Abstract
In this paper, we propose a novel feature selection method by jointly considering (1) ‘task-specific’ relations between response variables (e.g., clinical labels in this work) and neuroimaging features and (2) ‘self-representation’ relations among neuroimaging features in a sparse regression framework. Specifically, the task-specific relation is devised to learn the relative importance of features for representation of response variables by a linear combination of the input features in a supervised manner, while the self-representation relation is used to take into account the inherent information among neuroimaging features such that any feature can be represented by a weighted sum of the other features, regardless of the label information, in an unsupervised manner. By integrating these two different relations along with a group sparsity constraint, we formulate a new sparse linear regression model for class-discriminative feature selection. The selected features are used to train a support vector machine for classification. To validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset; experimental results showed superiority of the proposed method over the state-of-the-art methods considered in this work.
Similar content being viewed by others
Notes
Available at ‘http://www.loni.usc.edu/ADNI’
Please refer to ‘www.adni-info.org’ for up-to-date information.
Refer to ‘http://www.adni-info.org’ for more details.
Available at ‘http://mipav.cit.nih.gov/clickwrap.php’
Note that we use a set of ROI volumes as features.
The term ‘self-similarity’, widely used in machine learning and computer vision, such as the literature (Liu et al. 2010; Zhu et al. 2015), indicates that each sample/feature can be represented by both other samples/features and itself. In this work, we assume that features are dependent, so it is reasonable to indicate that each ROI (or feature) can be sparsely represented by all ROIs (or features).
Available at ‘http://www.csie.ntu.edu.tw/cjlin/libsvm/’.
In Tables 2, 3, and 4, the boldface denotes the maximum performance in each column. (⋆ : Statistically significant from the proposed method with p < 0.05 and ∗: Statistically significant different from the proposed method with p < 0.001 on the paired-sample t-tests at 95% significance level between results of our method and all other competing methods).
The number in the parentheses represents an index of an ROI. Please refer to Table 7 for the full name of the respective ROIs.
References
Chételat, G., Eustache, F., Viader, F., Sayette, V.D.L., Pélerin, A., Mézenge, F., Hannequin, D., Dupuy, B., Baron, J.-C., & Desgranges, B. (2005). FDG-PET measurement is more accurate than neuropsychological assessments to predict global cognitive deterioration in patients with mild cognitive impairment. Neurocase, 11(1), 14–25.
Convit, A., De Asis, J., De Leon, M., Tarshish, C., De Santi, S., & Rusinek, H. (2000). Atrophy of the medial occipitotemporal, inferior, and middle temporal gyri in non-demented elderly predict decline to Alzheimers disease. Neurobiology of Aging, 21(1), 19–26.
Duchesne, S., Caroli, A., Geroldi, C., Collins, D.L., & Frisoni, G.B. (2009). Relating one-year cognitive change in mild cognitive impairment to baseline MRI features. NeuroImage, 47(4), 1363–1370.
Duda, R.O., Hart, P.E., & Stork, D.G. (2012). Pattern classification. Wiley.
Elhamifar, E., & Vidal, R. (2009). Sparse subspace clustering, CVPR (pp. 2790–2797).
Fox, N.C., & Schott, J.M. (2004). Imaging cerebral atrophy: Normal ageing to Alzheimer’s disease. The Lancet, 363(9406), 392–394.
Greicius, M.D., Srivastava, G., Reiss, A.L., & Menon, V. (2004). Default-mode network activity distinguishes Alzheimer’s disease from healthy aging: evidence from functional MRI. Proceedings of the National Academy of Sciences of the United States of America, 101(13), 4637–4642.
Guo, X., Wang, Z., Li, K., Li, Z., Qi, Z., Jin, Z., Yao, L., & Chen, K. (2010). Voxel-based assessment of gray and white matter volumes in Alzheimer’s disease. Neuroscience Letters, 468(2), 146–150.
He, X., Cai, D., & Niyogi, P. (2005). Laplacian score for feature selection, NIPS (pp. 507–514).
Kabani, N.J. (1998). 3D anatomical atlas of the human brain. NeuroImage, 7, 0700–0717.
Kim, H.J., Adluru, N., Bendlin, B.B., Johnson, S.C., Vemuri, B.C., & Singh, V. (2014). Canonical correlation analysis on riemannian manifolds and its applications, European Conference on Computer Vision (pp. 251–267).
Lee, G.-Y., Kim, J., Kim, J.H., Kim, K., & Seong, J.-K. (2014). Online learning for classification of Alzheimer disease based on cortical thickness and hippocampal shape analysis. Healthcare Informatics Research, 20 (1), 61–68.
Liu, G., Lin, Z., & Yu, Y. (2010). Robust subspace segmentation by low-rank representation, ICML (pp. 663–670).
López-de-Ipiña, K., Solé-Casals, J., Eguiraun, H., Alonso, J.B., Travieso, C.M., Ezeiza, A., Barroso, N., Ecay-Torres, M., Martinez-Lage, P., & Beitia, B. (2015). Feature selection for spontaneous speech analysis to aid in Alzheimer’s disease diagnosis: A fractal dimension approach. Computer Speech and Language, 30 (1), 43–60.
Lorenzi, M., Simpson, I.J., Mendelson, A.F., Vos, S.B., Cardoso, M.J., Modat, M., Schott, J.M., & Ourselin, S. (2016). Multimodal image analysis in Alzheimers disease via statistical modelling of non-local intensity correlations. Scientific Reports, 6.
Misra, C., Fan, Y., & Davatzikos, C. (2009). Baseline and longitudinal patterns of brain atrophy in MCI patients, and their use in prediction of short-term conversion to AD: results from ADNI. NeuroImage, 44(4), 1415–1422.
Mwangi, B., Tian, T.S., & Soares, J.C. (2014). A review of feature reduction techniques in neuroimaging. Neuroinformatics, 12(2), 229–244.
Shen, D., & Davatzikos, C. (2002). HAMMER: hierarchical attribute matching mechanism for elastic registration. IEEE Transactions on Medical Imaging, 21(11), 1421–1439.
Sled, J.G., Zijdenbos, A.P., & Evans, A.C. (1998). A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Transactions on Medical Imaging, 17(1), 87–97.
Spedding, A.L., Di Fatta, G., & Saddy, J.D. (2015). An LDA and probability-based classifier for the diagnosis of Alzheimer’s Disease from structural MRI, BIBM (pp. 1404–1411).
Suk, H.-I., Lee, S.-W., & Shen, D. (2015a). Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. Brain Structure and Function, 220(2), 841–859.
Suk, H.-I., Wee, C.-Y., Lee, S.-W., & Shen, D. (2015b). Supervised discriminative group sparse representation for mild cognitive impairment diagnosis. Neuroinformatics, 13(3), 277–295.
Thung, K.-H., Wee, C.-Y., Yap, P.-T., & Shen D. (2014). Neurodegenerative disease diagnosis using incomplete multimodality data via matrix shrinkage and completion. NeuroImage, 91, 386–400.
Thung, K.-H., Wee, C.-Y., Yap, P.-T., & Shen, D. (2015). Identification of progressive mild cognitive impairment patients using incomplete longitudinal MRI scans. Brain Structure and Function 1–17.
Wang, H., Nie, F., Huang, H., Risacher, S., Saykin, A.J., & Shen, L. (2011). Identifying AD-sensitive and cognitionrelevant imaging biomarkers via joint classification and regression, MICCAI (pp. 115–123).
Wang, Y., Fan, Y., Bhatt, P., & Davatzikos, C. (2010). High-dimensional pattern regression using machine learning: From medical images to continuous clinical variables. NeuroImage, 50(4), 1519–1535.
Wipf, D., & Nagarajan, S. (2010). Iterative reweighted and methods for finding sparse solutions. IEEE Journal of Selected Topics in Signal Processing, 4(2), 317–329.
Yuan, M., & Lin, Y. (2006). Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society Series B, 68(1), 49–67.
Zhang, D., & Shen, D. (2012). Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease. NeuroImage, 59(2), 895–907.
Zhang, D., Wang, Y., Zhou, L., Yuan, H., & Shen, D. (2011). Multimodal classification of Alzheimer’s disease and mild cognitive impairment. NeuroImage, 55(3), 856–867.
Zhang, Y., Brady, M., & Smith, S. (2001). Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Transactions on Medical Imaging, 20(1), 45–57.
Zhu, P., Zuo, W., Zhang, L., Hu, Q., & Shiu, S.C.K. (2015). Unsupervised feature selection by regularized selfrepresentation. Pattern Recognition, 48(2), 438–446.
Zhu, X., Suk, H.-I., & Shen, D. (2014a). Matrix-Similarity Based Loss Function and Feature Selection for Alzheimer’s Disease Diagnosis, CVPR (pp. 3089–3096).
Zhu, X., Suk, H.-I., & Shen, D. (2014b). Multi-modality canonical feature selection for Alzheimers disease diagnosis, MICCAI (pp. 162–169).
Zhu, X., Suk, H.-I., & Shen, D. (2014c). A novel matrix-similarity based loss function for joint regression and classification in AD diagnosis. NeuroImage, 14(0), 1–30.
Zhu, X., Suk, H.-I., & Shen, D. (2014d). A novel multi-relation regularization method for regression and classification in AD diagnosis, MICCAI (pp. 401–408).
Zhu, X., Suk, H.-I., Lee, S.-W., & Shen, D. (2015a). Canonical feature selection for joint regression and multi-class identification in Alzheimers disease diagnosis. Brain Imaging and Behavior, pp. 1–11.
Zhu, X., Suk, H.-I., Wang, L., Lee, S.-W., Shen, D., Initiative, A.D.N., & et al. (2015b). A novel relational regularization feature selection method for joint regression and classification in AD diagnosis. Medical Image Analysis, 38, 205–214.
Acknowledgments
This work was supported in part by NIH grants (EB006733, EB008374, MH100217, MH108914, AG041721, AG049371, AG042599, AG053867, EB022880, MH110274), the Nation Natural Science Foundation of China (Grant No: 61573270), the Brain Research Program through the National Research Foundation of Korea funded by the Ministry of Science, ICT & Future Planning (NRF-2014M3C7A1046050), the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning, and by the Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (No. 2017-0-00451).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
Xiaofeng Zhu, Heung-Il Suk, Seong-Whan Lee, and Dinggang Shen declare that they have no conflict of interest.
Ethical approval
We confirm that this article does not contain any studies with either human participants or animals performed by any of the authors.
Informed Consent
We confirm that informed consent was obtained from all individual participants included in the study.
Rights and permissions
About this article
Cite this article
Zhu, X., Suk, HI., Lee, SW. et al. Discriminative self-representation sparse regression for neuroimaging-based alzheimer’s disease diagnosis. Brain Imaging and Behavior 13, 27–40 (2019). https://doi.org/10.1007/s11682-017-9731-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11682-017-9731-x