U-MLP: MLP-based ultralight refinement network for medical image segmentation

计算机科学 人工智能 分割 卷积神经网络 模式识别(心理学) 滑动窗口协议 编码器 变压器 图像分割 窗口(计算) 物理 量子力学 电压 操作系统
作者
Shuo Gao,Wenhui Yang,Menglei Xu,Hao Zhang,Yu Hong,Airong Qian,Wenjuan Zhang
出处
期刊:Computers in Biology and Medicine [Elsevier]
卷期号:165: 107460-107460 被引量:1
标识
DOI:10.1016/j.compbiomed.2023.107460
摘要

The convolutional neural network (CNN) and Transformer play an important role in computer-aided diagnosis and intelligent medicine. However, CNN cannot obtain long-range dependence, and Transformer has shortcomings in computational complexity and a large number of parameters. Recently, compared with CNN and Transformer, the Multi-Layer Perceptron (MLP)-based medical image processing network can achieve higher accuracy with smaller computational and parametric quantities. Hence, in this work, we propose an encoder-decoder network, U-MLP, based on the ReMLP block. The ReMLP block contains an overlapping sliding window mechanism and a Multi-head Gate Self-Attention (MGSA) module, where the overlapping sliding window can extract local features of the image like convolution, then combines MGSA to fuse the information extracted from multiple dimensions to obtain more contextual semantic information. Meanwhile, to increase the generalization ability of the model, we design the Vague Region Refinement (VRRE) module, which uses the primary features generated by network inference to create local reference features, thus determining the pixel class by inferring the proximity between local features and labeled features. Extensive experimental evaluation shows U-MLP boosts the performance of segmentation. In the skin lesions, spleen, and left atrium segmentation on three benchmark datasets, our U-MLP method achieved a dice similarity coefficient of 88.27%, 97.61%, and 95.91% on the test set, respectively, outperforming 7 state-of-the-art methods.
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
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
原子发布了新的文献求助10
刚刚
田様应助西出阳关采纳,获得10
刚刚
刚刚
many_stone完成签到,获得积分10
1秒前
1秒前
1秒前
saily完成签到,获得积分10
2秒前
ruanyh发布了新的文献求助20
2秒前
seannnnnnn完成签到,获得积分10
2秒前
wuliumu发布了新的文献求助10
2秒前
lunar完成签到,获得积分10
3秒前
NexusExplorer应助kourosz采纳,获得10
3秒前
咕咕咕完成签到,获得积分10
3秒前
3秒前
CooperLI发布了新的文献求助10
3秒前
Enkcy发布了新的文献求助10
3秒前
3秒前
KIORking完成签到,获得积分10
4秒前
77发布了新的文献求助50
5秒前
田様应助细腻冰岚采纳,获得10
5秒前
lida完成签到,获得积分10
5秒前
5秒前
Owen应助AA采纳,获得10
5秒前
zhangJL发布了新的文献求助10
5秒前
Devoted完成签到,获得积分20
6秒前
6秒前
6秒前
FashionBoy应助快乐的雨竹采纳,获得10
7秒前
7秒前
7秒前
叶长亭完成签到,获得积分10
7秒前
perovskite完成签到,获得积分10
7秒前
azure发布了新的文献求助10
7秒前
8秒前
8秒前
丘比特应助依依一一采纳,获得10
8秒前
无花果应助动听从寒采纳,获得10
9秒前
9秒前
36456657应助血小板采纳,获得10
9秒前
抹茶肥肠发布了新的文献求助10
10秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Mechanistic Modeling of Gas-Liquid Two-Phase Flow in Pipes 2500
Kelsen’s Legacy: Legal Normativity, International Law and Democracy 1000
Handbook on Inequality and Social Capital 800
Conference Record, IAS Annual Meeting 1977 610
Interest Rate Modeling. Volume 3: Products and Risk Management 600
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3547058
求助须知:如何正确求助?哪些是违规求助? 3124082
关于积分的说明 9357821
捐赠科研通 2822663
什么是DOI,文献DOI怎么找? 1551622
邀请新用户注册赠送积分活动 723570
科研通“疑难数据库(出版商)”最低求助积分说明 713825