计算机应用研究2024，Vol.41Issue(6)：1876-1881,6.DOI:10.19734/j.issn.1001-3695.2023.09.0405
3D UNeXt:轻量级快速脑提取网络
3D UNeXt:lightweight and efficient network for effective brain extraction
摘要
Abstract
In order to solve the drawbacks of existing brain extraction network,i.e.,complex network structure,large amounts of parameters and low inference speed,this paper proposed a novel network 3D UNeXt for fast and effective brain ex-traction.3D UNeXt greatly reduced parameters and the number of floating point operators(FLOPs),and achieved promising results with the combination of 3D convolution,3D MLP and multi-scale feature fusion.3D UNeXt used U-Net as the basic ar-chitecture and employed 3D convolutional modules to obtain local features in encoding stage.Specifically,the proposed 3D MLP module at the bottleneck stage enhanced the extraction of global features and long-range dependencies among them.In decoding stage,this paper designed a lightweight multiscale feature fusion module to effectively fuse multiscale low-level fea-tures and high-level counterparts.In detail,the 3D MLP module performed linear shift operations in three different axes to ob-tain global receptive fields from different dimension features and establish long-range dependencies among them.This paper compared 3D UNeXt with other counterparts on three datasets:IBSR,NFBS,and HTU-BrainMask.Experimental results show that the 3D UNeXt is superior over other baselines in terms of network parameters,FLOPs,inference accuracy,and inference speed.关键词
脑提取/深度神经网络/U-Net/多尺度特征融合/3D MLPKey words
brain extraction/deep neural network/U-Net/multi-scale feature fusion/3D MLP分类
信息技术与安全科学引用本文复制引用
申华磊,王琦,上官国庆,刘栋..3D UNeXt:轻量级快速脑提取网络[J].计算机应用研究,2024,41(6):1876-1881,6.基金项目
国家自然科学基金项目(62072160) （62072160）
河南省科技攻关项目(232102211024) （232102211024）
