基于注意力增强的卷积框架在阿尔茨海默症分类中的应用

doi:10.3969/j.issn.0255-8297.2026.05.009

摘要/Abstract

摘要： 阿尔茨海默症（Alzheimer’s disease,AD）的辅助诊断作为脑科学领域的重要研究课题，一直受到广泛关注。本文提出了一种新颖的深度学习模型AttentionConvFusion（ACF），通过引入自注意力机制对卷积核的权重进行动态优化，使其能够更加有效地捕捉神经影像中的关键特征。实验结果表明，ACF模型在不同的阿尔茨海默症分类任务中展现了令人满意的性能。在对阿尔茨海默症与正常认知的分类任务中，ACF模型达到了81.5%的准确率；在阿尔茨海默症与轻度认知障碍的分类任务中，该模型达到了80.1%的准确率；在多分类任务中，该模型达到了77.8%的准确率。结果表明，本文提出的ACF在阿尔茨海默症的诊断与分类中具有显著优势。

关键词: 深度学习, 阿尔茨海默症, 卷积神经网络, Transformer, 图像分类, 计算机辅助诊断

Abstract: The auxiliary diagnosis of Alzheimer’ s disease (AD) has long been an important research topic in brain science. This paper proposed a novel deep learning model termed AttentionConvFusion (ACF). By introducing a self-attention mechanism that dynamically optimizes convolutional kernel weights, the model can more effectively capture critical features in neuroimaging data. Experimental results show that the proposed ACF model achieves satisfactory performance across different AD classification tasks. Specifically, in the classification of AD versus normal cognition, the ACF model achieves an accuracy of 81.5%. For AD versus mild cognitive impairment, it achieves an accuracy of 80.1%. In the multi-class classification task, it achieves an accuracy of 77.8%. These results indicate that the proposed ACF model has significant advantages in the diagnosis and classification of AD.

Key words: deep learning, Alzheimer’s disease, convolutional neural network, Transformer, image classification, computer-aided diagnosis

中图分类号:

TP391.41

张括, 胡众义. 基于注意力增强的卷积框架在阿尔茨海默症分类中的应用[J]. 应用科学学报, 2026, 44(5): 827-837.

ZHANG Kuo, HU Zhongyi. Application of an Attention-Enhanced Convolutional Framework in Alzheimer’s Disease Classification[J]. Journal of Applied Sciences, 2026, 44(5): 827-837.

[1] Zheng Q Y, Wang X. Alzheimer’s disease: insights into pathology, molecular mechanisms, and therapy [J]. Protein & Cell, 2025, 16(2): 83-120.
[2] Li Z, Yang N, He L, et al. Global burden of dementia death from 1990 to 2019, with projections to 2050: an analysis of 2019 global burden of disease study [J]. The Journal of Prevention of Alzheimer’s Disease, 2024, 11(4): 1013-1021.
[3] Tzeng H M, Raji M A, Shan Y, et al. Annual wellness visits and early dementia diagnosis among medicare beneficiaries [J]. JAMA Network Open, 2024, 7(10): e2437247.
[4] Bilello M, Doshi J, Nabavizadeh S A, et al. Correlating cognitive decline with white matter Lesion and brain atrophy magnetic resonance imaging measurements in Alzheimer’s disease [J]. Journal of Alzheimer’s Disease, 2015, 48(4): 987-994.
[5] Lazli L, Boukadoum M, Mohamed O A. A survey on computer-aided diagnosis of brain disorders through MRI based on machine learning and data mining methodologies with an emphasis on Alzheimer disease diagnosis and the contribution of the multimodal fusion [J]. Applied Sciences, 2020, 10(5): 1894.
[6] Kohler M, Langer S. Statistical theory for image classification using deep convolutional neural network with cross-entropy loss under the hierarchical max-pooling model [J]. Journal of Statistical Planning and Inference, 2025, 234: 106188.
[7] Brahmi W, Jdey I, Drira F. Exploring the role of convolutional neural networks (CNN) in dental radiography segmentation: a comprehensive systematic literature review [J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108510.
[8] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [PP/OL]. V1. (2017-06-12) [2025-02-20]. https://arxiv.org/abs/1706.03762.
[9] Gillioz A, Casas J, Mugellini E, et al. Overview of the transformer-based models for NLP tasks [J]. Federated Conference on Computer Science and Information Systems, 2020, 21: 179-183.
[10] Park K, Soh J W, Cho N I. A dynamic residual self-attention network for lightweight single image super-resolution [J]. IEEE Transactions on Multimedia, 2023, 25: 907-918.
[11] Pan S W, Yang B, Wang S K, et al. Oil well production prediction based on CNN-LSTM model with self-attention mechanism [J]. Energy, 2023, 284: 128701.
[12] Liang Z, Tao M L, Xie J, et al. A radio signal recognition approach based on complex-valued CNN and self-attention mechanism [J]. IEEE Transactions on Cognitive Communications and Networking, 2022, 8(3): 1358-1373.
[13] Leung K K, Barnes J, Modat M, et al. Brain MAPS: an automated, accurate and robust brain extraction technique using a template library [J]. NeuroImage, 2011, 55(3): 1091-1108.
[14] Cortes C, Vapnik V. Support-vector networks [J]. Machine Learning, 1995, 20(3): 273-297.
[15] Breiman L. Random forests [J]. Machine Learning, 2001, 45(1): 5-32.
[16] Cover T, Hart P. Nearest neighbor pattern classification [J]. IEEE Transactions on Information Theory, 1967, 13(1): 21-27.
[17] Bhatt D, Patel C, Talsania H, et al. CNN variants for computer vision: history, architecture, application, challenges and future scope [J]. Electronics, 2021, 10(20): 2470.
[18] Loos V, Pardasani R, Awasthi N. Demystifying the effect of receptive field size in U-Net models for medical image segmentation [J]. Journal of Medical Imaging, 2024, 11(5): 054004.
[19] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278–2324.
[20] Chen C X, Golovko V, Kroshchanka A, et al. An analytical approach for unsupervised learning rate estimation using rectified linear units [J]. Frontiers in Neuroscience, 2024, 18: 1362510.
[21] Xu J, Li Z S, Du B W, et al. Reluplex made more practical: leaky ReLU [C]//IEEE Symposium on Computers and Communications (ISCC), 2020: 1-7.
[22] Han K, Xiao A, Wu E, et al. Transformer in transformer [C]//Advances in Neural Information Processing Systems (NeurIPS 2021), 2021: 15908–15919.
[23] Yu Y, Si X S, Hu C H, et al. A review of recurrent neural networks: LSTM cells and network architectures [J]. Neural Computation, 2019, 31(7): 1235-1270.
[24] Yan C G, Wang X D, Zuo X N, et al. DPABI: data processing & analysis for (resting-state) brain imaging [J]. Neuroinformatics, 2016, 14(3): 339-351.
[25] Flandin G, Friston K. Statistical parametric mapping (SPM) [J]. Scholarpedia, 2008, 3(4): 6232.
[26] Jo T, Kim J, Bice P, et al. Novel circling SWAT for deep learning based diagnostic classification of Alzheimer’s disease: application to metabolome data [J]. Alzheimer’s & Dementia, 2022, 18(S6): e069310.
[27] Rohanian M, Hough J, Purver M. Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer’s dementia recognition from spontaneous speech [C]//Interspeech 2020, 2020: 2187-2191.

基于注意力增强的卷积框架在阿尔茨海默症分类中的应用

Application of an Attention-Enhanced Convolutional Framework in Alzheimer’s Disease Classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王宇帆, 邵子龙, 蒲媛雪, 章昊文, 张静怡, 秦昆. 遥感影像小目标检测方法与应用[J]. 应用科学学报, 2026, 44(4): 598-614.
[2]	邹国镜, 丛铭, 崔建军, 韩玲. 视觉感知的投影式三维语义分割后处理方法[J]. 应用科学学报, 2026, 44(4): 626-643.
[3]	叶帅, 商娅娜, 陈娜, 刘书朋, 刘勇. 利用压缩感知减缓AFM光纤探针磨损[J]. 应用科学学报, 2026, 44(3): 345-357.
[4]	廖清, 陈泓佑, 刘重阳, 屈凌峰, 段纪平, 夏萍, 田宝单, 范勇. 基于AttResVGG模型的燃烧室点火预测算法[J]. 应用科学学报, 2026, 44(3): 390-408.
[5]	张蕾, 李萄苑, 李明飞, 邓海敏, 谢诚. 基于“面-廓-色”多通道特征融合的多肉叶片繁育评分算法[J]. 应用科学学报, 2026, 44(2): 316-329.
[6]	陈昱胤, 李贯峰, 秦晶, 肖毓航. 基于改进Transformer的复杂逻辑查询模型[J]. 应用科学学报, 2026, 44(1): 34-49.
[7]	吴文强, 陈爱斌, 李潇瑶. 基于特征融合注意力和对比学习的森林图像去雾[J]. 应用科学学报, 2026, 44(1): 97-109.
[8]	江泽涛, 杨建琛, 李孟桐, 程留明, 张路豪. 一种基于边缘特征引导的低照度图像细节增强方法[J]. 应用科学学报, 2025, 43(6): 948-961.
[9]	朱诗逸, 陆小锋. 基于骨骼的脑卒中患者手势识别与康复评估[J]. 应用科学学报, 2025, 43(5): 817-827.
[10]	熊俊, 刘守全, 安旭, 郭甜, 邰宝宇. 一种基于轮廓度量的卷积神经网络遥感图像建筑物分割方法[J]. 应用科学学报, 2025, 43(4): 709-720.
[11]	鲁桢, 吴建斌. 基于字符识别的无载体隐写[J]. 应用科学学报, 2025, 43(4): 684-693.
[12]	邵子龙, 漆林, 陈昆, 许玉斌, 秦昆, 余长慧. 密集多实例建筑物场景变化检测[J]. 应用科学学报, 2025, 43(4): 656-671.
[13]	杨婉, 陈爱斌, 赵莹, 武阅, 甑鑫, 肖治术. 基于双层路由注意力和自校准卷积的豹个体识别[J]. 应用科学学报, 2025, 43(2): 348-360.
[14]	汪婉灵, 熊邦书, 欧巧凤, 余磊, 饶智博. 基于暗区域引导的低照度图像增强[J]. 应用科学学报, 2025, 43(2): 245-256.
[15]	吴祥, 肖剑, 吉根林. 基于多尺度特征融合和注意力机制的视频异常检测方法[J]. 应用科学学报, 2025, 43(2): 234-244.