Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks

Abstract This paper presents a fully automatic and end-to-end optimised airway segmentation method for thoracic computed tomography, based on the U-Net architecture. We use a simple and low-memory 3D U-Net as backbone, which allows the method to process large 3D image patches, often comprising full...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Antonio Garcia-Uceda, Raghavendra Selvan, Zaigham Saghir, Harm A. W. M. Tiddens, Marleen de Bruijne
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/04be7a8e66d846138c66cbc7a117dc5e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:04be7a8e66d846138c66cbc7a117dc5e
record_format dspace
spelling oai:doaj.org-article:04be7a8e66d846138c66cbc7a117dc5e2021-12-02T16:35:37ZAutomatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks10.1038/s41598-021-95364-12045-2322https://doaj.org/article/04be7a8e66d846138c66cbc7a117dc5e2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95364-1https://doaj.org/toc/2045-2322Abstract This paper presents a fully automatic and end-to-end optimised airway segmentation method for thoracic computed tomography, based on the U-Net architecture. We use a simple and low-memory 3D U-Net as backbone, which allows the method to process large 3D image patches, often comprising full lungs, in a single pass through the network. This makes the method simple, robust and efficient. We validated the proposed method on three datasets with very different characteristics and various airway abnormalities: (1) a dataset of pediatric patients including subjects with cystic fibrosis, (2) a subset of the Danish Lung Cancer Screening Trial, including subjects with chronic obstructive pulmonary disease, and (3) the EXACT’09 public dataset. We compared our method with other state-of-the-art airway segmentation methods, including relevant learning-based methods in the literature evaluated on the EXACT’09 data. We show that our method can extract highly complete airway trees with few false positive errors, on scans from both healthy and diseased subjects, and also that the method generalizes well across different datasets. On the EXACT’09 test set, our method achieved the second highest sensitivity score among all methods that reported good specificity.Antonio Garcia-UcedaRaghavendra SelvanZaigham SaghirHarm A. W. M. TiddensMarleen de BruijneNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Antonio Garcia-Uceda
Raghavendra Selvan
Zaigham Saghir
Harm A. W. M. Tiddens
Marleen de Bruijne
Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks
description Abstract This paper presents a fully automatic and end-to-end optimised airway segmentation method for thoracic computed tomography, based on the U-Net architecture. We use a simple and low-memory 3D U-Net as backbone, which allows the method to process large 3D image patches, often comprising full lungs, in a single pass through the network. This makes the method simple, robust and efficient. We validated the proposed method on three datasets with very different characteristics and various airway abnormalities: (1) a dataset of pediatric patients including subjects with cystic fibrosis, (2) a subset of the Danish Lung Cancer Screening Trial, including subjects with chronic obstructive pulmonary disease, and (3) the EXACT’09 public dataset. We compared our method with other state-of-the-art airway segmentation methods, including relevant learning-based methods in the literature evaluated on the EXACT’09 data. We show that our method can extract highly complete airway trees with few false positive errors, on scans from both healthy and diseased subjects, and also that the method generalizes well across different datasets. On the EXACT’09 test set, our method achieved the second highest sensitivity score among all methods that reported good specificity.
format article
author Antonio Garcia-Uceda
Raghavendra Selvan
Zaigham Saghir
Harm A. W. M. Tiddens
Marleen de Bruijne
author_facet Antonio Garcia-Uceda
Raghavendra Selvan
Zaigham Saghir
Harm A. W. M. Tiddens
Marleen de Bruijne
author_sort Antonio Garcia-Uceda
title Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks
title_short Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks
title_full Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks
title_fullStr Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks
title_full_unstemmed Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks
title_sort automatic airway segmentation from computed tomography using robust and efficient 3-d convolutional neural networks
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/04be7a8e66d846138c66cbc7a117dc5e
work_keys_str_mv AT antoniogarciauceda automaticairwaysegmentationfromcomputedtomographyusingrobustandefficient3dconvolutionalneuralnetworks
AT raghavendraselvan automaticairwaysegmentationfromcomputedtomographyusingrobustandefficient3dconvolutionalneuralnetworks
AT zaighamsaghir automaticairwaysegmentationfromcomputedtomographyusingrobustandefficient3dconvolutionalneuralnetworks
AT harmawmtiddens automaticairwaysegmentationfromcomputedtomographyusingrobustandefficient3dconvolutionalneuralnetworks
AT marleendebruijne automaticairwaysegmentationfromcomputedtomographyusingrobustandefficient3dconvolutionalneuralnetworks
_version_ 1718383673394331648