Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study

Abstract Background Segmentation of important structures in temporal bone CT is the basis of image-guided otologic surgery. Manual segmentation of temporal bone CT is time- consuming and laborious. We assessed the feasibility and generalization ability of a proposed deep learning model for automated...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang Wang, Yi Lv, Junchen Wang, Furong Ma, Yali Du, Xin Fan, Menglin Wang, Jia Ke
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Deep learning Neural network Automatic segmentation Temporal bone CT Accuracy Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/3376463b8a5c4b5baf3685e472ba548e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3376463b8a5c4b5baf3685e472ba548e
record_format	dspace
spelling	oai:doaj.org-article:3376463b8a5c4b5baf3685e472ba548e2021-11-14T12:33:39ZFully automated segmentation in temporal bone CT with neural network: a preliminary assessment study10.1186/s12880-021-00698-x1471-2342https://doaj.org/article/3376463b8a5c4b5baf3685e472ba548e2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12880-021-00698-xhttps://doaj.org/toc/1471-2342Abstract Background Segmentation of important structures in temporal bone CT is the basis of image-guided otologic surgery. Manual segmentation of temporal bone CT is time- consuming and laborious. We assessed the feasibility and generalization ability of a proposed deep learning model for automated segmentation of critical structures in temporal bone CT scans. Methods Thirty-nine temporal bone CT volumes including 58 ears were divided into normal (n = 20) and abnormal groups (n = 38). Ossicular chain disruption (n = 10), facial nerve covering vestibular window (n = 10), and Mondini dysplasia (n = 18) were included in abnormal group. All facial nerves, auditory ossicles, and labyrinths of the normal group were manually segmented. For the abnormal group, aberrant structures were manually segmented. Temporal bone CT data were imported into the network in unmarked form. The Dice coefficient (DC) and average symmetric surface distance (ASSD) were used to evaluate the accuracy of automatic segmentation. Results In the normal group, the mean values of DC and ASSD were respectively 0.703, and 0.250 mm for the facial nerve; 0.910, and 0.081 mm for the labyrinth; and 0.855, and 0.107 mm for the ossicles. In the abnormal group, the mean values of DC and ASSD were respectively 0.506, and 1.049 mm for the malformed facial nerve; 0.775, and 0.298 mm for the deformed labyrinth; and 0.698, and 1.385 mm for the aberrant ossicles. Conclusions The proposed model has good generalization ability, which highlights the promise of this approach for otologist education, disease diagnosis, and preoperative planning for image-guided otology surgery.Jiang WangYi LvJunchen WangFurong MaYali DuXin FanMenglin WangJia KeBMCarticleDeep learningNeural networkAutomatic segmentationTemporal bone CTAccuracyMedical technologyR855-855.5ENBMC Medical Imaging, Vol 21, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning Neural network Automatic segmentation Temporal bone CT Accuracy Medical technology R855-855.5
spellingShingle	Deep learning Neural network Automatic segmentation Temporal bone CT Accuracy Medical technology R855-855.5 Jiang Wang Yi Lv Junchen Wang Furong Ma Yali Du Xin Fan Menglin Wang Jia Ke Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study
description	Abstract Background Segmentation of important structures in temporal bone CT is the basis of image-guided otologic surgery. Manual segmentation of temporal bone CT is time- consuming and laborious. We assessed the feasibility and generalization ability of a proposed deep learning model for automated segmentation of critical structures in temporal bone CT scans. Methods Thirty-nine temporal bone CT volumes including 58 ears were divided into normal (n = 20) and abnormal groups (n = 38). Ossicular chain disruption (n = 10), facial nerve covering vestibular window (n = 10), and Mondini dysplasia (n = 18) were included in abnormal group. All facial nerves, auditory ossicles, and labyrinths of the normal group were manually segmented. For the abnormal group, aberrant structures were manually segmented. Temporal bone CT data were imported into the network in unmarked form. The Dice coefficient (DC) and average symmetric surface distance (ASSD) were used to evaluate the accuracy of automatic segmentation. Results In the normal group, the mean values of DC and ASSD were respectively 0.703, and 0.250 mm for the facial nerve; 0.910, and 0.081 mm for the labyrinth; and 0.855, and 0.107 mm for the ossicles. In the abnormal group, the mean values of DC and ASSD were respectively 0.506, and 1.049 mm for the malformed facial nerve; 0.775, and 0.298 mm for the deformed labyrinth; and 0.698, and 1.385 mm for the aberrant ossicles. Conclusions The proposed model has good generalization ability, which highlights the promise of this approach for otologist education, disease diagnosis, and preoperative planning for image-guided otology surgery.
format	article
author	Jiang Wang Yi Lv Junchen Wang Furong Ma Yali Du Xin Fan Menglin Wang Jia Ke
author_facet	Jiang Wang Yi Lv Junchen Wang Furong Ma Yali Du Xin Fan Menglin Wang Jia Ke
author_sort	Jiang Wang
title	Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study
title_short	Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study
title_full	Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study
title_fullStr	Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study
title_full_unstemmed	Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study
title_sort	fully automated segmentation in temporal bone ct with neural network: a preliminary assessment study
publisher	BMC
publishDate	2021
url	https://doaj.org/article/3376463b8a5c4b5baf3685e472ba548e
work_keys_str_mv	AT jiangwang fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT yilv fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT junchenwang fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT furongma fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT yalidu fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT xinfan fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT menglinwang fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy AT jiake fullyautomatedsegmentationintemporalbonectwithneuralnetworkapreliminaryassessmentstudy
_version_	1718429158845972480

Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study

Ejemplares similares