MRI与PET融合的阿尔茨海默病诊断综述
A Review of MRI-PET Fusion for Alzheimer’s Disease Diagnosis
DOI: 10.12677/jisp.2026.154042, PDF,    科研立项经费支持
作者: 秦傲雪, 邵 博, 杨琳倩, 张子琦, 李堎源, 蔡浩然, 卢佳玉：贵州大学大数据与信息工程学院，贵州 贵阳；谭伟杰：贵州大学贵州省大数据实验室，贵州 贵阳
关键词: 阿尔茨海默病；磁共振成像；正电子发射断层成像；多模态融合；深度学习；Alzheimer’s Disease； Magnetic Resonance Imaging； Positron Emission Tomography； Multimodal Fusion； Deep Learning
摘要: 本文梳理磁共振成像(MRI)与正电子发射断层成像(PET)多模态融合在阿尔茨海默病(AD)辅助诊断中的进展。检索PubMed、Web of Science、Google Scholar及中文期刊平台2011~2025年发表的文献，初检420余篇，纳入23篇代表性研究，按数据与预处理、特征表征、融合层级和缺失模态学习归纳。MRI与PET提供结构–代谢互补信息，但示踪剂对应不同生物学过程，不宜未分层合并评价；基于深度学习的特征级融合(双编码器、共享潜空间、交叉注意力)为主流策略；PET缺失时，知识蒸馏与模态掩码可规避生成式补全的伪病理风险；多数高准确率来自单一队列小样本，受试者级划分与独立验证不足。MRI/PET融合有助于AD早期识别、认知正常(CN)与轻度认知障碍(MCI)分类及MCI转化预测，但受制于样本量与外部验证不足，应发展域自适应融合、纵向个体化预测与不确定性感知的模态补全，并按FDG、Aβ与Tau分层报告结果。
Abstract: This review examines the progress of magnetic resonance imaging (MRI) and positron emission tomography (PET) multimodal fusion in the assisted diagnosis of Alzheimer’s disease (AD). The literature published between 2011 and 2025 was searched in PubMed, Web of Science, Google Scholar, and Chinese-language journal platforms; more than 420 records were identified initially, and 23 representative studies were retained after screening. The evidence was organized by data and preprocessing, feature representation, fusion level, and missing-modality learning. MRI and PET provide complementary structural-metabolic information, but their tracers reflect distinct biological processes and should not be pooled without stratification; deep learning-based feature-level fusion through dual encoders, shared latent spaces, and cross-attention is the main-stream strategy; when PET is missing, knowledge distillation and modality masking avoid the pseudo-pathological risk of generative completion; and most high accuracies come from small samples in a single cohort, with subject-level splitting and independent validation remaining insufficient. MRI/PET fusion facilitates early AD identification, the classification of cognitively normal (CN), mild cognitive impairment (MCI), and AD, and MCI conversion prediction, but it is constrained by limited sample sizes and insufficient external validation; domain-adaptive fusion, longitudinal individualized prediction, and uncertainty-aware modality completion should therefore be developed, and results should be reported stratified by FDG, Aβ, and tau tracer.
文章引用：秦傲雪, 邵博, 杨琳倩, 张子琦, 李堎源, 蔡浩然, 卢佳玉, 谭伟杰. MRI与PET融合的阿尔茨海默病诊断综述[J]. 图像与信号处理, 2026, 15(4): 470-478. https://doi.org/10.12677/jisp.2026.154042

参考文献

[1] Jack, C.R., Bennett, D.A., Blennow, K., Carrillo, M.C., Dunn, B., Haeberlein, S.B., et al. (2018) NIA‐AA Research Framework: Toward a Biological Definition of Alzheimer’s Disease. Alzheimer’s & Dementia, 14, 535-562.
https://doi.org/10.1016/j.jalz.2018.02.018
[2] Frisoni, G.B., Fox, N.C., Jack, C.R., Scheltens, P. and Thompson, P.M. (2010) The Clinical Use of Structural MRI in Alzheimer Disease. Nature Reviews Neurology, 6, 67-77.
https://doi.org/10.1038/nrneurol.2009.215
[3] Johnson, K.A., Minoshima, S., Bohnen, N.I., et al. (2013) Appropriate Use Criteria for Amyloid PET: A Report of the Amyloid Imaging Task Force, the Society of Nuclear Medicine and Molecular Imaging, and the Alzheimer’s Association. Alzheimer’s & Dementia, 9, e1-e16.
https://doi.org/10.1016/j.jalz.2013.01.002
[4] Christodoulou, R., Woodward, A., Pitsillos, R., Ibrahim, R. and Georgiou, M. (2025) Artificial Intelligence in Alzheimer’s Disease Diagnosis and Prognosis Using PET-MRI: A Narrative Review of High-Impact Literature Post-Tauvid Approval. Journal of Clinical Medicine, 14, Article 5913.
https://doi.org/10.3390/jcm14165913
[5] Zhang, R., Sheng, J., Zhang, Q., Wang, J. and Wang, B. (2025) A Review of Multimodal Fusion-Based Deep Learning for Alzheimer’s Disease. Neuroscience, 576, 80-95.
https://doi.org/10.1016/j.neuroscience.2025.04.035
[6] Weiner, M.W., Veitch, D.P., Aisen, P.S., Beckett, L.A., Cairns, N.J., Green, R.C., et al. (2013) The Alzheimer’s Disease Neuroimaging Initiative: A Review of Papers Published since Its Inception. Alzheimer’s & Dementia, 9, e111-e194.
https://doi.org/10.1016/j.jalz.2013.05.1769
[7] Marcus, D.S., Wang, T.H., Parker, J., Csernansky, J.G., Morris, J.C. and Buckner, R.L. (2007) Open Access Series of Imaging Studies (OASIS): Cross-Sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults. Journal of Cognitive Neuroscience, 19, 1498-1507.
https://doi.org/10.1162/jocn.2007.19.9.1498
[8] Ellis, K.A., Bush, A.I., Darby, D., De Fazio, D., Foster, J., Hudson, P., et al. (2009) The Australian Imaging, Biomarkers and Lifestyle (AIBL) Study of Aging: Methodology and Baseline Characteristics of 1112 Individuals Recruited for a Longitudinal Study of Alzheimer’s Disease. International Psychogeriatrics, 21, 672-687.
https://doi.org/10.1017/s1041610209009405
[9] Zhang, D., Wang, Y., Zhou, L., Yuan, H. and Shen, D. (2011) Multimodal Classification of Alzheimer’s Disease and Mild Cognitive Impairment. NeuroImage, 55, 856-867.
https://doi.org/10.1016/j.neuroimage.2011.01.008
[10] Wen, J., Thibeau-Sutre, E., Diaz-Melo, M., Samper-González, J., Routier, A., Bottani, S., et al. (2020) Convolutional Neural Networks for Classification of Alzheimer’s Disease: Overview and Reproducible Evaluation. Medical Image Analysis, 63, Article 101694.
https://doi.org/10.1016/j.media.2020.101694
[11] Suk, H.I., Lee, S.W. and Shen, D. (2014) Hierarchical Feature Representation and Multimodal Fusion with Deep Learning for AD/MCI Diagnosis. NeuroImage, 101, 569-582.
https://doi.org/10.1016/j.neuroimage.2014.06.077
[12] Zhou, T., Thung, K.H., Zhu, X. and Shen, D. (2019) Effective Feature Learning and Fusion of Multimodality Data Using Stage‐Wise Deep Neural Network for Dementia Diagnosis. Human Brain Mapping, 40, 1001-1016.
https://doi.org/10.1002/hbm.24428
[13] Tang, Y., Xiong, X., Tong, G., Yang, Y. and Zhang, H. (2024) Multimodal Diagnosis Model of Alzheimer’s Disease Based on Improved Transformer. BioMedical Engineering OnLine, 23, Article No. 8.
https://doi.org/10.1186/s12938-024-01204-4
[14] Abdelaziz, M., Wang, T., Anwaar, W. and Elazab, A. (2025) Multi-Scale Multimodal Deep Learning Framework for Alzheimer’s Disease Diagnosis. Computers in Biology and Medicine, 184, Article 109438.
https://doi.org/10.1016/j.compbiomed.2024.109438
[15] Thung, K., Yap, P. and Shen, D. (2017) Multi-Stage Diagnosis of Alzheimer’s Disease with Incomplete Multimodal Data via Multi-Task Deep Learning. In: Cardoso, M., et al., Eds., Lecture Notes in Computer Science, Springer International Publishing, 160-168.
https://doi.org/10.1007/978-3-319-67558-9_19
[16] Li, R., Zhang, W., Suk, H., Wang, L., Li, J., Shen, D., et al. (2014) Deep Learning Based Imaging Data Completion for Improved Brain Disease Diagnosis. In: Golland, P., Hata, N., Barillot, C., Hornegger, J. and Howe, R., Eds., Lecture Notes in Computer Science, Springer International Publishing, 305-312.
https://doi.org/10.1007/978-3-319-10443-0_39
[17] Pan, Y., Liu, M., Lian, C., Zhou, T., Xia, Y. and Shen, D. (2018) Synthesizing Missing PET from MRI with Cycle-Consistent Generative Adversarial Networks for Alzheimer’s Disease Diagnosis. In: Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C. and Fichtinger, G., Eds., Lecture Notes in Computer Science, Springer International Publishing, 455-463.
https://doi.org/10.1007/978-3-030-00931-1_52
[18] Lin, W., Lin, W., Chen, G., Zhang, H., Gao, Q., Huang, Y., et al. (2021) Bidirectional Mapping of Brain MRI and PET with 3D Reversible GAN for the Diagnosis of Alzheimer’s Disease. Frontiers in Neuroscience, 15, Article ID: 646013.
https://doi.org/10.3389/fnins.2021.646013
[19] Kwak, M.G., Mao, L., Zheng, Z., Su, Y., Lure, F. and Li, J. (2025) A Cross-Modal Mutual Knowledge Distillation Framework for Alzheimer’s Disease Diagnosis: Addressing Incomplete Modalities. IEEE Transactions on Automation Science and Engineering, 22, 14218-14233.
https://doi.org/10.1109/tase.2025.3556290
[20] 张烁, 张荣, 郭颖婕, 余红梅. 基于3D残差网络的阿尔茨海默病辅助诊断模型研究[J]. 中国卫生统计, 2024, 41(6): 883-888, 892.
[21] Subramanyam Rallabandi, V.P. and Seetharaman, K. (2023) Deep Learning-Based Classification of Healthy Aging Controls, Mild Cognitive Impairment and Alzheimer’s Disease Using Fusion of MRI-PET Imaging. Biomedical Signal Processing and Control, 80, Article 104312.
https://doi.org/10.1016/j.bspc.2022.104312
[22] Feng, J., Zhao, X., Liu, Z., Ding, Y. and Wang, F. (2025) A Multi-View Multimodal Deep Learning Framework for Alzheimer’s Disease Diagnosis. Frontiers in Neuroscience, 19, Article ID: 1658776.
https://doi.org/10.3389/fnins.2025.1658776
[23] Pellegrini, E., Ballerini, L., Hernandez, M.d.C.V., Chappell, F.M., González‐Castro, V., Anblagan, D., et al. (2018) Machine Learning of Neuroimaging for Assisted Diagnosis of Cognitive Impairment and Dementia: A Systematic Review. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring, 10, 519-535.
https://doi.org/10.1016/j.dadm.2018.07.004