Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Abstract Middle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	C. A. Neves, E. D. Tran, I. M. Kessler, N. H. Blevins
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/e694cee3ee8840d693749ea6b4300175
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e694cee3ee8840d693749ea6b4300175
record_format	dspace
spelling	oai:doaj.org-article:e694cee3ee8840d693749ea6b43001752021-12-02T15:13:59ZFully automated preoperative segmentation of temporal bone structures from clinical CT scans10.1038/s41598-020-80619-02045-2322https://doaj.org/article/e694cee3ee8840d693749ea6b43001752021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80619-0https://doaj.org/toc/2045-2322Abstract Middle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.C. A. NevesE. D. TranI. M. KesslerN. H. BlevinsNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q C. A. Neves E. D. Tran I. M. Kessler N. H. Blevins Fully automated preoperative segmentation of temporal bone structures from clinical CT scans
description	Abstract Middle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.
format	article
author	C. A. Neves E. D. Tran I. M. Kessler N. H. Blevins
author_facet	C. A. Neves E. D. Tran I. M. Kessler N. H. Blevins
author_sort	C. A. Neves
title	Fully automated preoperative segmentation of temporal bone structures from clinical CT scans
title_short	Fully automated preoperative segmentation of temporal bone structures from clinical CT scans
title_full	Fully automated preoperative segmentation of temporal bone structures from clinical CT scans
title_fullStr	Fully automated preoperative segmentation of temporal bone structures from clinical CT scans
title_full_unstemmed	Fully automated preoperative segmentation of temporal bone structures from clinical CT scans
title_sort	fully automated preoperative segmentation of temporal bone structures from clinical ct scans
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e694cee3ee8840d693749ea6b4300175
work_keys_str_mv	AT caneves fullyautomatedpreoperativesegmentationoftemporalbonestructuresfromclinicalctscans AT edtran fullyautomatedpreoperativesegmentationoftemporalbonestructuresfromclinicalctscans AT imkessler fullyautomatedpreoperativesegmentationoftemporalbonestructuresfromclinicalctscans AT nhblevins fullyautomatedpreoperativesegmentationoftemporalbonestructuresfromclinicalctscans
_version_	1718387604767899648

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Ejemplares similares