Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.

In recent years, the rapid development of deep neural networks has made great progress in automatic organ segmentation from abdominal CT scans. However, automatic segmentation for small organs (e.g., the pancreas) is still a challenging task. As an inconspicuous and small organ in the abdomen, the p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yingjing Yan, Defu Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/5a603d6f3dc84edcb0601716aee734c3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5a603d6f3dc84edcb0601716aee734c3
record_format	dspace
spelling	oai:doaj.org-article:5a603d6f3dc84edcb0601716aee734c32021-11-25T06:23:39ZMulti-scale U-like network with attention mechanism for automatic pancreas segmentation.1932-620310.1371/journal.pone.0252287https://doaj.org/article/5a603d6f3dc84edcb0601716aee734c32021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0252287https://doaj.org/toc/1932-6203In recent years, the rapid development of deep neural networks has made great progress in automatic organ segmentation from abdominal CT scans. However, automatic segmentation for small organs (e.g., the pancreas) is still a challenging task. As an inconspicuous and small organ in the abdomen, the pancreas has a high degree of anatomical variability and is indistinguishable from the surrounding organs and tissues, which usually leads to a very vague boundary. Therefore, the accuracy of pancreatic segmentation is sometimes below satisfaction. In this paper, we propose a 2.5D U-net with an attention mechanism. The proposed network includes 2D convolutional layers and 3D convolutional layers, which means that it requires less computational resources than 3D segmentation models while it can capture more spatial information along the third dimension than 2D segmentation models. Then We use a cascaded framework to increase the accuracy of segmentation results. We evaluate our network on the NIH pancreas dataset and measure the segmentation accuracy by the Dice similarity coefficient (DSC). Experimental results demonstrate a better performance compared with state-of-the-art methods.Yingjing YanDefu ZhangPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 5, p e0252287 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yingjing Yan Defu Zhang Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.
description	In recent years, the rapid development of deep neural networks has made great progress in automatic organ segmentation from abdominal CT scans. However, automatic segmentation for small organs (e.g., the pancreas) is still a challenging task. As an inconspicuous and small organ in the abdomen, the pancreas has a high degree of anatomical variability and is indistinguishable from the surrounding organs and tissues, which usually leads to a very vague boundary. Therefore, the accuracy of pancreatic segmentation is sometimes below satisfaction. In this paper, we propose a 2.5D U-net with an attention mechanism. The proposed network includes 2D convolutional layers and 3D convolutional layers, which means that it requires less computational resources than 3D segmentation models while it can capture more spatial information along the third dimension than 2D segmentation models. Then We use a cascaded framework to increase the accuracy of segmentation results. We evaluate our network on the NIH pancreas dataset and measure the segmentation accuracy by the Dice similarity coefficient (DSC). Experimental results demonstrate a better performance compared with state-of-the-art methods.
format	article
author	Yingjing Yan Defu Zhang
author_facet	Yingjing Yan Defu Zhang
author_sort	Yingjing Yan
title	Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.
title_short	Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.
title_full	Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.
title_fullStr	Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.
title_full_unstemmed	Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.
title_sort	multi-scale u-like network with attention mechanism for automatic pancreas segmentation.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/5a603d6f3dc84edcb0601716aee734c3
work_keys_str_mv	AT yingjingyan multiscaleulikenetworkwithattentionmechanismforautomaticpancreassegmentation AT defuzhang multiscaleulikenetworkwithattentionmechanismforautomaticpancreassegmentation
_version_	1718413745634410496

Multi-scale U-like network with attention mechanism for automatic pancreas segmentation.

Ejemplares similares