Home Analysis of structural brain MRI and multi-parameter classification for Alzheimer’s disease
Article
Licensed
Unlicensed Requires Authentication

Analysis of structural brain MRI and multi-parameter classification for Alzheimer’s disease

  • Yingteng Zhang and Shenquan Liu EMAIL logo
Published/Copyright: June 15, 2017
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Biomedical Engineering / Biomedizinische Technik
From the journal Biomedical Engineering / Biomedizinische Technik Volume 63 Issue 4

Abstract

Incorporating with machine learning technology, neuroimaging markers which extracted from structural Magnetic Resonance Images (sMRI), can help distinguish Alzheimer’s Disease (AD) patients from Healthy Controls (HC). In the present study, we aim to investigate differences in atrophic regions between HC and AD and apply machine learning methods to classify these two groups. T1-weighted sMRI scans of 158 patients with AD and 145 age-matched HC were acquired from the ADNI database. Five kinds of parameters (i.e. cortical thickness, surface area, gray matter volume, curvature and sulcal depth) were obtained through the preprocessing steps. The recursive feature elimination (RFE) method for support vector machine (SVM) and leave-one-out cross validation (LOOCV) were applied to determine the optimal feature dimensions. Each kind of parameter was trained by SVM algorithm to acquire a classifier, which was used to classify HC and AD ultimately. Moreover, the ROC curves were depicted for testing the classifiers’ performance and the SVM classifiers of two-dimensional spaces took the top two important features as classification features for separating HC and AD to the maximum extent. The results showed that the decreased cortical thickness and gray matter volume dramatically exhibited the trend of atrophy. The key differences between AD and HC existed in the cortical thickness and gray matter volume of the entorhinal cortex and medial orbitofrontal cortex. In terms of classification results, an optimal accuracy of 90.76% was obtained via multi-parameter combination (i.e. cortical thickness, gray matter volume and surface area). Meanwhile, the receiver operating characteristic (ROC) curves and area under the curve (AUC) were also verified multi-parameter combination could reach a better classification performance (AUC=0.94) after the SVM-RFE method. The results could be well prove that multi-parameter combination could provide more useful classified features from multivariate anatomical structure than single parameter. In addition, as cortical thickness and multi-parameter combination contained more important classified information with fewer feature dimensions after feature selection, it could be optimum to separate HC from AD to take the top two important features of them to construct SVM classifiers in two-dimensional space. The proposed work is a promising approach suggesting an important role for machine-learning based diagnostic image analysis for clinical practice.

Keywords: Alzheimer’s disease; classification; cortical feature; multi-parameter combination; structural MRI; support vector machine

Funding source: National Natural Science Foundation of China

Award Identifier / Grant number: 11572127

Award Identifier / Grant number: 11172103

Funding statement: This work was supported by the National Natural Science Foundation of China under Grant Nos. 11572127 and 11172103.

  1. Author Statement

  2. Research funding: This work was supported by the National Natural Science Foundation of China under Grant Nos. 11572127 and 11172103.

  3. Conflict of interest: Authors state no conflict of interest.

  4. Informed consent: Informed consent is not applicable.

  5. Ethical approval: The conducted research is not related to either human or animals use.

References

[1] Abraham A, Pedregosa F, Eickenberg M, et al. Machine learning for neuroimaging with scikit-learn. Front Neuroinform 2014; 8: 14.10.3389/fninf.2014.00014Search in Google Scholar PubMed PubMed Central

[2] Aguilar C, Westman E, Muehlboeck JS, et al. Different multivariate techniques for automated classification of MRI data in Alzheimer’s disease and mild cognitive impairment. Psychiatry Res 2013; 212: 89–98.10.1016/j.pscychresns.2012.11.005Search in Google Scholar PubMed

[3] Arbabshirani MR, Plis S, Sui J, Calhoun VD. Single subject prediction of brain disorders in neuroimaging: promises and pitfalls. NeuroImage 2016; 145(Pt B): 137.10.1016/j.neuroimage.2016.02.079Search in Google Scholar PubMed PubMed Central

[4] Ashburner J, Friston KJ. Voxel-based morphometry—the methods. NeuroImage 2000; 11: 805–821.10.1006/nimg.2000.0582Search in Google Scholar PubMed

[5] Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. Comput Learn Theory 1992: 144–152.10.1145/130385.130401Search in Google Scholar

[6] Budson AE, Sullivan AL, Mayer E. Suppression of false recognition in Alzheimer’s disease and in patients with frontal lobe lesions. Brain 2002; 125: 2750–2765.10.1093/brain/awf277Search in Google Scholar PubMed

[7] Casanova R, Hsu FC, Espeland MA; Alzheimer’s disease Neuroimaging I. Classification of structural MRI images in Alzheimer’s disease from the perspective of ill-posed problems. PLoS One 2012; 7: e44877.10.1371/journal.pone.0044877Search in Google Scholar PubMed PubMed Central

[8] Challis E, Hurley P, Serra L, Bozzali M, Oliver S, Cercignani M. Gaussian process classification of Alzheimer’s disease and mild cognitive impairment from resting-state fMRI. NeuroImage 2015; 112: 232–243.10.1016/j.neuroimage.2015.02.037Search in Google Scholar PubMed

[9] Cherbuin N, Shaw M, Sachdev PS, Anstey KJ. Validated dementia risk factor composite is associated with lower hippocampal volumes and cortical thickness. Alzheimers Dement 2015; 11: P813–P814.10.1016/j.jalz.2015.06.1804Search in Google Scholar

[10] Cohn-Sheehy B, Ghosh P, Wirth M, Lehmann M, Madison C, Irwin W, et al. Temporoparietal cortical thickness outperforms hippocampal volume as a biomarker for atypical and early-onset Alzheimer’s disease. Alzheimers Dement 2013; 9: P41–P42.10.1016/j.jalz.2013.05.066Search in Google Scholar

[11] Corbo V, Salat DH, Powell MA, Milberg WP, McGlinchey RE. Combat exposure is associated with cortical thickness in Veterans with a history of chronic pain. Psychiatry Res 2016; 249: 38–44.10.1016/j.pscychresns.2016.02.003Search in Google Scholar PubMed

[12] Craddock RC, Holtzheimer PE, 3rd, Hu XP, Mayberg HS. Disease state prediction from resting state functional connectivity. Magn Reson Med 2009; 62: 1619–1628.10.1002/mrm.22159Search in Google Scholar PubMed PubMed Central

[13] De Martino F, Valente G, Staeren N, Ashburner J, Goebel R, Formisano E. Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns. NeuroImage 2008; 43: 44–58.10.1016/j.neuroimage.2008.06.037Search in Google Scholar PubMed

[14] Desikan RS, Segonne F, Fischl B, Quinn BT, Dickerson BC, Blacker D, et al. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. NeuroImage 2006; 31: 968–980.10.1016/j.neuroimage.2006.01.021Search in Google Scholar PubMed

[15] Dhikav V, Duraisamy S, Anand KS, Garga UC. Hippocampal volumes among older Indian adults: Comparison with Alzheimer’s disease and mild cognitive impairment. Ann Indian Acad Neurol 2016; 19: 195–200.10.4103/0972-2327.176863Search in Google Scholar PubMed PubMed Central

[16] Dickerson BC, Feczko E, Augustinack JC, et al. Differential effects of aging and Alzheimer’s disease on medial temporal lobe cortical thickness and surface area. Neurobiol Aging 2009; 30: 432–440.10.1016/j.neurobiolaging.2007.07.022Search in Google Scholar PubMed PubMed Central

[17] Du AT, Schuff N, Amend D. Magnetic resonance imaging of the entorhinal cortex and hippocampus in mild cognitive impairment and Alzheimer’s disease. J Neurol Neurosurg Psychiatry 2001; 71: 441–447.10.1136/jnnp.71.4.441Search in Google Scholar PubMed PubMed Central

[18] Du AT, Schuff N, Kramer JH, et al. Different regional patterns of cortical thinning in Alzheimer’s disease and frontotemporal dementia. Brain 2007; 130: 1159–1166.10.1093/brain/awm016Search in Google Scholar PubMed PubMed Central

[19] Farahat AK, Ghodsi A, Kamel MS. An efficient greedy method for unsupervised feature selection. IEEE International Conference on Data Mining, ICDM 2011, Vancouver, BC, Canada, December DBLP. 2011: 160–170.10.1109/ICDM.2011.22Search in Google Scholar

[20] Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006; 27: 861–874.10.1016/j.patrec.2005.10.010Search in Google Scholar

[21] Ferri CP, Prince M, Brayne C, et al. Global prevalence of dementia: a Delphi consensus study. The Lancet 2005; 366: 2112–2117.10.1016/S0140-6736(05)67889-0Search in Google Scholar

[22] Fischl B. FreeSurfer. NeuroImage 2012; 62: 774–781.10.1016/j.neuroimage.2012.01.021Search in Google Scholar PubMed PubMed Central

[23] Fjell AM, Walhovd KB, Fennema-Notestine C, et al. CSF biomarkers in prediction of cerebral and clinical change in mild cognitive impairment and Alzheimer’s disease. J Neurosci 2010; 30: 2088–2101.10.1523/JNEUROSCI.3785-09.2010Search in Google Scholar PubMed PubMed Central

[24] Friston KJ, Holmes AP, Worsley KJ. Statistical parametric maps in functional imaging: a general linear approach. Human Brain Mapp 1994; 2: 189–210.10.1002/hbm.460020402Search in Google Scholar

[25] Goryawala M, Zhou Q, Barker W, Loewenstein DA, Duara R, Adjouadi M. Inclusion of neuropsychological scores in atrophy models improves diagnostic classification of Alzheimer’s disease and mild cognitive impairment. Comput Intell Neurosci 2015; 2015: 56.10.1155/2015/865265Search in Google Scholar PubMed PubMed Central

[26] Guo X, Li Z, Chen K, Yao L, Wang Z, Li K. Mapping gray matter volume and cortical thickness in Alzheimer’s disease. Proc SPIE Int Soc Opt Eng 2010; 7626: 76260B1–76260B9.10.1117/12.844070Search in Google Scholar

[27] Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. Mach Learn 2002; 46: 34.10.1023/A:1012487302797Search in Google Scholar

[28] Hoesen GWV, Hyman BT, Damasio AR. Entorhinal cortex pathology in Alzheimer’s disease. Hippocampus 1991; 1: 1–8.10.1002/hipo.450010102Search in Google Scholar PubMed

[29] Hoesen GWV, Parvizi J, Chu CC. Orbitofrontal cortex pathology in Alzheimer’s disease. Cereb Cortex 2000; 10: 243–251.10.1093/cercor/10.3.243Search in Google Scholar PubMed

[30] Ikonomovic MD, Abrahamson EE, Isanski BA. Superior frontal cortex cholinergic axon density in mild cognitive impairment and early Alzheimer disease. Arch Neurol 2007; 64: 1312–1317.10.1001/archneur.64.9.1312Search in Google Scholar PubMed

[31] Im K, Lee JM, Seo SW, et al. Sulcal morphology changes and their relationship with cortical thickness and gyral white matter volume in mild cognitive impairment and Alzheimer’s disease. NeuroImage 2008; 43: 103–113.10.1016/j.neuroimage.2008.07.016Search in Google Scholar PubMed

[32] Kloppel S, Peter J, Ludl A, et al. Applying automated MR-based diagnostic methods to the memory clinic: a prospective study. J Alzheimers Dis 2015; 47: 939–954.10.3233/JAD-150334Search in Google Scholar PubMed PubMed Central

[33] Li M, Qin Y, Gao F, Zhu W, He X. Discriminative analysis of multivariate features from structural MRI and diffusion tensor images. Magn Reson Imaging 2014; 32: 1043–1051.10.1016/j.mri.2014.05.008Search in Google Scholar PubMed

[34] Lillemark L, Sørensen L, Pai A, Dam EB, Nielsen M. Brain region’s relative proximity as marker for Alzheimer’s disease based on structural MRI. BMC Med Imaging 2014; 14: 1–12.10.1186/1471-2342-14-21Search in Google Scholar PubMed PubMed Central

[35] Michel V, Gramfort A, Varoquaux G, Eger E, Keribin C, Thirion B. A supervised clustering approach for fMRI-based inference of brain states. Pattern Recognit 2012; 45: 2041–2049.10.1016/j.patcog.2011.04.006Search in Google Scholar

[36] Moradi E, Pepe A, Gaser C, Huttunen H, Tohka J. Alzheimer’s disease neuroimaging I. Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects. NeuroImage 2015; 104: 398–412.10.1016/j.neuroimage.2014.10.002Search in Google Scholar PubMed PubMed Central

[37] Nir TM, Villalon-Reina JE, Prasad G, et al. Diffusion weighted imaging-based maximum density path analysis and classification of Alzheimer’s disease. Neurobiol Aging 2015; 36 Suppl 1: S132–S140.10.1016/j.neurobiolaging.2014.05.037Search in Google Scholar PubMed PubMed Central

[38] Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res 2011; 12: 6.Search in Google Scholar

[39] Richards BA, Chertkow H, Singh V, et al. Patterns of cortical thinning in Alzheimer’s disease and frontotemporal dementia. Neurobiol Aging 2009; 30: 1626–1636.10.1016/j.neurobiolaging.2007.12.019Search in Google Scholar PubMed

[40] Sabuncu MR, Leemput KV. The relevance voxel machine (RVoxM): a self-tuning Bayesian model for informative image-based prediction. IEEE Trans Med Imaging 2012; 31: 2290–2306.10.1109/TMI.2012.2216543Search in Google Scholar PubMed PubMed Central

[41] Salat DH, Greve DN, Pacheco JL, et al. Regional white matter volume differences in nondemented aging and Alzheimer’s disease. NeuroImage 2009; 44: 1247–1258.10.1016/j.neuroimage.2008.10.030Search in Google Scholar PubMed PubMed Central

[42] Simmons A, Westman E, Zhang Y, et al. Multivariate data analysis of regional MRI volumes and cortical thickness measures to distinguish between Alzheimer’s disease, mild cognitive impairment and healthy controls. Alzheimers Dement 2009; 5: e16.10.1016/j.jalz.2009.07.075Search in Google Scholar

[43] Szatkowska I, Szymanska O, Bojarski P, Grabowska A. Cognitive inhibition in patients with medial orbitofrontal damage. Exp Brain Res 2007; 181: 109–115.10.1007/s00221-007-0906-3Search in Google Scholar PubMed

[44] Tessitore A, Santangelo G, De Micco R, et al. Cortical thickness changes in patients with Parkinson’s disease and impulse control disorders. Parkinsonism Relat Disord 2016; 24: 119–125.10.1016/j.parkreldis.2015.10.013Search in Google Scholar PubMed

[45] Tierney MC, Yao C, Kiss A, McDowell I. Neuropsychological tests accurately predict incident Alzheimer disease after 5 and 10 years. Neurology 2005; 64: 1853–1859.10.1212/01.WNL.0000163773.21794.0BSearch in Google Scholar PubMed

[46] Velayudhan L, Proitsi P, Westman E, et al. Entorhinal cortex thickness predicts cognitive decline in Alzheimer’s disease. J Alzheimers Dis 2013; 33: 755–766.10.3233/JAD-2012-121408Search in Google Scholar PubMed

[47] Visser PJ, Verhey FR, Hofman PA, Scheltens P, Jolles J. Medial temporal lobe atrophy predicts Alzheimer’s disease in patients with minor cognitive impairment. J Neurol Neurosurg Psychiatry 2002; 72: 491–497.Search in Google Scholar

[48] Wasserstein RL, Lazar NA. The ASA’s statement on p-values: context, process, and purpose. Am Stat 2016; 70: 129–133.10.1080/00031305.2016.1154108Search in Google Scholar

[49] Wee CY, Yap PT, Shen D, Alzheimer’s disease neuroimaging I. Prediction of Alzheimer’s disease and mild cognitive impairment using cortical morphological patterns. Hum Brain Mapp 2013; 34: 3411–3425.10.1002/hbm.22156Search in Google Scholar PubMed PubMed Central

[50] Yang Y, Raine A. Prefrontal structural and functional brain imaging findings in antisocial, violent, and psychopathic individuals: a meta-analysis. Psychiatry Res 2009; 174: 81–88.10.1016/j.pscychresns.2009.03.012Search in Google Scholar PubMed PubMed Central

[51] Zhang Y, Dong Z, Phillips P, et al. Detection of subjects and brain regions related to Alzheimer’s disease using 3D MRI scans based on eigenbrain and machine learning. Front Comput Neurosci 2015; 9: 66.10.3389/fncom.2015.00066Search in Google Scholar PubMed PubMed Central

[52] Zhao M, Zhao C, Zheng C. Identifying concealed information using wavelet feature extraction and support vector machine. Procedia Environ Sci 2011; 8: 337–343.10.1016/j.proenv.2011.10.053Search in Google Scholar

[53] Zweig MH, Campbell G. Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 1993; 39: 17.10.1093/clinchem/39.4.561Search in Google Scholar

Received: 2016-08-25
Accepted: 2017-05-16
Published Online: 2017-06-15
Published in Print: 2018-07-26

©2018 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Research articles
  3. A new in vitro spine test rig to track multiple vertebral motions under physiological conditions
  4. In-service characterization of a polymer wick-based quasi-dry electrode for rapid pasteless electroencephalography
  5. Spike detection using a multiresolution entropy based method
  6. Obstacles in using a computer screen for steady-state visually evoked potential stimulation
  7. Classification of pulmonary pathology from breath sounds using the wavelet packet transform and an extreme learning machine
  8. Filtering of ECG signals distorted by magnetic field gradients during MRI using non-linear filters and higher-order statistics
  9. Failure analysis of eleven Gates Glidden drills that fractured intraorally during post space preparation. A retrieval analysis study
  10. Assessing multiple muscle activation during squat movements with different loading conditions – an EMG study
  11. In-vivo monitoring of infection via implantable microsensors: a pilot study
  12. Analysis of structural brain MRI and multi-parameter classification for Alzheimer’s disease
  13. False spectra formation in the differential two-channel scheme of the laser Doppler flowmeter
  14. A priori knowledge integration for the detection of cerebral aneurysm
  15. Is the location of the signal intensity weighted centroid a reliable measurement of fluid displacement within the disc?
  16. Image-based 3D surface approximation of the bladder using structure-from-motion for enhanced cystoscopy based on phantom data
  17. Fused multivariate empirical mode decomposition (MEMD) and inverse solution method for EEG source localization
  18. Quantifying the dynamics of electroencephalographic (EEG) signals to distinguish alcoholic and non-alcoholic subjects using an MSE based K-d tree algorithm
  19. A hybrid active force control of a lower limb exoskeleton for gait rehabilitation
  20. Short communication
  21. Can somatosensory electrical stimulation relieve spasticity in post-stroke patients? A TMS pilot study
https://doi.org/10.1515/bmt-2016-0239
Keywords for this article
Alzheimer’s disease; classification; cortical feature; multi-parameter combination; structural MRI; support vector machine

Articles in the same Issue

  1. Frontmatter
  2. Research articles
  3. A new in vitro spine test rig to track multiple vertebral motions under physiological conditions
  4. In-service characterization of a polymer wick-based quasi-dry electrode for rapid pasteless electroencephalography
  5. Spike detection using a multiresolution entropy based method
  6. Obstacles in using a computer screen for steady-state visually evoked potential stimulation
  7. Classification of pulmonary pathology from breath sounds using the wavelet packet transform and an extreme learning machine
  8. Filtering of ECG signals distorted by magnetic field gradients during MRI using non-linear filters and higher-order statistics
  9. Failure analysis of eleven Gates Glidden drills that fractured intraorally during post space preparation. A retrieval analysis study
  10. Assessing multiple muscle activation during squat movements with different loading conditions – an EMG study
  11. In-vivo monitoring of infection via implantable microsensors: a pilot study
  12. Analysis of structural brain MRI and multi-parameter classification for Alzheimer’s disease
  13. False spectra formation in the differential two-channel scheme of the laser Doppler flowmeter
  14. A priori knowledge integration for the detection of cerebral aneurysm
  15. Is the location of the signal intensity weighted centroid a reliable measurement of fluid displacement within the disc?
  16. Image-based 3D surface approximation of the bladder using structure-from-motion for enhanced cystoscopy based on phantom data
  17. Fused multivariate empirical mode decomposition (MEMD) and inverse solution method for EEG source localization
  18. Quantifying the dynamics of electroencephalographic (EEG) signals to distinguish alcoholic and non-alcoholic subjects using an MSE based K-d tree algorithm
  19. A hybrid active force control of a lower limb exoskeleton for gait rehabilitation
  20. Short communication
  21. Can somatosensory electrical stimulation relieve spasticity in post-stroke patients? A TMS pilot study
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 7.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/bmt-2016-0239/html
Scroll to top button