Automatic detect lung node with deep learning in segmentation and imbalance data labeling

Abstract In this study, a novel method with the U-Net-based network architecture, 2D U-Net, is employed to segment the position of lung nodules, which are an early symptom of lung cancer and have a high probability of becoming a carcinoma, especially when a lung nodule is bigger than 15 $$\mathrm{m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ting-Wei Chiu, Yu-Lin Tsai, Shun-Feng Su
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b06b32aa28454d3185a755c627a8e2e6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b06b32aa28454d3185a755c627a8e2e6
record_format	dspace
spelling	oai:doaj.org-article:b06b32aa28454d3185a755c627a8e2e62021-12-02T15:00:14ZAutomatic detect lung node with deep learning in segmentation and imbalance data labeling10.1038/s41598-021-90599-42045-2322https://doaj.org/article/b06b32aa28454d3185a755c627a8e2e62021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90599-4https://doaj.org/toc/2045-2322Abstract In this study, a novel method with the U-Net-based network architecture, 2D U-Net, is employed to segment the position of lung nodules, which are an early symptom of lung cancer and have a high probability of becoming a carcinoma, especially when a lung nodule is bigger than 15 $$\mathrm{mm}^2$$ mm 2 . A serious problem of considering deep learning for all medical images is imbalanced labeling between foreground and background. The lung nodule is the foreground which accounts for a lower percentage in a whole image. The evaluation function adopted in this study is dice coefficient loss, which is usually used in image segmentation tasks. The proposed pre-processing method in this study is to use complementary labeling as the input in U-Net. With this method, the labeling is swapped. The no-nodule position is labeled. And the position of the nodule becomes non-labeled. The result shows that the proposal in this study is efficient in a small quantity of data. This method, complementary labeling could be used in a small data quantity scenario. With the use of ROI segmentation model in the data pre-processing, the results of lung nodule detection can be improved a lot as shown in the experiments.Ting-Wei ChiuYu-Lin TsaiShun-Feng SuNature 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 Ting-Wei Chiu Yu-Lin Tsai Shun-Feng Su Automatic detect lung node with deep learning in segmentation and imbalance data labeling
description	Abstract In this study, a novel method with the U-Net-based network architecture, 2D U-Net, is employed to segment the position of lung nodules, which are an early symptom of lung cancer and have a high probability of becoming a carcinoma, especially when a lung nodule is bigger than 15 $$\mathrm{mm}^2$$ mm 2 . A serious problem of considering deep learning for all medical images is imbalanced labeling between foreground and background. The lung nodule is the foreground which accounts for a lower percentage in a whole image. The evaluation function adopted in this study is dice coefficient loss, which is usually used in image segmentation tasks. The proposed pre-processing method in this study is to use complementary labeling as the input in U-Net. With this method, the labeling is swapped. The no-nodule position is labeled. And the position of the nodule becomes non-labeled. The result shows that the proposal in this study is efficient in a small quantity of data. This method, complementary labeling could be used in a small data quantity scenario. With the use of ROI segmentation model in the data pre-processing, the results of lung nodule detection can be improved a lot as shown in the experiments.
format	article
author	Ting-Wei Chiu Yu-Lin Tsai Shun-Feng Su
author_facet	Ting-Wei Chiu Yu-Lin Tsai Shun-Feng Su
author_sort	Ting-Wei Chiu
title	Automatic detect lung node with deep learning in segmentation and imbalance data labeling
title_short	Automatic detect lung node with deep learning in segmentation and imbalance data labeling
title_full	Automatic detect lung node with deep learning in segmentation and imbalance data labeling
title_fullStr	Automatic detect lung node with deep learning in segmentation and imbalance data labeling
title_full_unstemmed	Automatic detect lung node with deep learning in segmentation and imbalance data labeling
title_sort	automatic detect lung node with deep learning in segmentation and imbalance data labeling
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b06b32aa28454d3185a755c627a8e2e6
work_keys_str_mv	AT tingweichiu automaticdetectlungnodewithdeeplearninginsegmentationandimbalancedatalabeling AT yulintsai automaticdetectlungnodewithdeeplearninginsegmentationandimbalancedatalabeling AT shunfengsu automaticdetectlungnodewithdeeplearninginsegmentationandimbalancedatalabeling
_version_	1718389225008660480

Automatic detect lung node with deep learning in segmentation and imbalance data labeling

Ejemplares similares