Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor

As a non-invasive, low-cost medical imaging technology, magnetic resonance imaging (MRI) has become an important tool for brain tumor diagnosis. Many scholars have carried out some related researches on MRI brain tumor segmentation based on deep convolutional neural networks, and have achieved good...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xueqin He, Wenjie Xu, Jane Yang, Jianyao Mao, Sifang Chen, Zhanxiang Wang
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	magnetic resonance imaging (MRI) semantic segmentation convolutional neural network residual network attention mechanism brain tumor Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/8d2e0e3645d74b22ae74c975c9cedc4b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8d2e0e3645d74b22ae74c975c9cedc4b
record_format	dspace
spelling	oai:doaj.org-article:8d2e0e3645d74b22ae74c975c9cedc4b2021-12-01T08:00:53ZDeep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor1662-453X10.3389/fnins.2021.782968https://doaj.org/article/8d2e0e3645d74b22ae74c975c9cedc4b2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnins.2021.782968/fullhttps://doaj.org/toc/1662-453XAs a non-invasive, low-cost medical imaging technology, magnetic resonance imaging (MRI) has become an important tool for brain tumor diagnosis. Many scholars have carried out some related researches on MRI brain tumor segmentation based on deep convolutional neural networks, and have achieved good performance. However, due to the large spatial and structural variability of brain tumors and low image contrast, the segmentation of MRI brain tumors is challenging. Deep convolutional neural networks often lead to the loss of low-level details as the network structure deepens, and they cannot effectively utilize the multi-scale feature information. Therefore, a deep convolutional neural network with a multi-scale attention feature fusion module (MAFF-ResUNet) is proposed to address them. The MAFF-ResUNet consists of a U-Net with residual connections and a MAFF module. The combination of residual connections and skip connections fully retain low-level detailed information and improve the global feature extraction capability of the encoding block. Besides, the MAFF module selectively extracts useful information from the multi-scale hybrid feature map based on the attention mechanism to optimize the features of each layer and makes full use of the complementary feature information of different scales. The experimental results on the BraTs 2019 MRI dataset show that the MAFF-ResUNet can learn the edge structure of brain tumors better and achieve high accuracy.Xueqin HeWenjie XuJane YangJianyao MaoSifang ChenZhanxiang WangZhanxiang WangFrontiers Media S.A.articlemagnetic resonance imaging (MRI)semantic segmentationconvolutional neural networkresidual networkattention mechanismbrain tumorNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	magnetic resonance imaging (MRI) semantic segmentation convolutional neural network residual network attention mechanism brain tumor Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	magnetic resonance imaging (MRI) semantic segmentation convolutional neural network residual network attention mechanism brain tumor Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Xueqin He Wenjie Xu Jane Yang Jianyao Mao Sifang Chen Zhanxiang Wang Zhanxiang Wang Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor
description	As a non-invasive, low-cost medical imaging technology, magnetic resonance imaging (MRI) has become an important tool for brain tumor diagnosis. Many scholars have carried out some related researches on MRI brain tumor segmentation based on deep convolutional neural networks, and have achieved good performance. However, due to the large spatial and structural variability of brain tumors and low image contrast, the segmentation of MRI brain tumors is challenging. Deep convolutional neural networks often lead to the loss of low-level details as the network structure deepens, and they cannot effectively utilize the multi-scale feature information. Therefore, a deep convolutional neural network with a multi-scale attention feature fusion module (MAFF-ResUNet) is proposed to address them. The MAFF-ResUNet consists of a U-Net with residual connections and a MAFF module. The combination of residual connections and skip connections fully retain low-level detailed information and improve the global feature extraction capability of the encoding block. Besides, the MAFF module selectively extracts useful information from the multi-scale hybrid feature map based on the attention mechanism to optimize the features of each layer and makes full use of the complementary feature information of different scales. The experimental results on the BraTs 2019 MRI dataset show that the MAFF-ResUNet can learn the edge structure of brain tumors better and achieve high accuracy.
format	article
author	Xueqin He Wenjie Xu Jane Yang Jianyao Mao Sifang Chen Zhanxiang Wang Zhanxiang Wang
author_facet	Xueqin He Wenjie Xu Jane Yang Jianyao Mao Sifang Chen Zhanxiang Wang Zhanxiang Wang
author_sort	Xueqin He
title	Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor
title_short	Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor
title_full	Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor
title_fullStr	Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor
title_full_unstemmed	Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor
title_sort	deep convolutional neural network with a multi-scale attention feature fusion module for segmentation of multimodal brain tumor
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/8d2e0e3645d74b22ae74c975c9cedc4b
work_keys_str_mv	AT xueqinhe deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor AT wenjiexu deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor AT janeyang deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor AT jianyaomao deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor AT sifangchen deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor AT zhanxiangwang deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor AT zhanxiangwang deepconvolutionalneuralnetworkwithamultiscaleattentionfeaturefusionmoduleforsegmentationofmultimodalbraintumor
_version_	1718405425531977728

Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor

Ejemplares similares