Deep Learning for Alzheimer’s Disease Classification using Texture Features

Author(s): Jae-Hong So , Nuwan Madusanka , Heung-Kook Choi* , Boo-Kyeong Choi , Hyeon-Gyun Park .

Journal Name: Current Medical Imaging

Volume 15 , Issue 7 , 2019

Become EABM
Become Reviewer

Graphical Abstract:


Abstract:

Background: We propose a classification method for Alzheimer’s disease (AD) based on the texture of the hippocampus, which is the organ that is most affected by the onset of AD.

Methods: We obtained magnetic resonance images (MRIs) of Alzheimer’s patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. This dataset consists of image data for AD, mild cognitive impairment (MCI), and normal controls (NCs), classified according to the cognitive condition. In this study, the research methods included image processing, texture analyses, and deep learning. Firstly, images were acquired for texture analyses, which were then re-spaced, registered, and cropped with Gabor filters applied to the resulting image data. In the texture analyses, we applied the 3-dimensional (3D) gray-level co-occurrence (GLCM) method to evaluate the textural features of the image, and used Fisher’s coefficient to select the appropriate features for classification. In the last stage, we implemented a deep learning multi-layer perceptron (MLP) model, which we divided into three types, namely, AD-MCI, AD-NC, and MCI-NC.

Results: We used this model to assess the accuracy of the proposed method. The classification accuracy of the proposed deep learning model was confirmed in the cases of AD-MCI (72.5%), ADNC (85%), and MCI-NC (75%). We also evaluated the results obtained using a confusion matrix, support vector machine (SVM), and K-nearest neighbor (KNN) classifier and analyzed the results to objectively verify our model. We obtained the highest accuracy of 85% in the AD-NC.

Conclusion: The proposed model was at least 6–19% more accurate than the SVM and KNN classifiers, respectively. Hence, this study confirms the validity and superiority of the proposed method, which can be used as a diagnostic tool for early Alzheimer’s diagnosis.

Keywords: Alzheimer's disease, deep learning, texture analysis, hippocampus, image processing, classification.

[1]
Alzheimer's Association. Alzheimer’s disease facts and figures. Alzheimers Dement 2018; 14(3): 367-62.
[http://dx.doi.org/10.1016/j.jalz.2018.02.001]
[2]
Brookmeyer R, Abdalla N, Kawas CH, Corrada MM. Forecasting the prevalence of preclinical and clinical Alzheimer’s disease in the United States. Alzheimers Dement 2018; 14(2): 121-29.
[http://dx.doi.org/10.1016/j.jalz.2017.10.009] [PMID: 29233480]
[3]
Huang J, Auchus AP. Diffusion tensor imaging of normal appearing white matter and its correlation with cognitive functioning in mild cognitive impairment and Alzheimer’s disease. Ann N Y Acad Sci 2007; 1097(1): 259-64.
[http://dx.doi.org/10.1196/annals.1379.021] [PMID: 17413027]
[4]
Petersen RC, Smith GE, Waring SC, Ivnik RJ, Tangalos EG, Kokmen E. Mild cognitive impairment: clinical characterization and outcome. Arch Neurol 1999; 56(3): 303-08.
[http://dx.doi.org/10.1001/archneur.56.3.303] [PMID: 10190820]
[5]
Mangialasche F, Solomon A, Winblad B, Mecocci P, Kivipelto M. Alzheimer’s disease: clinical trials and drug development Lancet Neurol 2010; 9(7): 702-16.
[http://dx.doi.org/10.1016/S1474-4422(10)70119-8] [PMID: 20610346]
[6]
Mueller SG, Weiner MW, Thal LJ, et al. Ways toward an early diagnosis in Alzheimer’s disease: the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Alzheimers Dement 2005; 1(1): 55-66.
[http://dx.doi.org/10.1016/j.jalz.2005.06.003] [PMID: 17476317]
[7]
Querbes O, Aubry F, Pariente J, et al. Early diagnosis of Alzheimer’s disease using cortical thickness: impact of cognitive reserve. Brain 2009; 132(Pt8): 2036-47.
[http://dx.doi.org/10.1093/brain/awp105] [PMID: 19439419]
[8]
Ovais M, Zia N, Ahmad I, et al. Phyto-therapeutic and nanomedicinal approaches to cure Alzheimer’s disease: Present status and future opportunities. Front Aging Neurosci 2018; 10: 284.
[http://dx.doi.org/10.3389/fnagi.2018.00284] [PMID: 30405389]
[9]
Chételat G. Multimodal neuroimaging in Alzheimer’s disease: Early diagnosis, physiopathological mechanisms, and impact of lifestyle. J Alzheimers Dis 2018; 4(s1): S199-211.
[http://dx.doi.org/10.3233/JAD-179920] [PMID: 29504542]
[10]
Davatzikos C, Bhatt P, Shaw LM, Batmanghelich KN, Trojanowski JQ. Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification. Neurobiol Aging 2011; 32(12): 2322.e19.
[http://dx.doi.org/10.1016/j.neurobiolaging.2010.05.023] [PMID: 20594615]
[11]
Samper-González J, Burgos N, Bottani S, et al. Reproducible evaluation of classification methods in Alzheimer’s disease: Framework and application to MRI and PET data. Neuroimage 2018; 183: 504-21.
[http://dx.doi.org/10.1016/j.neuroimage.2018.08.042] [PMID: 30130647]
[12]
Callen DJA, Black SE, Gao F, Caldwell CB, Szalai JP. Beyond the hippocampus: MRI volumetry confirms widespread limbic atrophy in AD. Neurology 2001; 57(9): 1669-74.
[http://dx.doi.org/10.1212/WNL.57.9.1669] [PMID: 11706109]
[13]
Lancaster JL, Tordesillas-Gutiérrez D, Martinez M, et al. Bias between MNI and Talairach coordinates analyzed using the ICBM- 152 brain template. Hum Brain Mapp 2007; 28(11): 1194-205.
[http://dx.doi.org/10.1002/hbm.20345] [PMID: 17266101]
[14]
Mori S, Oishi K, Jiang H, et al. Stereotaxic white matter atlas based on diffusion tensor imaging in an ICBM template. Neuroimage 2008; 40(2): 570-82.
[http://dx.doi.org/10.1016/j.neuroimage.2007.12.035] [PMID: 18255316]
[15]
Wesarg S, Seitel M, Firle EA, Dold C. AHA conform visualization of conventionally acquired cardiac CT data using the toolkits itk and vtk. CARS 2004.
[http://dx.doi.org/10.1016/j.ics.2004.03.322]
[16]
Madusanka N, Choi H-K, So J-H, Choi B-K. Alzheimer’s disease classification based on multi-feature fusion. Curr Med Imaging Rev 2018; 15(2): 161-8.
[http://dx.doi.org/110.2174/1573405614666181012102626]
[17]
Fedorov A, Beichel R, Kalpathy-Cramer J, et al. 3D Slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging 2012; 30(9): 1323-41.
[http://dx.doi.org/10.1016/j.mri.2012.05.001] [PMID: 22770690]
[18]
Fedorov A, Tuncali K, Fennessy FM, et al. Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 2012; 36(4): 987-2.
[http://dx.doi.org/10.1002/jmri.23688] [PMID: 22645031]
[19]
Gabor D. Theory of communication. Part 1 the analysis of information. Journal of the Institution of Electrical Engineers-Part III Radio and Communication Engineering 1946; 93(26): 429-12.
[http://dx.doi.org/10.1049/ji-3-2.1946.0074]
[20]
Zhang J, Tan T, Ma L. Invariant texture segmentation via circular Gabor filters. In:Proceedings of the 16th IAPR International Conference on Pattern Recognition (ICPR) 2002; Quebec, Canada. 901-4.
[21]
Kong WK, Zhang D, Li W. Palmprint feature extraction using 2-D Gabor filters. Pattern Recognit 2003; 36(10): 2339-8.
[http://dx.doi.org/10.1016/S0031-3203(03)00121-3]
[22]
Jain AK, Ratha NK, Lakshmanan S. Object detection using Gabor filters. Pattern Recognit 1997; 30(2): 295-15.
[http://dx.doi.org/10.1016/S0031-3203(96)00068-4]
[23]
Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell 1996; 18(8): 837-5.
[http://dx.doi.org/10.1109/34.531803]
[24]
Dunn D, Higgins WE, Wakeley J. Texture segmentation using 2-d gabor elementary functions. IEEE Trans Pattern Anal Mach Intell 1994; 16(2): 130-9.
[http://dx.doi.org/10.1109/34.273736]
[25]
Robert M. Haralick, K Shanmugam, Its’Hak Dinstein. Textural features for image classification. IEEE Trans Cybern 1973; 3(6): 610-1.
[26]
Gadelmawla ES. A vision system for surface roughness characterization using the gray level co-occurrence matrix. NDT Int 2004; 37(7): 577-11.
[http://dx.doi.org/10.1016/j.ndteint.2004.03.004]
[27]
Partio M, Cramariuc B, Gabbouj M, Visa A. Rock texture retrieval using gray level co-occurrence matrix. In: Proceedings of the 5th Nordic Signal Processing Symposium, NORSIG 2002; Norway;. 1-5.
[28]
Tuceryan M, Jain AK. The handbook of pattern recognition and computer vision. 2nd ed. New Jersey: World Scientific, Inc. 1998.
[29]
Soh L, Tsatsoulis C. Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens 1999; 37(2): 780-15.
[http://dx.doi.org/10.1109/36.752194]
[30]
Pydipati R, Burks TF, Lee WS. Identification of citrus disease using color texture features and discriminant analysis. Comput Electron Agric 2006; 52(1-2): 49-10.
[http://dx.doi.org/10.1016/j.compag.2006.01.004]
[31]
Wang H, Guo X-H, Jia Z-W, et al. Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image. Eur J Radiol 2010; 74(1): 124-9.
[http://dx.doi.org/10.1016/j.ejrad.2009.01.024] [PMID: 19261415]
[32]
Kayitakire F, Hamel C, Defourny P. Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery. Remote Sens Environ 2006; 102(3-4): 390-11.
[http://dx.doi.org/10.1016/j.rse.2006.02.022]
[33]
Fisher RA. The use of multiple measurements in taxonomic problems. Ann Eugen 1936; 7(2): 179-9.
[http://dx.doi.org/10.1111/j.1469-1809.1936.tb02137.x]
[34]
Plata S. A note on Fisher’s correlation coefficient. Appl Math Lett 2006; 19(6): 499-3.
[http://dx.doi.org/10.1016/j.aml.2005.02.036]
[35]
Saqlain SM, Sher M, Shah FA, et al. Fisher score and Matthews correlation coefficient-based feature subset selection for heart disease diagnosis using support vector machines. Knowl Inf Syst 2019; 58(1): 139-67.
[36]
Narang A, Batra B, Ahuja A, Yadav J, Pachauri N. Classification of EEG signals for epileptic seizures using Levenberg-Marquardt algorithm based multilayer perceptron neural network. J Intell Fuzzy Syst 2018; 34(3): 1669-8.
[http://dx.doi.org/10.3233/JIFS-169460]
[37]
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521(7553): 436-4.
[http://dx.doi.org/10.1038/nature14539] [PMID: 26017442]
[38]
Bayat FM, Prezioso M, Chakrabarti B, Nili H, Kataeva I, Strukov D. Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nat Commun 2018; 9(1): 2331.
[http://dx.doi.org/10.1038/s41467-018-04482-4] [PMID: 29899421]
[39]
Chaudhuri BB, Bhattacharya U. Efficient training and improved performance of multilayer perceptron in pattern classification. Neurocomputing 2000; 34(1-4): 11-27.
[http://dx.doi.org/10.1016/S0925-2312(00)00305-2]
[40]
Pham BT, Bui DT, Pourghasemi HR, Indra P, Dholakia MB. Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theor Appl Climatol 2017; 128(1-2): 255-18.
[http://dx.doi.org/10.1007/s00704-015-1702-9]
[41]
Zeiler MD, Ranzato M, Monga R, et al. On rectified linear units for speech processing. ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing 2013; Vancouver, BC, Canada. 3517-4.
[42]
Maas Andrew L, Awni Y. Hannun, Andrew Y Ng. Rectifier nonlinearities improve neural network acoustic models. International Conference on Machine Learning (ICML) 2013; Atlanta; USA. 3-5.
[43]
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. AISTATS 2010; 9: 249-7.
[44]
Townsend JT. Theoretical analysis of an alphabetic confusion matrix. Percept Psychophys 1971; 9(1): 40-10. 10.3758/BF03213026
[http://dx.doi.org/10.3758/BF03213026]
[45]
Patil TR, Sherekar SS. Performance analysis of Naive Bayes and J48 classification algorithm for data classification. Int J Comput Appl 2013; 6(2): 256-5.
[46]
Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542(7639): 115-8.
[http://dx.doi.org/10.1038/nature21056] [PMID: 28117445]
[47]
Veropoulos K, Campbell C, Cristianini N. Controlling the sensitivity of support vector machines. In: Proceedings of the International Joint Conference on AI 1999; Sweden. 60-5.
[48]
Ruuska S, Hämäläinen W, Kajava S, Mughal M, Matilainen P, Mononen J. Evaluation of the confusion matrix method in the validation of an automated system for measuring feeding behaviour of cattle. Behav Processes 2018; 148: 56-62.
[http://dx.doi.org/10.1016/j.beproc.2018.01.004] [PMID: 29330090]
[49]
Ohsaki M, Wang P, Matsuda K, Katagiri S, Watanabe H, Ralescu A. Confusion-matrix-based kernel logistic regression for imbalanced data classification. IEEE Trans Knowl Data Eng 2017; 29(9): 1806-13.
[http://dx.doi.org/10.1109/TKDE.2017.2682249]
[50]
Albert MS, DeKosky ST, Dickson D, et al. The diagnosis of mild cognitive impairment due to Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimers Dement 2011; 7(3): 270-79.
[http://dx.doi.org/10.1016/j.jalz.2011.03.008] [PMID: 21514249]
[51]
Liu S, Liu S, Cai W, Pujol S, Kikinis R, Feng D. Early diagnosis of Alzheimer’s disease with deep learning. In: IEEE 11th International Symposium on Biomedical Imaging (ISBI); 2014; Beijing, China;. 1015-8.
[http://dx.doi.org/10.1109/ISBI.2014.6868045]
[52]
Gray KR, Wolz R, Keihaninejad S, et al. Regional analysis of FDG-PET for use in the classification of Alzheimer’s Disease. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2011; Chicago, IL, USA. 1082-5.
[http://dx.doi.org/10.1109/ISBI.2011.5872589]


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 15
ISSUE: 7
Year: 2019
Page: [689 - 698]
Pages: 10
DOI: 10.2174/1573405615666190404163233
Price: $58

Article Metrics

PDF: 13
HTML: 2