Vision graph U-Net: Geometric learning enhanced encoder for medical image segmentation and restoration

计算机科学 人工智能 编码器 图形 图像分割 分割 图像(数学) 计算机视觉 理论计算机科学 操作系统
作者
Yuanhong Jiang,Qiaoqiao Ding,Yu Guang Wang,Píetro Lió,Xiaoqun Zhang
出处
期刊:Inverse Problems and Imaging [American Institute of Mathematical Sciences]
卷期号:18 (3): 672-689 被引量:1
标识
DOI:10.3934/ipi.2023049
摘要

Convolutional neural networks (CNNs) are known for their powerful feature extraction ability, and have achieved great success in a variety of image processing tasks. However, convolution filters only extract local features and neglect long-range self-similarity information, which is the vital prior information commonly existing in image data. To this end, we put forward a new backbone neural network: vision graph U-Net (VGU-Net), which is the first model to construct multi-scale graph structures through the hierarchical down-sampling layers of the U-Net architecture. The graph structure is constructed by the self-attention mechanism. By replacing CNNs in the bottleneck layer and skip connection layers with the graph convolution networks (GCNs), the multi-scale graph structure visualization allows an interpretation of long-range interactions. We extend the VGU-Net backbone model for the widely considered compressed sensing MR image reconstruction task and propose a knowledge-driven deep unrolling scheme based on the half-quadratic splitting algorithm, which combines the interpretability of knowledge-driven model with the versatility of data-driven deep learning method to achieve remarkable reconstruction results. Moreover, we verify the segmentation ability of the VGU-Net backbone model on the multi-modality brain tumor segmentation dataset and white blood cell image segmentation dataset, and both achieve state-of-the-art performance. The code is publicly available at https://github.com/jyh6681/VGU-Net.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
顾矜应助xinxin采纳,获得10
1秒前
Yuntao_Chen完成签到,获得积分10
1秒前
2秒前
淡淡的豁应助轻松的笑容采纳,获得30
2秒前
英姑应助苗条梦玉采纳,获得10
3秒前
烟花应助ZH采纳,获得10
3秒前
柯一一应助xnzll采纳,获得10
4秒前
4秒前
5秒前
6秒前
晚伍发布了新的文献求助10
8秒前
魏少爷发布了新的文献求助10
8秒前
8秒前
研友_xLOMQZ完成签到,获得积分0
9秒前
9秒前
de发布了新的文献求助10
9秒前
研友_8DAv0L发布了新的文献求助10
9秒前
天天快乐应助纯真采蓝采纳,获得10
10秒前
10秒前
10秒前
11秒前
Jasper应助稻下乘凉采纳,获得100
11秒前
柒月发布了新的文献求助10
12秒前
14秒前
tyf完成签到,获得积分10
14秒前
浮熙发布了新的文献求助10
14秒前
kykykkk完成签到,获得积分10
15秒前
redking发布了新的文献求助10
15秒前
比巴卜发布了新的文献求助10
17秒前
64658应助研友_8DAv0L采纳,获得10
18秒前
de完成签到,获得积分10
19秒前
天天快乐应助Endeavor采纳,获得10
20秒前
20秒前
22秒前
一只住在海边的猫完成签到,获得积分10
24秒前
25秒前
26秒前
wade发布了新的文献求助10
26秒前
纯真采蓝发布了新的文献求助10
28秒前
29秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975755
求助须知:如何正确求助?哪些是违规求助? 3520108
关于积分的说明 11200829
捐赠科研通 3256492
什么是DOI,文献DOI怎么找? 1798298
邀请新用户注册赠送积分活动 877509
科研通“疑难数据库(出版商)”最低求助积分说明 806403