MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism

Abstract Accurate segmentation of brain tumor magnetic resonance imaging (MRI) is crucial for treatment planning. Addressing the challenges of complex tumor structures and inadequate cross‐channel information utilization in Unet‐based segmentation, this paper proposes the multi‐scale residual brain...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyan Shen, Ju Wang, Yuhua Zhao, Rui Zhou, Han Gao, Jiakai Zhang, Hongming Shen
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Image Processing
Subjects:
Online Access:https://doi.org/10.1049/ipr2.13266
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121436967600128
author Xiaoyan Shen
Ju Wang
Yuhua Zhao
Rui Zhou
Han Gao
Jiakai Zhang
Hongming Shen
author_facet Xiaoyan Shen
Ju Wang
Yuhua Zhao
Rui Zhou
Han Gao
Jiakai Zhang
Hongming Shen
author_sort Xiaoyan Shen
collection DOAJ
description Abstract Accurate segmentation of brain tumor magnetic resonance imaging (MRI) is crucial for treatment planning. Addressing the challenges of complex tumor structures and inadequate cross‐channel information utilization in Unet‐based segmentation, this paper proposes the multi‐scale residual brain tumor MRI segmentation network (MRS‐Net) incorporating an attention mechanism to enhance segmentation accuracy. First, the double residual feature fusion module is utilized to enhance the fusion of feature information between different levels. Second, the Atrous Spatial Pyramid Pooling is introduced as a bridging module of the network to capture the features at different scales of the image, so as to enhance the extraction capability of the network for detailed features. Finally, the inverted residual coordinate attention module replaces the direct splicing in Unet to fuse the large feature information at each level and scale, thus enhancing the model's ability to recognize the spatial location information of brain tumors. The Dice coefficients, positive predictive values (PPVs), sensitivities (Sensitivity) and Hausdorff distance (HD), which are the four evaluation indexes, reach 84.54%, 87.43%, 88.37% and 2.248, respectively, which are improved by 1.85%, 2.11%, 2.88% and 6.0%, respectively, compared with Unet. The experimental results show that MRS‐Net achieves better brain tumor image segmentation.
format Article
id doaj-art-2f45fb2429e24fbc8eceac41b1b544a1
institution Kabale University
issn 1751-9659
1751-9667
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Image Processing
spelling doaj-art-2f45fb2429e24fbc8eceac41b1b544a12024-12-16T04:00:31ZengWileyIET Image Processing1751-96591751-96672024-12-0118144542455010.1049/ipr2.13266MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanismXiaoyan Shen0Ju Wang1Yuhua Zhao2Rui Zhou3Han Gao4Jiakai Zhang5Hongming Shen6School of Information Science and Technology Nantong University Nantong ChinaSchool of Information Science and Technology Nantong University Nantong ChinaYancheng Tongzhou Orthopedic Hospital Yancheng ChinaZhang Jian College Nantong University Nantong ChinaJiangsu Cancer Hospital Nanjing ChinaSchool of Information Science and Technology Nantong University Nantong ChinaSchool of Microelectronics and School of Integrated Circuits (Jiangsu Key Laboratory of Semi. Dev. & IC Design, Package and Test) Nantong University Nantong ChinaAbstract Accurate segmentation of brain tumor magnetic resonance imaging (MRI) is crucial for treatment planning. Addressing the challenges of complex tumor structures and inadequate cross‐channel information utilization in Unet‐based segmentation, this paper proposes the multi‐scale residual brain tumor MRI segmentation network (MRS‐Net) incorporating an attention mechanism to enhance segmentation accuracy. First, the double residual feature fusion module is utilized to enhance the fusion of feature information between different levels. Second, the Atrous Spatial Pyramid Pooling is introduced as a bridging module of the network to capture the features at different scales of the image, so as to enhance the extraction capability of the network for detailed features. Finally, the inverted residual coordinate attention module replaces the direct splicing in Unet to fuse the large feature information at each level and scale, thus enhancing the model's ability to recognize the spatial location information of brain tumors. The Dice coefficients, positive predictive values (PPVs), sensitivities (Sensitivity) and Hausdorff distance (HD), which are the four evaluation indexes, reach 84.54%, 87.43%, 88.37% and 2.248, respectively, which are improved by 1.85%, 2.11%, 2.88% and 6.0%, respectively, compared with Unet. The experimental results show that MRS‐Net achieves better brain tumor image segmentation.https://doi.org/10.1049/ipr2.13266image processingimage segmentation
spellingShingle Xiaoyan Shen
Ju Wang
Yuhua Zhao
Rui Zhou
Han Gao
Jiakai Zhang
Hongming Shen
MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism
IET Image Processing
image processing
image segmentation
title MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism
title_full MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism
title_fullStr MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism
title_full_unstemmed MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism
title_short MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism
title_sort mrs net brain tumour segmentation network based on feature fusion and attention mechanism
topic image processing
image segmentation
url https://doi.org/10.1049/ipr2.13266
work_keys_str_mv AT xiaoyanshen mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism
AT juwang mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism
AT yuhuazhao mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism
AT ruizhou mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism
AT hangao mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism
AT jiakaizhang mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism
AT hongmingshen mrsnetbraintumoursegmentationnetworkbasedonfeaturefusionandattentionmechanism