ETUNet:Exploring efficient transformer enhanced UNet for 3D brain tumor segmentation

编码器 分割 计算机科学 人工智能 图像分割 深度学习 瓶颈 模式识别(心理学) 计算机视觉 嵌入式系统 操作系统
作者
W. Zhang,Shanxiong Chen,Yuqi Ma,Yu Liu,Xu Cao
出处
期刊:Computers in Biology and Medicine [Elsevier]
卷期号:171: 108005-108005 被引量:3
标识
DOI:10.1016/j.compbiomed.2024.108005
摘要

Medical image segmentation is a crucial topic in medical image processing. Accurately segmenting brain tumor regions from multimodal MRI scans is essential for clinical diagnosis and survival prediction. However, similar intensity distributions, variable tumor shapes, and fuzzy boundaries pose severe challenges for brain tumor segmentation. Traditional segmentation networks based on UNet struggle to establish explicit long-range dependencies from the feature space due to the limitations of the CNN receptive field. This is particularly crucial for dense prediction tasks such as brain tumor segmentation. Recent works have incorporated the powerful global modeling capability of Transformer into UNet to achieve more precise segmentation results. Nevertheless, these methods encounter some issues: (1) the global information is often modeled by simply stacking Transformer layers for a specific module, resulting in high computational complexity and underutilization of the potential of the UNet architecture; (2) the rich boundary information of tumor subregions in multi-scale features is often overlooked. Motivated by these challenges, we propose an advanced fusion of Transformer with UNet by reexamining the core three parts (encoder, bottleneck, and skip connections). Firstly, we introduce a CNN-Transformer module in the encoder to replace the traditional CNN module, enabling the capture of deep spatial dependencies from input images. To address high-level semantic information, we incorporate a computationally efficient spatial-channel attention layer in the bottleneck for global interaction, highlighting important semantic features from the encoder path output. For irregular lesions, we fuse the multi-scale features from the encoder output and the decoder features in the skip connections by calculating cross-attention. This adaptive querying of valuable information from multi-scale features enhances the boundary localization ability of the decoder path and suppresses redundant features with low correlation. Compared to existing methods, our model further enhances the learning capacity of the overall UNet architecture while maintaining low computational complexity. Experimental results on the BraTS2018 and BraTS2020 datasets for brain tumor segmentation tasks demonstrate that our model achieves comparable or superior results compared to recent CNN or Transformer-based models. The average DSC and HD95 on the two datasets are 0.854, 6.688, and 0.862, 5.455 respectively. At the same time, our model achieves optimal segmentation of Enhancing tumors, showcasing the effectiveness of our method. Our code will be made publicly available at https://github.com/wzhangck/ETUnet.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
彩色觅荷完成签到,获得积分10
3秒前
Ninomae发布了新的文献求助10
3秒前
4秒前
渣渣慧完成签到,获得积分10
4秒前
5秒前
斯文败类应助wb采纳,获得10
6秒前
Ninomae完成签到,获得积分10
7秒前
9秒前
9秒前
yinyue发布了新的文献求助10
10秒前
852应助Echo采纳,获得10
11秒前
12秒前
神乐咩咩子完成签到,获得积分20
13秒前
15秒前
16秒前
NZH关闭了NZH文献求助
17秒前
17秒前
18秒前
GEZI发布了新的文献求助10
19秒前
今宵 别梦寒完成签到,获得积分10
19秒前
21秒前
蓝色条纹衫完成签到 ,获得积分10
22秒前
慕青应助雪掩的往事采纳,获得10
23秒前
23秒前
香蕉觅云应助落后的瑾瑜采纳,获得10
24秒前
Akim应助想要发文章采纳,获得10
24秒前
Echo发布了新的文献求助10
24秒前
25秒前
陈早睡完成签到,获得积分10
25秒前
26秒前
26秒前
顺利念柏发布了新的文献求助10
28秒前
渝安发布了新的文献求助10
28秒前
我一定要坚持下去完成签到,获得积分10
29秒前
29秒前
Echo完成签到,获得积分10
31秒前
pinge发布了新的文献求助10
32秒前
Rixxed发布了新的文献求助10
32秒前
34秒前
35秒前
高分求助中
The ACS Guide to Scholarly Communication 2500
Sustainability in Tides Chemistry 2000
Studien zur Ideengeschichte der Gesetzgebung 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 810
Pharmacogenomics: Applications to Patient Care, Third Edition 800
Genera Insectorum: Mantodea, Fam. Mantidæ, Subfam. Hymenopodinæ (Classic Reprint) 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3082549
求助须知:如何正确求助?哪些是违规求助? 2735847
关于积分的说明 7539036
捐赠科研通 2385432
什么是DOI,文献DOI怎么找? 1264844
科研通“疑难数据库(出版商)”最低求助积分说明 612830
版权声明 597685