DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images

(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images; (2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng Chen, Jiancang Zhou, Kangneng Zhou, Zhiliang Wang, Ruoxiu Xiao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	COVID-19 infection segmentation 3D convolutional neural network data enhancement weighted loss function Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/08b8ddd4758d43b2b95187f2f6862b1a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:08b8ddd4758d43b2b95187f2f6862b1a
record_format	dspace
spelling	oai:doaj.org-article:08b8ddd4758d43b2b95187f2f6862b1a2021-11-25T17:20:05ZDW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images10.3390/diagnostics111119422075-4418https://doaj.org/article/08b8ddd4758d43b2b95187f2f6862b1a2021-10-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/1942https://doaj.org/toc/2075-4418(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images; (2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to geometric characteristics. Due to the complexity of tubular tissues in lung region, they are clustered to the lung parenchyma center based on their filtered possibility. Thus, infection is improved after data enhancement. Then, deep weighted UNet is established to refining 3D infection texture, and weighted loss function is introduced. It changes cost calculation of different samples, causing target samples to dominate convergence direction. Finally, the trained network effectively extracts 3D infection from CT images by adjusting driving strategy of different samples. (3) Results: Using Accuracy, Precision, Recall and Coincidence rate, 20 subjects from a private dataset and eight subjects from Kaggle Competition COVID-19 CT dataset tested this method in hold-out validation framework. This work achieved good performance both in the private dataset (99.94–00.02%, 60.42–11.25%, 70.79–09.35% and 63.15–08.35%) and public dataset (99.73–00.12%, 77.02–06.06%, 41.23–08.61% and 52.50–08.18%). We also applied some extra indicators to test data augmentation and different models. The statistical tests have verified the significant difference of different models. (4) Conclusions: This study provides a COVID-19 infection segmentation technology, which provides an important prerequisite for the quantitative analysis of COVID-19 CT images.Cheng ChenJiancang ZhouKangneng ZhouZhiliang WangRuoxiu XiaoMDPI AGarticleCOVID-19infection segmentation3D convolutional neural networkdata enhancementweighted loss functionMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 1942, p 1942 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	COVID-19 infection segmentation 3D convolutional neural network data enhancement weighted loss function Medicine (General) R5-920
spellingShingle	COVID-19 infection segmentation 3D convolutional neural network data enhancement weighted loss function Medicine (General) R5-920 Cheng Chen Jiancang Zhou Kangneng Zhou Zhiliang Wang Ruoxiu Xiao DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images
description	(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images; (2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to geometric characteristics. Due to the complexity of tubular tissues in lung region, they are clustered to the lung parenchyma center based on their filtered possibility. Thus, infection is improved after data enhancement. Then, deep weighted UNet is established to refining 3D infection texture, and weighted loss function is introduced. It changes cost calculation of different samples, causing target samples to dominate convergence direction. Finally, the trained network effectively extracts 3D infection from CT images by adjusting driving strategy of different samples. (3) Results: Using Accuracy, Precision, Recall and Coincidence rate, 20 subjects from a private dataset and eight subjects from Kaggle Competition COVID-19 CT dataset tested this method in hold-out validation framework. This work achieved good performance both in the private dataset (99.94–00.02%, 60.42–11.25%, 70.79–09.35% and 63.15–08.35%) and public dataset (99.73–00.12%, 77.02–06.06%, 41.23–08.61% and 52.50–08.18%). We also applied some extra indicators to test data augmentation and different models. The statistical tests have verified the significant difference of different models. (4) Conclusions: This study provides a COVID-19 infection segmentation technology, which provides an important prerequisite for the quantitative analysis of COVID-19 CT images.
format	article
author	Cheng Chen Jiancang Zhou Kangneng Zhou Zhiliang Wang Ruoxiu Xiao
author_facet	Cheng Chen Jiancang Zhou Kangneng Zhou Zhiliang Wang Ruoxiu Xiao
author_sort	Cheng Chen
title	DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images
title_short	DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images
title_full	DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images
title_fullStr	DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images
title_full_unstemmed	DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images
title_sort	dw-unet: loss balance under local-patch for 3d infection segmentation from covid-19 ct images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/08b8ddd4758d43b2b95187f2f6862b1a
work_keys_str_mv	AT chengchen dwunetlossbalanceunderlocalpatchfor3dinfectionsegmentationfromcovid19ctimages AT jiancangzhou dwunetlossbalanceunderlocalpatchfor3dinfectionsegmentationfromcovid19ctimages AT kangnengzhou dwunetlossbalanceunderlocalpatchfor3dinfectionsegmentationfromcovid19ctimages AT zhiliangwang dwunetlossbalanceunderlocalpatchfor3dinfectionsegmentationfromcovid19ctimages AT ruoxiuxiao dwunetlossbalanceunderlocalpatchfor3dinfectionsegmentationfromcovid19ctimages
_version_	1718412451557408768

DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images

Ejemplares similares