Hybrid attention mechanism of feature fusion for medical image segmentation

Author:

Tong Shanshan12,Zuo Zhentao134ORCID,Liu Zuxiang134,Sun Dengdi25,Zhou Tiangang134

Affiliation:

1. Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

2. AHU‐IAI AI Joint Laboratory Anhui University Hefei China

3. State Key Laboratory of Brain and Cognitive Science Institute of Biophysics, Chinese Academy of Sciences Beijing China

4. University of Chinese Academy of Sciences Beijing China

5. School of Artificial Intelligence Anhui University Hefei China

Abstract

AbstractTraditional convolution neural networks (CNN) have achieved good performance in multi‐organ segmentation of medical images. Due to the lack of ability to model long‐range dependencies and correlations between image pixels, CNN usually ignores the information of channel dimension. To further improve the performance of multi‐organ segmentation, a hybrid attention mechanism model is proposed. First, a CNN was used to extract multi‐scale feature maps and fed into the Channel Attention Enhancement Module (CAEM) to selectively pay attention to target organs in medical images, and the Transformer encoded tokenized image patches from CNN feature maps as the input sequence to model long‐range dependencies. Second, the decoder upsampled the output from Transformer and fused with the CAEM features in multi‐scale through skip connections. Finally, we introduced a Refinement Module (RM) after the decoder to improve feature correlations of the same organ and the feature discriminability between different organs. The model outperformed on dice coefficient (%) and hd95 on both the synapse multi‐organ segmentation and cardiac diagnosis challenge datasets. The hybrid attention mechanisms exhibited high efficiency and high segmentation accuracy in medical images.

Funder

Youth Innovation Promotion Association of the Chinese Academy of Sciences

Publisher

Institution of Engineering and Technology (IET)

Subject

Electrical and Electronic Engineering,Computer Vision and Pattern Recognition,Signal Processing,Software

Reference41 articles.

1. Codella N. Rotemberg V. Tschandl P. Celebi M.E. Dusza S. Gutman D. Helba B. Kalloo A. Liopyris K. Marchetti M. et al.:Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368 (2019)

2. Block Level Skip Connections Across Cascaded V-Net for Multi-Organ Segmentation

3. Li J. Wang W. Chen C. Zhang T. Zha S. Yu H. Wang J.:Transbtsv2: Wider instead of deeper transformer for medical image segmentation(2022)

4. Long J. Shelhamer E. Darrell T.:Fully convolutional networks for semantic segmentation. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp.3431–3440.IEEE Piscataway(2015)

5. He K. Zhang X. Ren S. Sun J.:Deep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp.770–778.IEEE Piscataway(2016)

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. MAGNet: A Convolutional Neural Network with Multi-Scale and Global Attention Modules for Medical Image Segmentation;2024 IEEE International Symposium on Circuits and Systems (ISCAS);2024-05-19

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3