KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Enhancing Alzheimer's Disease Classification using 3D Convolutional Neural Network and Multilayer Perceptron Model with Attention Network

  • Enoch A. Frimpong (School of Information and Software Engineering, University of Electronic Science and Technology of China) ;
  • Zhiguang Qin (School of Information and Software Engineering, University of Electronic Science and Technology of China) ;
  • Regina E. Turkson (Department of Computer Science and Information Technology, University of Cape Coast, PMB University Post Office) ;
  • Bernard M. Cobbinah (School of Computer Science and Engineering, University of Electronic Science and Technology of China) ;
  • Edward Y. Baagyere (Department of Computer Science, C. K. Tedam University of Technology and Applied Sciences) ;
  • Edwin K. Tenagyei (School of Engineering and Built Environment, Griffith University)
  • Received : 2023.01.25
  • Accepted : 2023.10.18
  • Published : 2023.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Alzheimer's disease (AD) is a neurological condition that is recognized as one of the primary causes of memory loss. AD currently has no cure. Therefore, the need to develop an efficient model with high precision for timely detection of the disease is very essential. When AD is detected early, treatment would be most likely successful. The most often utilized indicators for AD identification are the Mini-mental state examination (MMSE), and the clinical dementia. However, the use of these indicators as ground truth marking could be imprecise for AD detection. Researchers have proposed several computer-aided frameworks and lately, the supervised model is mostly used. In this study, we propose a novel 3D Convolutional Neural Network Multilayer Perceptron (3D CNN-MLP) based model for AD classification. The model uses Attention Mechanism to automatically extract relevant features from Magnetic Resonance Images (MRI) to generate probability maps which serves as input for the MLP classifier. Three MRI scan categories were considered, thus AD dementia patients, Mild Cognitive Impairment patients (MCI), and Normal Control (NC) or healthy patients. The performance of the model is assessed by comparing basic CNN, VGG16, DenseNet models, and other state of the art works. The models were adjusted to fit the 3D images before the comparison was done. Our model exhibited excellent classification performance, with an accuracy of 91.27% for AD and NC, 80.85% for MCI and NC, and 87.34% for AD and MCI.

Keywords

Acknowledgement

This paper is supported by the National Natural Science Foundation of China, major instrument project number: 62027827; Name: Development of a multimodal auxiliary diagnostic equipment for fetal heart sound-cardiac-ultrasound; Date: 2021.01-2025.12.

References

  1. F. Ammarah, S. M. Anwar, M. Awais, and S. Rehman, "A deep CNN based multi-class classification of Alzheimer's disease using MRI," in Proc. of IEEE International Conference on Imaging systems and techniques (IST), pp. 1-6, 2017.
  2. B. Ron, E. Johnson, K. Ziegler-Graham, and H. M. Arrighi, "Forecasting the global burden of Alzheimer's disease," Alzheimer's & dementia, vol. 3, no. 3, pp. 186-191, 1 July 2007. https://doi.org/10.1016/j.jalz.2007.04.381
  3. S. J. Dennis, and J. Hardy, "The amyloid hypothesis of Alzheimer's disease at 25 years," EMBO molecular medicine, vol. 8, no. 6, pp.595-608, Jun 2016. https://doi.org/10.15252/emmm.201606210
  4. Alzheimer Association, "Alzheimer's disease facts and figures," Alzheimer's & Dementia, pp.327-406, 2021.
  5. F. P. Cleusa, M. Prince, C. Brayne, H. Brodaty, L. Fratiglioni, M. Ganguli, K. Hall, "Global prevalence of dementia: a Delphi consensus study," The lancet, vol. 366, no. 9503, pp.2112-2117, 17 Dec 2005. https://doi.org/10.1016/S0140-6736(05)67889-0
  6. Osmosis. Alzheimer's disease - plaques, tangles, causes, symptoms & pathology [Video]. YouTube. (2016, March 22). [Online]. Available: https://www.youtube.com/watch?v=v5gdH_Hydes&t=31s 
  7. S. Monika, S. Ahuja, S. Rani, D. Koundal, A. Zaguia, and W. Enbeyle, "An Exploration: Alzheimer's Disease Classification Based on Convolutional Neural Network," BioMed Research International, Jan 2022.
  8. G. Emilie, G. Chetelat, M. Chupin, R. Cuingnet, B. Desgranges, H. Kim, M. Niethammer, "Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging," Neuroimage, vol. 47, no. 4, pp.1476-1486, 1 Oct 2009. https://doi.org/10.1016/j.neuroimage.2009.05.036
  9. K. Stefan, C. M. Stonnington, C. Chu, B. Draganski, R. I. Scahill, J. D. Rohrer, N. C. Fox, C. R. Jack Jr, J. Ashburner, and R. S. J. Frackowiak, "Automatic classification of MR scans in Alzheimer's disease," Brain, vol. 131, no. 3, pp.681-689, 1 March 2008. https://doi.org/10.1093/brain/awm319
  10. F. Montenegro, J. Manuel, B. Villarini, A. Angelopoulou, E. Kapetanios, J. Garcia-Rodriguez, and V. Argyriou, "A survey of alzheimer's disease early diagnosis methods for cognitive assessment," Sensors, vol 20, no. 24, p.7292, 18 Dec 2020.
  11. E. M. Amir, S. Luo, and R. Chiong, "Deep learning to detect Alzheimer's disease from neuroimaging: A systematic literature review," Computer methods and programs in biomedicine, vol. 187, p.105242, 1 April 2020.
  12. L. P. Jason, J. Pruessner, A. P. Zijdenbos, D. L. Collins, S. J. Teipel, H. Hampel, and A. C. Evans, "Automated cortical thickness measurements from MRI can accurately separate Alzheimer's patients from normal elderly controls," Neurobiology of aging, vol. 29, no. 1, pp.23-30, 1 Jan2008.
  13. S. Alessia, A. Cerasa, and A. Quattrone, "Random forest algorithm for the classification of neuroimaging data in Alzheimer's disease: a systematic review," Frontiers in aging neuroscience, vol. 9, p.329, 6 Oct 2017.
  14. L. Manhua, D. Cheng, K. Wang, and Y. Wang, "Multi-modality cascaded convolutional neural networks for Alzheimer's disease diagnosis," Neuroinformatics, vol. 16, no. 3, pp.295-308, Oct 2018. https://doi.org/10.1007/s12021-018-9370-4
  15. I. Jyoti, and Y. Zhang, "Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks," Brain informatics, vol. 5, no. 2, pp. 1-14, Dec 2018. https://doi.org/10.1186/s40708-018-0080-3
  16. I. Jyoti, and Y. Zhang, "An ensemble of deep convolutional neural networks for Alzheimer's disease detection and classification," in Proc. of NIPS 2017 Workshop on Machine Learning for Health, 2 Dec 2017.
  17. M. R. Krishn, S. Urolagin, J. A. A. Jothi, A. S. Neogi, and N. Nawaz, "Deep learning-based sentiment analysis and topic modeling on tourism during Covid-19 pandemic," Frontiers in Computer Science, vol. 3, p.775368, 5 Nov 2021.
  18. I. Jyoti, and Y. Zhang, "A novel deep learning based multi-class classification method for Alzheimer's disease detection using brain MRI data," in Proc. of International conference on brain informatics, Springer, Cham, pp. 213-222, 16 Nov 2017.
  19. H. Ehsan, R. Keynton, and A. El-Baz, "Alzheimer's disease diagnostics by adaptation of 3D convolutional network," in Proc. of IEEE international conference on image processing (ICIP), IEEE, pp. 126-130, 25 Sep 2016.
  20. F. Feng, P. Wang, K. Zhao, B. Zhou, H. Yao, Q. Meng, L. Wang, "Radiomic features of hippocampal subregions in Alzheimer's disease and amnestic mild cognitive impairment," Frontiers in aging neuroscience, vol. 10, p. 290, 25 Sep 2018.
  21. I. Arevalo-Rodriguez, N. Smailagic, M. i Figuls, A. Ciapponi, E. Sanchez-Perez, A. Giannakou, O. Pedraza, X. Bonfill Cosp, S. Cullum, "Mini-Mental State Examination (MMSE) for the detection of Alzheimer's disease and other dementias in people with mild cognitive impairment (MCI)," Cochrane database of systematic reviews, vol. 3, 2015.
  22. F. J. Huff, F. Boller, F. Lucchelli, R. Querriera, J. Beyer, S. Belle, "The neurologic examination in patients with probable Alzheimer's disease," Archives of Neurology, vol. 9, no. 44, pp. 929-932, 1987. https://doi.org/10.1001/archneur.1987.00520210031015
  23. Mayo Clinic Staff. Learn How Alzheimer's Is Diagnosed. [Online]. Available: https://www.mayoclinic.org/diseasesconditions/alzheimers-disease/in-depth/alzheimers/art20048075 2019 
  24. C. Ledig, A. Schuh, R. Guerrero, R. A. Heckemann, D. Rueckert, "Structural brain imaging in Alzheimer's disease and mild cognitive impairment: biomarker analysis and shared morphometry database," Scientific reports, vol. 1, no. 8, p.11258, 2018.
  25. Y. Huang, J. Xu, Y. Zhou, T. Tong, X. Zhuang, & Alzheimer's Disease Neuroimaging Initiative (ADNI), "Diagnosis of Alzheimer's disease via multi-modality 3D convolutional neural network," Frontiers in neuroscience, vol. 13, p. 509, 2019.
  26. G. Liang, X. Xing, L. Liu, Y. Zhang, Q. Ying, A. Lin, N. Jacobs, "Alzheimer's disease classification using 2d convolutional neural networks," in Proc. of 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 3008-3012, 2021.
  27. K. Gunawardena, R. Rajapakse, N. Kodikara, "Applying convolutional neural networks for predetection of alzheimer's disease from structural MRI data," in Proc. of 24th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), pp. 1-7, November 2017.
  28. K. Aderghal, M. Boissenin, J. Benois-Pineau, G. Catheline, K. Afdel, "Classification of sMRI for AD Diagnosis with Convolutional Neuronal Networks: A Pilot 2-D+ Study on ADNI," in Proc. of MultiMedia Modeling: 23rd International Conference, MMM 2017, Proceedings, Part I, pp. 690-701, 2017.
  29. S. Luo, X. Li, and J. Li, "Automatic Alzheimer's disease recognition from MRI data using deep learning method," Journal of Applied Mathematics and Physics, vol. 5, no. 9, pp. 1892-1898, 2017. https://doi.org/10.4236/jamp.2017.59159
  30. S.-H. Wang, P. Phillips, Y. Sui, B. Liu, M. Yang, and H. Cheng, "Classification of Alzheimer's disease based on eight-layer convolutional neural network with leaky rectified linear unit and max pooling," Journal of Medical Systems, vol. 42, no. 5, p. 85, 2018.
  31. M. Liu, D. Cheng, W. Yan, & Alzheimer's Disease Neuroimaging Initiative, "Classification of Alzheimer's disease by combination of convolutional and recurrent neural networks using FDGPET images," Frontiers in neuroinformatics, vol. 12, p. 35, 2018.
  32. E. G. Marwa, H. Moustafa, F. Khalifa, H. Khater, E. AbdElhalim, "An MRI-based deep learning approach for accurate detection of Alzheimer's disease," Alexandria Engineering Journal, vol. 63, pp. 211-221, 2023. https://doi.org/10.1016/j.aej.2022.07.062
  33. X. Zhang, L. Han, W. Zhu, L. Sun, D. Zhang, "An explainable 3D residual self-attention deep neural network for joint atrophy localization and Alzheimer's disease diagnosis using structural MRI," IEEE journal of biomedical and health informatics, vol. 11, no. 26, pp. 5289-5297, 2022.  https://doi.org/10.1109/JBHI.2021.3066832
  34. A. Ardekani, A. Bachman, "Model-based automatic detection of the anterior and posterior commissures on MRI scans," Neuroimage, vol. 46, no. 3, pp. 677-682, 1 Jul 2009. https://doi.org/10.1016/j.neuroimage.2009.02.030
  35. J. Mark, P. Bannister, M. Brady, and S. Smith, "Improved optimization for the robust and accurate linear registration and motion correction of brain images," Neuroimage, vol. 17, no. 2, pp.825-841, 1 Oct 2002. https://doi.org/10.1006/nimg.2002.1132
  36. L. Christian, R. Wolz, P. Aljabar, J. Lotjonen, R. A. Heckemann, A. Hammers, D. Rueckert, "Multi-class brain segmentation using atlas propagation and EM-based refinement," in Proc. of 9th IEEE International Symposium on Biomedical Imaging (ISBI), pp.896-899, 2 May 2012.
  37. K. Zhaokai, M. Zhang, W. Zhu, Y. Yi, T. Wang, and B. Zhang, "Multi-modal data Alzheimer's disease detection based on 3D convolution," Biomedical Signal Processing and Control, vol. 75, p.103565, 1 May 2022.
  38. S.R. Braulio, R. Villalon-Fonseca, and G. Marin-Raventos, "Alzheimer's disease early detection using a low cost three-dimensional densenet-121 architecture," in Proc. of International conference on smart homes and health telematics, pp. 3-15, 2020.
  39. J. R. Clifford, M. A. Bernstein, N. C. Fox, P. Thompson, G. Alexander, D. Harvey, B. Borowski, "The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods," Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, vol. 27, no. 4, pp.685-691, Apr 2008. https://doi.org/10.1002/jmri.21049
  40. Y. Zhao, B. Ma, P. Jiang, D. Zeng, X. Wang, S. Li, "Prediction of Alzheimer's disease progression with multi-information generative adversarial network," IEEE Journal of Biomedical and Health Informatics, vol. 3, no. 25, pp. 711-719, 2020. https://doi.org/10.1109/JBHI.2020.3006925
  41. X. Bi, X. Zhao, H. Huang, D. Chen, Y. Ma, "Functional brain network classification for Alzheimer's disease detection with deep features and extreme learning machine," Cognitive Computation, vol. 12, pp. 513-527, 2020. https://doi.org/10.1007/s12559-019-09688-2
  42. C. Lian, M. Liu, J. Zhang, D. Shen, "Hierarchical fully convolutional network for joint atrophy localization and Alzheimer's disease diagnosis using structural MRI," IEEE transactions on pattern analysis and machine intelligence, vol. 4, no. 42, pp. 880-893, 2020.  https://doi.org/10.1109/TPAMI.2018.2889096