Oh Hyun Gee Ryoo Jeong Hee Han Won Woo Lee
author_sort	Junyoung Park
title	Quantitative salivary gland SPECT/CT using deep convolutional neural networks
title_short	Quantitative salivary gland SPECT/CT using deep convolutional neural networks
title_full	Quantitative salivary gland SPECT/CT using deep convolutional neural networks
title_fullStr	Quantitative salivary gland SPECT/CT using deep convolutional neural networks
title_full_unstemmed	Quantitative salivary gland SPECT/CT using deep convolutional neural networks
title_sort	quantitative salivary gland spect/ct using deep convolutional neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/f3a8bc3ffdf945d9a14af105a526b01b
work_keys_str_mv	AT junyoungpark quantitativesalivaryglandspectctusingdeepconvolutionalneuralnetworks AT jaesunglee quantitativesalivaryglandspectctusingdeepconvolutionalneuralnetworks AT dongkyuoh quantitativesalivaryglandspectctusingdeepconvolutionalneuralnetworks AT hyungeeryoo quantitativesalivaryglandspectctusingdeepconvolutionalneuralnetworks AT jeongheehan quantitativesalivaryglandspectctusingdeepconvolutionalneuralnetworks AT wonwoolee quantitativesalivaryglandspectctusingdeepconvolutionalneuralnetworks
_version_	1718391759134785536

Quantitative salivary gland SPECT/CT using deep convolutional neural networks

Ejemplares similares