Cargando…

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network

OBJECTIVE: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. MATERIALS AND METHODS: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31–8...

Descripción completa

Detalles Bibliográficos
Autores principales: Yoo, Seung-Jin, Yoon, Soon Ho, Lee, Jong Hyuk, Kim, Ki Hwan, Choi, Hyoung In, Park, Sang Joon, Goo, Jin Mo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Korean Society of Radiology 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7909864/
https://www.ncbi.nlm.nih.gov/pubmed/33169549
http://dx.doi.org/10.3348/kjr.2020.0318
_version_ 1783656014645559296
author Yoo, Seung-Jin
Yoon, Soon Ho
Lee, Jong Hyuk
Kim, Ki Hwan
Choi, Hyoung In
Park, Sang Joon
Goo, Jin Mo
author_facet Yoo, Seung-Jin
Yoon, Soon Ho
Lee, Jong Hyuk
Kim, Ki Hwan
Choi, Hyoung In
Park, Sang Joon
Goo, Jin Mo
author_sort Yoo, Seung-Jin
collection PubMed
description OBJECTIVE: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. MATERIALS AND METHODS: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31–89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. RESULTS: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). CONCLUSION: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.
format Online
Article
Text
id pubmed-7909864
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher The Korean Society of Radiology
record_format MEDLINE/PubMed
spelling pubmed-79098642021-03-04 Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network Yoo, Seung-Jin Yoon, Soon Ho Lee, Jong Hyuk Kim, Ki Hwan Choi, Hyoung In Park, Sang Joon Goo, Jin Mo Korean J Radiol Thoracic Imaging OBJECTIVE: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. MATERIALS AND METHODS: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31–89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. RESULTS: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). CONCLUSION: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images. The Korean Society of Radiology 2021-03 2020-10-30 /pmc/articles/PMC7909864/ /pubmed/33169549 http://dx.doi.org/10.3348/kjr.2020.0318 Text en Copyright © 2021 The Korean Society of Radiology http://creativecommons.org/licenses/by-nc/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Thoracic Imaging
Yoo, Seung-Jin
Yoon, Soon Ho
Lee, Jong Hyuk
Kim, Ki Hwan
Choi, Hyoung In
Park, Sang Joon
Goo, Jin Mo
Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network
title Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network
title_full Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network
title_fullStr Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network
title_full_unstemmed Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network
title_short Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network
title_sort automated lung segmentation on chest computed tomography images with extensive lung parenchymal abnormalities using a deep neural network
topic Thoracic Imaging
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7909864/
https://www.ncbi.nlm.nih.gov/pubmed/33169549
http://dx.doi.org/10.3348/kjr.2020.0318
work_keys_str_mv AT yooseungjin automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork
AT yoonsoonho automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork
AT leejonghyuk automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork
AT kimkihwan automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork
AT choihyoungin automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork
AT parksangjoon automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork
AT goojinmo automatedlungsegmentationonchestcomputedtomographyimageswithextensivelungparenchymalabnormalitiesusingadeepneuralnetwork