基于概率分类器加权的多模态AD分类模型研究
Research on Multimodal AD Classification Model Based on Weighted Probability Classifier
摘要: 阿尔茨海默症(Alzheimer’s Disease, AD)是一种最常见的神经退行性疾病，其症状具体表现为记忆和思维能力的退化，同时AD是受遗传因素影响很大的疾病，目前对AD仍无有效的治疗手段，许多研究基于单一模态数据进行早期诊断的研究效果不理想。为此，研究基于磁共振影像(MRI)和单核苷酸多态性(Single Nucleotide Polymorphim, SNP)两种模态数据提出一种概率分类器加权的多模态集成学习新框架，为分类器提供更丰富、全面的信息，从而提高AD诊断分类的准确率和稳定性。研究方法在AD vs NC、MCIc vs NC和MCInc vs MCIc的5次5折交叉验证实验结果平均准确率分别高达80%、76%、70%，结果表明研究提出的多模态集成学习模型与利用单一模态数据的分类模型相比更具有优势。
Abstract: Alzheimer’s Disease (AD) is one of the most common neurodegenerative diseases. Its symptoms are specifically manifested as the deterioration of memory and thinking ability. At the same time, AD is a disease that is greatly affected by genetic factors. Without effective treatment, many studies based on single modal data for early diagnosis have unsatisfactory results. Therefore, based on the two modal data of Magnetic Resonance Imaging (MRI) and Single Nucleotide Polymorphim (SNP), the study proposed a new framework for multimodal ensemble learning weighted by probabilistic classifiers. The device provides richer and more comprehensive information, thereby improving the accuracy and stability of AD diagnostic classification. This research method is used in the 5-fold crossover of AD vs NC, MCIc vs NC and MCInc vs MCIc. The average verification accuracy rates are as high as 80%, 76%, and 70%. The results show that the multi-modal integrated learning model proposed by the research, compared with the classification model of single modal data has more advantages.
文章引用：陈国斌, 曾安. 基于概率分类器加权的多模态AD分类模型研究[J]. 计算机科学与应用, 2021, 11(3): 760-769. https://doi.org/10.12677/CSA.2021.113078

参考文献

[1] Alzheimer’s Association (2018) 2018 Alzheimer’s Disease Facts and Figures. Alzheimer’s Dementia, 14, 367-429. [Google Scholar] [CrossRef] 
[2] Jagust, W. (2013) Vulnerable Neural Systems and the Borderland of Brain Aging and Neurodegeneration. Neuron, 77, 219-234. [Google Scholar] [CrossRef] [PubMed]
[3] Buckner, R.L. (2004) Memory and Executive Function in Aging and AD: Multiple Factors That Cause Decline and Reserve Factors That Compensate. Neuron, 44, 195-208. [Google Scholar] [CrossRef] [PubMed]
[4] Braak, H. and Braak, E. (1991) Neuropathological Staging of Alzheimer-Related Changes. Acta Neuropathologica, 82, 239-259. [Google Scholar] [CrossRef] 
[5] Gray, K.R., Wolz, R., Heckemann, R.A., Aljabar, P., Hammers, A. and Rueckert, D. (2012) Multi-Region Analysis of Longi-tudinal FDG-PET for the Classification of Alzheimer’s Disease. Neuroimage, 60, 221-229. [Google Scholar] [CrossRef] [PubMed]
[6] Pagani, M., De Carli, F., Morbelli, S., Oberg, J., Chincarini, A., Frisoni, G.B., Galluzzi, S., Perneczky, R., Drzezga, A., van Berckel, B.N., et al. (2015) Volume of Interest-Based [18F] Fluorodeoxyglucose PET Discriminates MCI Converting to Alzheimer’s Disease from Healthy Controls. A Euro-pean Alzheimer’s Disease Consortium (EADC) Study. NeuroImage: Clinical, 7, 34-42. [Google Scholar] [CrossRef] [PubMed]
[7] Chen, G., Ward, B.D., Xie, C., Li, W., Wu, Z., Jones, J.L., Franczak, M., Antuono, P. and Li, S.J. (2011) Classification of Alzheimer Disease, Mild Cognitive Impairment, and Normal Cognitive Status with Large-Scale Network Analysis Based on Resting-State Functional MR Imaging. Radiology, 259, 213-221. [Google Scholar] [CrossRef] [PubMed]
[8] Gaiteri, C., Mostafavi, S., Honey, C.J., De Jager, P.L. and Bennett, D.A. (2016) Genetic Variants in Alzheimer Disease-Molecular and Brain Network Approaches. Nature Re-views Neurology, 12, 1-15. [Google Scholar] [CrossRef] [PubMed]
[9] Shen, L., Kim, S., Risacher, S.L., Nho, K., Swaminathan, S., West, J.D., Foroud, T., Pankratz, N., Moore, J.H., Sloan, C.D., Huentelman, M.J., Craig, D.W., DeChairo, B.M., Potkin, S.G., Jack Jr., C.R., Weiner, M.W. and Saykin, A.J. (2010) Whole Genome Association Study of Brain-Wide Imaging Phe-notypes for Identifying Quantitative Trait Loci in MCI and AD: A Study of the ADNI Cohort. NeuroImage, 53, 1051-1063. [Google Scholar] [CrossRef] [PubMed]
[10] Hao, X., Yu, J. and Zhang, D. (2014) Identifying Genetic Associations with MRI-Derived Measures via Tree-Guided Sparse Learning. In: Golland, P., Hata, N., Barillot, C., Hornegger, J. and Howe, R., Eds., MICCAI 2014, LNCS, Vol. 8674, Springer, Heidelberg, 757-764. [Google Scholar] [CrossRef] [PubMed]
[11] Tripoliti, E.E., Fotiadis, D.I. and Argyropoulou, M. (2011) A Supervised Method to Assist the Diagnosis and Monitor Progression of Alzheimer’s Disease Using Data from an fMRI Experiment. Artificial Intelligence in Medicine, 53, 35-45. [Google Scholar] [CrossRef] [PubMed]
[12] Van Leemput, K., Maes, F., Vandermeulen, D., et al. (1999) Automated Model-Based Tissue Classification of MR Images of the Brain. IEEE Transactions on Medical Imaging, 18, 897-908. [Google Scholar] [CrossRef] [PubMed]
[13] Hinrichs, C., Singh, V., Mukherjee, L., et al. (2009) Spatially Augmented LP Boosting for AD Classification with Evaluations on the ADNI Dataset. Neuroimage, 48, 138-149. [Google Scholar] [CrossRef] [PubMed]
[14] Lin, D., Cao, H., Calhoun, V.D. and Wang, Y.P. (2014) Sparse Models for Correlative and Integrative Analysis of Imaging and Ge-netic Data. Journal of Neuroscience Methods, 237, 69-78. [Google Scholar] [CrossRef] [PubMed]
[15] Zhang, Z., Huang, H. and Shen, D. (2014) Integrative Analy-sis of Multi-Dimensional Imaging Genomics Data for Alzheimer’s Disease Prediction. Frontiers in Aging Neuroscience, 6, 260. [Google Scholar] [CrossRef] [PubMed]
[16] He, K. and Sun, J. (2015) Convolutional Neural Networks at Constrained Time Cost. CVPR 2015, Boston, 7-12 June 2015, 5. [Google Scholar] [CrossRef] 
[17] Korolev, S., Safiullin, A., Belyaev, M., et al. (2017) Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification. IEEE International Symposium on Biomed-ical Imaging, Melbourne, 18-21 April 2017, 835-838. [Google Scholar] [CrossRef] 
[18] He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 1-2. [Google Scholar] [CrossRef] 
[19] Tadas, B., Chaitanya, A. and Louis-Philippe, M. (2019) Multimodal Machine Learning: A Survey and Taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 423-443. [Google Scholar] [CrossRef] 
[20] Chang, C.C., Chow, C.C., Tellier, L.C., et al. (2015) Sec-ond-Generation PLINK: Rising to the Challenge of Larger and Richer Datasets. Gigascience, 4, 7. [Google Scholar] [CrossRef] [PubMed]
[21] Large, J., Lines, J. and Bagnall, A. (2019) A Probabilistic Classi-fier Ensemble Weighting Scheme Based on Cross-Validated Accuracy Estimates. Data Mining and Knowledge Discovery, 33, 1674-1709. [Google Scholar] [CrossRef] [PubMed]
[22] Salvatore, C., Cerasa, A., Battista, P., et al. (2015) Magnetic Resonance Imaging Biomarkers for the Early Diagnosis of Alzheimer’s Disease: A Machine Learning Approach. Fron-tiers in Neuroscience, 9, 307. [Google Scholar] [CrossRef] [PubMed]
[23] Wang, S.H., Phillips, P., Sui, Y., et al. (2018) Classification of Alz-heimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pool-ing. Journal of Medical Systems, 42, 85. [Google Scholar] [CrossRef] [PubMed]