[1]邹祥,王瑜,肖洪兵,等.基于有效感受野和注意力融合机制的脑肿瘤全自动分割[J].中国医学物理学杂志,2024,41(5):563-570.[doi:DOI:10.3969/j.issn.1005-202X.2024.05.006]
　ZOU Xiang,WANG Yu,XIAO Hongbing,et al.Fully-automatic brain tumor segmentation based on effective receptive field and attention fusion mechanism[J].Chinese Journal of Medical Physics,2024,41(5):563-570.[doi:DOI:10.3969/j.issn.1005-202X.2024.05.006]
点击复制

基于有效感受野和注意力融合机制的脑肿瘤全自动分割()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第5期
页码:
563-570
栏目:
医学影像物理
出版日期:
2024-05-23

文章信息/Info

Title:
Fully-automatic brain tumor segmentation based on effective receptive field and attention fusion mechanism
文章编号:
1005-202X（2024）05-0563-08
作者:
邹祥1; 王瑜1; 肖洪兵1; 杨迪2
1.北京工商大学计算机与人工智能学院， 北京 100048； 2.中工国际工程股份有限公司， 北京 100048
Author(s):
ZOU Xiang1;  WANG Yu1;  XIAO Hongbing1;  YANG Di2
1. School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China 2. China CAMC Engineering Co., Ltd., Beijing 100048, China
关键词:
脑肿瘤分割; EAU-Net; 有效感受野拓展模块; 注意力融合模块; 倒残差结构
Keywords:
Keywords: brain tumor segmentation EAU-Net effective receptive field expansion block attention fusion module inverted residual structure
分类号:
R318；TP181
DOI:
DOI:10.3969/j.issn.1005-202X.2024.05.006
文献标志码:
A
摘要:
深度学习在医学图像分割领域取得了显著成果，但其在脑肿瘤分割任务中，仍面临感受野不足、冗余信息过多、信息丢失等问题；为此，本研究提出一种基于编-解码结构的脑肿瘤分割网络模型（EAU-Net）。EAU-Net采用有效感受野拓展模块和注意力融合模块改善脑肿瘤分割网络感受野不足与冗余信息过多带来的不利影响；同时，引入基于倒残差结构的瓶颈重采样模块，有效避免上下采样时造成的信息损失，并采用深度卷积降低网络的计算量。在BraTS2020数据集上的实验结果表明，EAU-Net获得最优的分割精度，验证了其在脑肿瘤分割任务中的可行性和有效性。
Abstract:
Abstract: Despite significant achievements of deep learning in medical image segmentation, there are challenges for brain tumor segmentation using deep learning, such as insufficient receptive field, excessive redundant information, and information loss. To address these issues, a novel brain tumor segmentation network model (EAU-Net) is proposed based on encoder-decoder structure. EAU-Net incorporates an effective receptive field expansion block and an attention fusion module to minimize the adverse effects caused by insufficient receptive field and excessive redundant information which often occurred in the current brain tumor segmentation network. Additionally, a bottleneck resampling module based on inverted residual structure is introduced to effectively avoid information loss during upsampling and downsampling, while deep convolutions are used to reduce computational complexity. Experimental results on the BraTS2020 dataset reveal that EAU-Net achieves the highest segmentation accuracy, demonstrating its feasibility and effectiveness for brain tumor segmentation.

相似文献/References:

[1]段逸凡,肖洪兵,Rahman Md Mostafizur.基于3DSEU-Net不确定性循环焦点平均教师的半监督脑肿瘤分割[J].中国医学物理学杂志,2023,40(9):1121.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.010]
　DUAN Yifan,XIAO Hongbing,Rahman Md Mostafizur.Semi-supervised learning for brain tumor segmentation through 3DSEU-Net as uncertainty-aware mean teacher and cyclical focal loss[J].Chinese Journal of Medical Physics,2023,40(5):1121.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.010]

备注/Memo

备注/Memo:
【投稿日期】2023-12-16 【基金项目】北京市自然科学基金-北京市教育委员会科技计划重点项目（KZ202110011015） 【作者简介】邹祥，硕士研究生，研究方向：图像处理、机器学习，E-mail: 571529288@qq.com 【通信作者】王瑜，博士后，教授，博士生导师，研究方向：图像处理、模式识别，E-mail: wangyu@btbu.edu.cn
更新日期/Last Update: 2024-05-24