MCNet：融合多层感知机和卷积的轻量级病变区域分割网络
- 分享到:
摘要：
针对现有医学图像分割网络存在计算量大、对硬件资源要求高和推理速度慢等不足，提出一种轻量级快速分割网络MCNet。MCNet采用编码器-解码器架构，使用多层感知机（MLP）和卷积分别提取并融合医学图像的全局特征和局部特征，以减少网络参数量并提高分割精度。在编码阶段使用卷积分支和多层感知机分支分别提取多尺度的局部特征和全局特征。通过跳跃连接融合这些特征并送入解码器。在解码阶段使用注意力门控机制进行特征增强。在BUSI和ISIC2018数据集上进行实验。和当前最优方法相比，MCNet的Dice相似系数和均交并比在BUSI数据集上分别提高0.11%和0.09%、在ISIC2018数据集上分别提高0.64%和 0.95%。同时，MCNet显著减少了网络参数量、降低了浮点运算次数并缩短了CPU推理时间。
To address the shortcomings of existing medical image segmentation networks, such as high computational demands, significant hardware resource requirements, and slow inference speeds, a lightweight and fast segmentation network named MCNet is proposed. MCNet adopts an encoder-decoder architecture, utilizing both multilayer perceptron(MlP) and convolutions to extract and fuse global and local features of medical images, respectively, thereby reducing network parameters and improving segmentation accuracy, During the encoding stage, convolutional branches and MLP branches are used to extract multi-scale local and global features, These features are fused via skip connections and passed to the decoder. In the decoding stage, an attention gating mechanism is employed to enhance feature representation, Experiments were conducted on the BUSI and ISIC2018 datasets. Compared with state-of-the-art methods, MCNet achieves improvements in Dice similarity coefficient and mean Intersection over Union of 0.11% and 0.09% on the BUSI dataset, and 0.64% and 0.95% on the ISiC2018 dataset.respectively. Additionally, MCNet significantly reduces the number of network parameters, decreases the number of floatingpoint operations, and shortens CPU inference time.
作者：
申华磊，上官国庆，袁成雨， 陈艳浩，刘栋
Shen Hualei，Shangguan Guoqing，Yuan Chengyu，Chen Yanhao，Liu Dong
机构地区：
计算机与信息工程学院；河南省教育人工智能与个性化学习重点实验室；教学资源与教育质量评估大数据河南省工程实验室
引用本文：
李国平，韩婷。具有分数Brown运动的分数阶中立型随机微分方程解的存在唯一性[J].学报(自然科学版) ,2025,53(3) :104-111. (Li Guoping, Han Ting. Existence and uniqueness of solutions to fractional neutral stochastic differential equations with fractional brownian motion [J] .Journal of Henan Normal University(Natural Science Edition) ,2025,53(3) :104-111. DOI:10. 16366/j. cnki.1000-2367. 2023. 09. 20. 0001.)
基金：
宁夏高等学校科学研究项目；国家自然科学基金
关键词：
医学图像分割；深度神经网络；多层感知机（MLP）；轻量级网络
medical image segmentation; deep neural net work; multi-layer perceptron(MLP); lightweight network
分类号：
TP391. 41
