Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2014 Jul;12(3):381-94.
doi: 10.1007/s12021-013-9218-x.

Identifying informative imaging biomarkers via tree structured sparse learning for AD diagnosis

Affiliations

Identifying informative imaging biomarkers via tree structured sparse learning for AD diagnosis

Manhua Liu et al. Neuroinformatics. 2014 Jul.

Abstract

Neuroimaging provides a powerful tool to characterize neurodegenerative progression and therapeutic efficacy in Alzheimer's disease (AD) and its prodromal stage-mild cognitive impairment (MCI). However, since the disease pathology might cause different patterns of structural degeneration, which is not pre-known, it is still a challenging problem to identify the relevant imaging markers for facilitating disease interpretation and classification. Recently, sparse learning methods have been investigated in neuroimaging studies for selecting the relevant imaging biomarkers and have achieved very promising results on disease classification. However, in the standard sparse learning method, the spatial structure is often ignored, although it is important for identifying the informative biomarkers. In this paper, a sparse learning method with tree-structured regularization is proposed to capture patterns of pathological degeneration from fine to coarse scale, for helping identify the informative imaging biomarkers to guide the disease classification and interpretation. Specifically, we first develop a new tree construction method based on the hierarchical agglomerative clustering of voxel-wise imaging features in the whole brain, by taking into account their spatial adjacency, feature similarity and discriminability. In this way, the complexity of all possible multi-scale spatial configurations of imaging features can be reduced to a single tree of nested regions. Second, we impose the tree-structured regularization on the sparse learning to capture the imaging structures, and then use them for selecting the most relevant biomarkers. Finally, we train a support vector machine (SVM) classifier with the selected features to make the classification. We have evaluated our proposed method by using the baseline MR images of 830 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, which includes 198 AD patients, 167 progressive MCI (pMCI), 236 stable MCI (sMCI), and 229 normal controls (NC). Our experimental results show that our method can achieve accuracies of 90.2 %, 87.2 %, and 70.7 % for classifications of AD vs. NC, pMCI vs. NC, and pMCI vs. sMCI, respectively, demonstrating promising performance compared with other state-of-the-art methods.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
The flowchart of the proposed method
Fig. 2
Fig. 2
The proposed tree construction method by hierarchical agglomerative clustering
Fig. 3
Fig. 3
A sample tree (constructed with 6 adjacent image voxels) for illustration of 6 leaves: {V1, V2, V3, V4, V5, V6} and 5 nodes: {G1, G2, G3, G4, G5}
Fig. 4
Fig. 4
Comparison of classification accuracy with respect to different number of selected features by three feature-selection methods, t-test, Lasso, and the proposed tree-guided method, in classification of a AD vs. NC, b pMCI vs. NC, and c sMCI vs. pMCI
Fig. 5
Fig. 5
The biomarkers identified from the GM density map by a L1-norm Lasso and b our proposed tree-structured sparse learning method for AD vs. NC classification
Fig. 6
Fig. 6
The biomarkers identified from the GM density map by a L1-norm Lasso and b our proposed tree-structured sparse learning method for pMCI vs. NC classification
Fig. 7
Fig. 7
The biomarkers identified from the GM density map by a L1-norm Lasso and b our proposed tree-structured sparse learning method for pMCI vs. sMCI classification

References

    1. Chen Y, An H, Zhu H, Stone T, Smith JK, Hall C, et al. White matter abnormalities revealed by diffusion tensor imaging in non-demented and demented HIV+ patients. Neuro Image. 2009;47(4):1154–1162. - PMC - PubMed
    1. Chu C, Hsu AL, Chou KH, Bandettini P, Lin C for the Alzheimer’s Disease Neuroimaging Initiative. Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images. Neuro Image. 2012;60(1):59–70. - PubMed
    1. Cuingnet R, Gerardin E, Tessieras J, Auzias G, Lehericy S, Habert MO, et al. Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the ADNI database. Neuro Image. 2011;56(2):766–781. doi: 10.1016/j.neuroimage.2010.06.013. - DOI - PubMed
    1. Davatzikos C, Fan Y, Wu X, Shen D, Resnick SM. Detection of prodromal Alzheimer’s disease via pattern classification of magnetic resonance imaging. Neurobiology of Aging. 2008a;29(4):514–523. doi: 10.1016/j.neurobiolaging.2006.11.010. - DOI - PMC - PubMed
    1. Davatzikos C, Resnick SM, Wu X, Parmpi P, Clark CM. Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI. Neuro Image. 2008b;41(4):1220–1227. doi: 10.1016/j.neuroimage.2008.03.050. - DOI - PMC - PubMed

Publication types