Advertisement

Classification of Alzheimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling

  • Shui-Hua Wang
  • Preetha Phillips
  • Yuxiu Sui
  • Bin Liu
  • Ming Yang
  • Hong Cheng
Image & Signal Processing
Part of the following topical collections:
  1. Advanced Computational Intelligence and Soft Computing in Medical Imaging

Abstract

Alzheimer’s disease (AD) is a progressive brain disease. The goal of this study is to provide a new computer-vision based technique to detect it in an efficient way. The brain-imaging data of 98 AD patients and 98 healthy controls was collected using data augmentation method. Then, convolutional neural network (CNN) was used, CNN is the most successful tool in deep learning. An 8-layer CNN was created with optimal structure obtained by experiences. Three activation functions (AFs): sigmoid, rectified linear unit (ReLU), and leaky ReLU. The three pooling-functions were also tested: average pooling, max pooling, and stochastic pooling. The numerical experiments demonstrated that leaky ReLU and max pooling gave the greatest result in terms of performance. It achieved a sensitivity of 97.96%, a specificity of 97.35%, and an accuracy of 97.65%, respectively. In addition, the proposed approach was compared with eight state-of-the-art approaches. The method increased the classification accuracy by approximately 5% compared to state-of-the-art methods.

Keywords

Alzheimer’s disease Convolutional neural network Leaky rectified linear unit Max pooling Data augmentation Activation function 

Notes

Acknowledgements

This paper was supported by Open fund of Key Laboratory of Guangxi High Schools Complex System and Computational Intelligence (2016CSCI01), Natural Science Foundation of China (61602250) and Natural Science Foundation of Jiangsu Province (BK20150983), and National Institutes of Health (P50 AG05681, P01 AG03991, R01 AG021910, P50 MH071616, U24 RR021382, R01 MH56584).

Compliance with ethical standards

Conflict of interest

We have no conflicts of interest to disclose with regard to the subject matter of this paper.

References

  1. 1.
    Lange, C. et al., Prediction of Alzheimer's Dementia in Patients with Amnestic Mild Cognitive Impairment in Clinical Routine: Incremental Value of Biomarkers of Neurodegeneration and Brain Amyloidosis Added Stepwise to Cognitive Status. J. Alzheimers Dis. 61(1):373–388, 2018.CrossRefPubMedGoogle Scholar
  2. 2.
    Silveira, M. B. et al., F-18-Fluorocholine Uptake and Positron Emission Tomography Imaging in Rat Peritoneal Endometriosis. Reprod. Sci. 25(1):19–25, 2018.CrossRefPubMedGoogle Scholar
  3. 3.
    Liu, G., Phillips, P., and Yuan, T.-F., Detection of Alzheimer's Disease by Three-Dimensional Displacement Field Estimation in Structural Magnetic Resonance Imaging. J. Alzheimers Dis. 50(1):233–248, 2016.PubMedGoogle Scholar
  4. 4.
    Plant, C. et al., Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer's disease. NeuroImage. 50(1):162–174, 2010.CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    Savio, A., and Grana, M., Deformation based feature selection for Computer Aided Diagnosis of Alzheimer's Disease. Expert Syst. Appl. 40(5):1619–1628, 2013.CrossRefGoogle Scholar
  6. 6.
    Gray, K. R. et al., Random forest-based similarity measures for multi-modal classification of Alzheimer's disease. NeuroImage. 65:167–175, 2013.CrossRefPubMedGoogle Scholar
  7. 7.
    Zhang, Y., Detection of Alzheimer's disease by displacement field and machine learning. PeerJ. 3:Article ID. e1251, 2015.CrossRefGoogle Scholar
  8. 8.
    Wang, S.-H., Single slice based detection for Alzheimer’s disease via wavelet entropy and multilayer perceptron trained by biogeography-based optimization. Multimed. Tools Appl., 2016.  https://doi.org/10.1007/s11042-016-4222-4.
  9. 9.
    Sun, J.-D., Multivariate Approach for Alzheimer's disease Detection Using Stationary Wavelet Entropy and Predator-Prey Particle Swarm Optimization. J. Alzheimers Dis., 2017.  https://doi.org/10.3233/JAD-170069.
  10. 10.
    Gorji, H. T., and Haddadnia, J., A novel method for early diagnosis of Alzheimer's disease based on pseudo Zernike moment from structural MRI. Neuroscience. 305:361–371, 2015.CrossRefPubMedGoogle Scholar
  11. 11.
    Du, S., Alzheimer's Disease Detection by Pseudo Zernike Moment and Linear Regression Classification. CNS Neurol. Disord. Drug Targets. 16(1):11–15, 2017.CrossRefPubMedGoogle Scholar
  12. 12.
    Raza, M. et al., Appearance based pedestrians' head pose and body orientation estimation using deep learning. Neurocomputing. 272:647–659, 2018.CrossRefGoogle Scholar
  13. 13.
    Bach-Andersen, M., Romer-Odgaard, B., and Winther, O., Deep learning for automated drivetrain fault detection. Wind Energy. 21(1):29–41, 2018.CrossRefGoogle Scholar
  14. 14.
    Wei, G., Color Image Enhancement based on HVS and PCNN. SCIENCE CHINA Inf. Sci. 53(10):1963–1976, 2010.CrossRefGoogle Scholar
  15. 15.
    Wu, L. N., Segment-based coding of color images. Sci. China Ser. F-Inf. Sci. 52(6):914–925, 2009.CrossRefGoogle Scholar
  16. 16.
    Wu, L. N., Improved image filter based on SPCNN. Sci. China Ser. F-Inf. Sci. 51(12):2115–2125, 2008.CrossRefGoogle Scholar
  17. 17.
    Ardekani, B. A., Figarsky, K., and Sidtis, J. J., Sexual Dimorphism in the Human Corpus Callosum: An MRI Study Using the OASIS Brain Database. Cereb. Cortex. 23(10):2514–2520, 2013.CrossRefPubMedGoogle Scholar
  18. 18.
    Marcus, D. S. et al., Open access series of imaging studies (OASIS): Cross-sectional MRI data in young, middle aged, nondemented, and demented older adults. J. Cogn. Neurosci. 19(9):1498–1507, 2007.CrossRefPubMedGoogle Scholar
  19. 19.
    Marcus, D. S. et al., Open access series of imaging studies: longitudinal MRI data in nondemented and demented older adults. J. Cogn. Neurosci. 22(12):2677–2684, 2010.CrossRefPubMedPubMedCentralGoogle Scholar
  20. 20.
    Grassi, M. et al., A Clinically-Translatable Machine Learning Algorithm for the Prediction of Alzheimer's Disease Conversion in Individuals with Mild and Premild Cognitive Impairment. J. Alzheimers Dis. 61(4):1555–1572, 2018.CrossRefPubMedGoogle Scholar
  21. 21.
    Sheinerman, K. S. et al., Circulating brain-enriched microRNAs as novel biomarkers for detection and differentiation of neurodegenerative diseases. Alzheimers Res. Ther. 9:13: Article ID. 89, 2017.CrossRefGoogle Scholar
  22. 22.
    Frolich, L. et al., Incremental value of biomarker combinations to predict progression of mild cognitive impairment to Alzheimer's dementia. Alzheimers Res. Ther. 9:15: Article ID. 84, 2017.CrossRefGoogle Scholar
  23. 23.
    Dhal, K. G., Quraishi, M. I., and Das, S., An Improved Cuckoo Search based Optimal Ranged Brightness Preserved Histogram Equalization and Contrast Stretching Method. Int. J. Swarm Intell. Res. 8(1):1–29, 2017.CrossRefGoogle Scholar
  24. 24.
    Lu, H. M., Facial Emotion Recognition Based on Biorthogonal Wavelet Entropy, Fuzzy Support Vector Machine, and Stratified Cross Validation. IEEE Access. 4:8375–8385, 2016.CrossRefGoogle Scholar
  25. 25.
    Gorriz, J. M., and Ramírez, J., Wavelet entropy and directed acyclic graph support vector machine for detection of patients with unilateral hearing loss in MRI scanning. Front. Comput. Neurosci. 10:Article ID. 160, 2016.Google Scholar
  26. 26.
    Wu, L., Weights optimization of neural network via improved BCO approach. Prog. Electromagn. Res. 83:185–198, 2008.CrossRefGoogle Scholar
  27. 27.
    Jun, Y., and Wei, G., Find multi-objective paths in stochastic networks via chaotic immune PSO. Expert Syst. Appl. 37(3):1911–1919, 2010.CrossRefGoogle Scholar
  28. 28.
    Ozer, I., Ozer, Z., and Findik, O., Noise robust sound event classification with convolutional neural network. Neurocomputing. 272:505–512, 2018.CrossRefGoogle Scholar
  29. 29.
    Trakoolwilaiwan, T. et al., Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: three-class classification of rest, right-, and left-hand motor execution. Neurophotonics. 5(1):Article ID. 011008, 2018.Google Scholar
  30. 30.
    Chen, Y., Voxelwise detection of cerebral microbleed in CADASIL patients by leaky rectified linear unit and early stopping: A class-imbalanced susceptibility-weighted imaging data study. Multimed Tools Appl (2017).  https://doi.org/10.1007/s11042-017-4383-9
  31. 31.
    Hara, K., Saito, D., and Shouno, H., Analysis of Function of Rectified Linear Unit Used in Deep learning. in International Joint Conference on Neural Networks. IEEE: Killarney, IRELAND. 144–151, 2015Google Scholar
  32. 32.
    Liew, S. S., Khalil-Hani, M., and Bakhteri, R., Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems. Neurocomputing. 216:718–734, 2016.CrossRefGoogle Scholar
  33. 33.
    Jiang, Y. et al., Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling. IEEE Access. 5:16576–16583, 2017.CrossRefGoogle Scholar
  34. 34.
    Hang, S. T., and Aono, M., Bi-linearly weighted fractional max pooling An extension to conventional max pooling for deep convolutional neural network. Multimed. Tools Appl. 76(21):22095–22117, 2017.CrossRefGoogle Scholar
  35. 35.
    Lv, Y.-D., and Sui, Y., Alcoholism detection by data augmentation and convolutional neural network with stochastic pooling. J. Med. Syst. 42(1):Article ID. 2, 2018.CrossRefGoogle Scholar
  36. 36.
    Camps, J. et al., Deep learning for freezing of gait detection in Parkinson's disease patients in their homes using a waist-worn inertial measurement unit. Knowl.-Based Syst. 139:119–131, 2018.CrossRefGoogle Scholar
  37. 37.
    Wawrzynski, P., ASD plus M: Automatic parameter tuning in stochastic optimization and on-line learning. Neural Netw. 96:1–10, 2017.CrossRefPubMedGoogle Scholar
  38. 38.
    Hadgu, A.T., Nigam, A., and Diaz-Aviles, E., Large-Scale Learning with AdaGrad on Spark. in International Conference on Big Data. IEEE: Santa Clara, CA. 2828–2830, 2015Google Scholar
  39. 39.
    Al-Bander, B. et al., Multiscale sequential convolutional neural networks for simultaneous detection of fovea and optic disc. Biomed. Signal Process. Control. 40:91–101, 2018.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of InformaticsUniversity of LeicesterLeicesterUK
  2. 2.Department of Electrical Engineering, The City College of New YorkCUNYNew YorkUSA
  3. 3.West Virginia School of Osteopathic MedicineLewisburgUSA
  4. 4.Department of PsychiatryAffiliated Nanjing Brain Hospital of Nanjing Medical UniversityNanjingPeople’s Republic of China
  5. 5.Department of RadiologyZhong-Da Hospital of Southeast UniversityNanjingChina
  6. 6.Department of RadiologyChildren’s Hospital of Nanjing Medical UniversityNanjingPeople’s Republic of China
  7. 7.Department of NeurologyFirst Affiliated Hospital of Nanjing Medical UniversityNanjingChina

Personalised recommendations