|Table of Contents|

[1] Li Xuan, Lu Xuesong, Wang Haixian, Alzheimer’s disease classification based on sparse functionalconnectivity and non-negative matrix factorization [J]. Journal of Southeast University (English Edition), 2019, 35 (2): 147-152. [doi:10.3969/j.issn.1003-7985.2019.02.001]
Copy

Alzheimer’s disease classification based on sparse functionalconnectivity and non-negative matrix factorization()
基于稀疏功能连接及非负矩阵分解的阿尔兹海默症分类方法
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
35
Issue:
2019 2
Page:
147-152
Research Field:
Biological Science and Medical Engineering
Publishing date:
2019-06-30

Info

Title:
Alzheimer’s disease classification based on sparse functionalconnectivity and non-negative matrix factorization
基于稀疏功能连接及非负矩阵分解的阿尔兹海默症分类方法
Author(s):
Li Xuan1, Lu Xuesong2, Wang Haixian1, 3
1Key Laboratory of Child Development and Learning Science of Ministry of Education, Research Center for Learning Science, Southeast University, Nanjing 210096, China
2Department of Rehabilitation, Zhongda Hospital, Southeast University, Nanjing 210009, China
3School of Mathematics and Big Data, Foshan University, Foshan 528000, China
李璇1, 陆雪松2, 王海贤1, 3
1东南大学学习科学研究中心儿童发展与学习科学教育部重点实验室, 南京 210096; 2东南大学附属中大医院康复医学科, 南京 210009; 3佛山科学技术学院数学与大数据学院, 佛山 528000
Keywords:
Alzheimer’s disease;  sparse representation;  non-negative matrix factorization;  functional connectivity
阿尔兹海默症;  稀疏表示;  非负矩阵分解;  功能连接
PACS:
R318
DOI:
10.3969/j.issn.1003-7985.2019.02.001
Abstract:
A novel framework is proposed to obtain physiologically meaningful features for Alzheimer’s disease(AD)classification based on sparse functional connectivity and non-negative matrix factorization. Specifically, the non-negative adaptive sparse representation(NASR)method is applied to compute the sparse functional connectivity among brain regions based on functional magnetic resonance imaging(fMRI)data for feature extraction. Afterwards, the sparse non-negative matrix factorization(sNMF)method is adopted for dimensionality reduction to obtain low-dimensional features with straightforward physical meaning. The experimental results show that the proposed framework outperforms the competing frameworks in terms of classification accuracy, sensitivity and specificity. Furthermore, three sub-networks, including the default mode network, the basal ganglia-thalamus-limbic network and the temporal-insular network, are found to have notable differences between the AD patients and the healthy subjects. The proposed framework can effectively identify AD patients and has potentials for extending the understanding of the pathological changes of AD.
为了获得更具神经生理学意义的分类特征, 提出了基于稀疏功能连接及非负矩阵分解的阿尔兹海默症分类方法.该方法基于功能核磁共振信号, 采用非负自适应稀疏表示法计算脑区间的稀疏功能连接, 以提取分类特征.然后, 采用稀疏非负矩阵分解法进行特征降维, 以获得具有明确物理意义的低维特征.实验结果表明该方法的分类准确率、灵敏度和特异度均优于其他对比方法.此外, 发现了默认模式网络、基底神经节-丘脑-边缘结构网络及颞叶-脑岛网络在阿尔兹海默症病人和健康被试间具有明显差异.此方法能够有效地对阿尔兹海默症进行识别, 同时具有加深对该病症功能病变理解的潜力.

References:

[1] Biswal B, Zerrin Yetkin F, Haughton V M, et al. Functional connectivity in the motor cortex of resting human brain using echoplanar MRI [J]. Magnetic Resonance in Medicine, 1995, 34(4): 537-541. DOI:10.1002/mrm.1910340409.
[2] Balthazar M L F, Pereira F R S, Lopes T M, et al. Neuropsychiatric symptoms in Alzheimer’s disease are related to functional connectivity alterations in the salience network[J]. Human Brain Mapping, 2014, 35(4): 1237-1246. DOI:10.1002/hbm.22248.
[3] Teipel S, Drzezga A, Grothe M J, et al. Multimodal imaging in Alzheimer’s disease: Validity and usefulness for early detection [J]. The Lancet Neurology, 2015, 14(10): 1037-1053. DOI:10.1016/s1474-4422(15)00093-9.
[4] Lee D D, Seung H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755): 788-791. DOI:10.1038/44565.
[5] Padilla P, López M, Górriz J M, et al. NMF-SVM based CAD tool applied to functional brain images for the diagnosis of Alzheimer’s disease [J]. IEEE Transactions on Medical Imaging, 2012, 31(2): 207-216. DOI:10.1109/tmi.2011.2167628.
[6] Li X, Hu Z L, Wang H X. Overlapping community structure detection of brain functional network using non-negative matrix factorization [C]//International Conference on Neural Information Processing. Kyoto, Japan, 2016: 140-147.DOI:10.1007/978-3-319-46675-0_16.
[7] Li X, Wang H X. Identification of functional networks in resting state fMRI data using adaptive sparse representation and affinity propagation clustering [J]. Frontiers in Neuroscience, 2015, 9: 383-1-383-16.DOI:10.3389/fnins.2015.00383.
[8] Hoyer P O. Non-negative sparse coding [C]//Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing. Martigny, Switzerland, 2002: 557-565.
[9] Grave E, Obozinski G R, Bach F R. Trace lasso: A trace norm regularization for correlated designs [C]//Advances in Neural Information Processing Systems. Granada, Spain, 2011: 2187-2195.
[10] Yan C G, Zang Y F. DPARSF: A MATLAB toolbox for “pipeline” data analysis of resting-state fMRI [J]. Frontiers in Systems Neuroscience, 2010, 4:13-1-13-7. DOI:10.3389/fnsys.2010.00013.
[11] Tzourio-Mazoyer N, Landeau B, Papathanassiou D, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain [J]. Neuroimage, 2002, 15(1): 273-289. DOI:10.1006/nimg.2001.0978.
[12] Klaassens B L, van Gerven J M A, van der Grond J, et al. Diminished posterior precuneus connectivity with the default mode network differentiates normal aging from Alzheimer’s disease [J]. Frontiers in Aging Neuroscience, 2017, 9: 97. DOI:10.3389/fnagi.2017.00097.
[13] Aggleton J P, Pralus A, Nelson A J D, et al. Thalamic pathology and memory loss in early Alzheimer’s disease: Moving the focus from the medial temporal lobe to Papez circuit [J]. Brain, 2016, 139(7): 1877-1890. DOI:10.1093/brain/aww083.
[14] Harrison T M, Burggren A C, Small G W, et al. Altered memory-related functional connectivity of the anterior and posterior hippocampus in older adults at increased genetic risk for Alzheimer’s disease[J]. Human Brain Mapping, 2016, 37(1): 366-380. DOI:10.1002/hbm.23036.
[15] Rathore S, Habes M, Iftikhar M A, et al. A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer’s disease and its prodromal stages [J]. Neuroimage, 2017, 155: 530-548. DOI:10.1016/j.neuroimage.2017.03.057.
[16] Bi X A, Jiang Q, Sun Q, et al. Analysis of alzheimer’s disease based on the random neural network cluster in fMRI[J]. Frontiers in Neuroinformatics, 2018, 12: 60. DOI:10.3389/fninf.2018.00060.
[17] Lian C F, Liu M X, Zhang J, et al. Hierarchical fully convolutional network for joint atrophy localization and alzheimer’s disease diagnosis using structural MRI[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 99:1-14. DOI:10.1109/tpami.2018.2889096.

Memo

Memo:
Biographies: Li Xuan(1990—), female, Ph.D. candidate; Wang Haixian(corresponding author), male, doctor, professor, hxwang@seu.edu.cn.
Foundation items: The Foundation of Hygiene and Health of Jiangsu Province(No.H2018042), the National Natural Science Foundation of China(No.61773114), the Key Research and Development Plan(Industry Foresight and Common Key Technology)of Jiangsu Province(No.BE2017007-3).
Citation: Li Xuan, Lu Xuesong, Wang Haixian. Alzheimer’s disease classification based on sparse functional connectivity and non-negative matrix factorization[J].Journal of Southeast University(English Edition), 2019, 35(2):147-152.DOI:10.3969/j.issn.1003-7985.2019.02.001.
Last Update: 2019-06-20