广东工业大学学报2026，Vol.43Issue(1)：31-39,95,10.DOI:10.12052/gdutxb.250037
基于多尺度通道空间感知Mamba的阿尔茨海默症PET影像分类方法
Multi-scale Channel-spatial Perception Mamba for Alzheimer's Disease PET Image Classification Method
摘要
Abstract
To address the limitations of existing medical image diagnosis methods based on convolutional neural networks and Transformers,such as insufficient long-range dependency modeling and quadratic computational complexity,this paper proposes a 3D positron emission tomography(PET)image classification framework named state space hybrid convolutional model(SSHCM).The framework is built upon a multi-scale channel space perception Mamba architecture,which integrates a linear state-space model with a multi-scale feature interaction mechanism,using stacked LMamba blocks to capture long-range dependencies in 3D voxel sequences dynamically.A layer-wise cross-scale channel attention fusion module is designed to achieve adaptive fusion of global contextual semantic.Additionally,a channel-spatial perception module is constructed by combining large kernel convolutions with an inverted bottleneck structure,enhancing spatial feature fusion and improving lesion localization accuracy.Experimental results on the Alzheimer's Disease Neuroimaging Initiative dataset with 1 187 subjects show that the proposed model significantly outperforms ResNet,ViT,and Mamba variant models in terms of both accuracy and AUC.Specifically,the model achieves accuracy rates of 97.03%for AD classification and 83.33%for MCI conversion prediction tasks.关键词
阿尔茨海默病/正电子发射断层扫描/Mamba/状态空间模型/图像分类Key words
Alzheimer's disease/positron emission tomography/Mamba/state space models/image classification分类
信息技术与安全科学引用本文复制引用
黎舰泽,刘立程,吴慧东..基于多尺度通道空间感知Mamba的阿尔茨海默症PET影像分类方法[J].广东工业大学学报,2026,43(1):31-39,95,10.基金项目
国家自然科学基金资助项目(61976058,61300107) （61976058,61300107）
广东省自然科学基金资助项目(S2012010010212) （S2012010010212）
广州市科技计划项目(202206010007) （202206010007）
