4B fMRI Tabanlı Alzheimer Hastalığının Ön Tespiti için 3B-CAPSNET ve RNN Modellerinin Kullanılması

Abstract

Alzheimer hastalığının (AH) ilerlemesinin erken tahmini, bilişsel gerilemenin daha etkili bir şekilde yavaşlatılmasına yardımcı olabilmektedir. Dinlenme durumu fonksiyonel manyetik rezonans görüntüleme (dd-fMRG) kullanılarak otomatik AH tanısı için evrişimli sinir ağlarına (ESA) dayalı farklı yöntemlerin uygulanmasına yönelik çeşitli çalışmalar yapılmıştır. Bu çalışmalarda tanıtılan yöntemler iki büyük zorlukla karşılaşmaktadır. Birincisi, fMRG veri kümeleri küçük boyutta olduğundan aşırı uyum gözlemlenebilmektedir. İkincisi, fMRG oturumlarının 4 boyutlu (4B) bilgilerinin verimli bir şekilde modellenmesi gerekmektedir. Çalışmalardan bazıları, derin öğrenme yöntemlerini, 4B bilgiyi modellemek için fMRG verilerinden oluşturulan fonksiyonel bağlantı matrislerine veya ayrı 2B dilimler veya 3B hacimler olarak fMRG verilerine uygulamıştır. Ancak bu durumun her iki yöntem türünde de bilgi kaybına neden olduğu gözlemlenmiştir. Bu çalışmada, AD tanısı için fMRG verilerinin uzay-zamansal (4B) bilgilerini modellemek amacıyla Kapsül ağı (CapsNet) ve tekrarlayan sinir ağını (RNN) temel alan yeni bir model önerilmektedir. Önerilen modelin etkinliğini değerlendirmek için deneyler yapılmıştır. Sonuçlara göre, önerilen modelin AH’na karşı normal kontrol (NK) ve geç hafif bilişsel bozukluk (GHBB) ile erken hafif bilişsel bozukluk (EHBB) sınıflandırma görevlerinde sırasıyla %94.5 ve %61.8 doğruluk elde edebildiği görülmüştür.

Keywords

• Alzheimer hastalığı tespiti
• makine öğrenmesi
• manyetik rezonans görüntüleme
• evrişimli sinir ağları
• yinelemeli sinir ağı

Use of 3D-CAPSNET and RNN models for 4D fMRI-based Alzheimer’s Disease Pre-detection

Abstract

Predicting Alzheimer's disease (AD) at an early stage can assist more successfully prevent cognitive decline. Numerous investigations have focused on utilizing various convolutional neural network (CNN)-based techniques for automated diagnosis of AD through resting-state functional magnetic resonance imaging (rs-fMRI). Two main constraints face the methodologies presented in these studies. First, overfitting occurs due to the small size of fMRI datasets. Second, an effective modeling of the 4D information from fMRI sessions is required. In order to represent the 4D information, some studies used the deep learning techniques on functional connectivity matrices created from fMRI data, or on fMRI data as distinct 2D slices or 3D volumes. However, this results in information loss in both types of methods. In order to model the spatiotemporal (4D) information of fMRI data for AD diagnosis, a new model based on the capsule network (CapsNet) and recurrent neural network (RNN) is proposed in this study. To assess the suggested model's effectiveness, experiments were run. The findings show that the suggested model could classify AD against normal control (NC) and late mild cognitive impairment (lMCI) against early mild cognitive impairment (eMCI) with accuracy rates of 94.5% and 61.8%, respectively.

Keywords

• Alzheimer’s disease detection
• machine learning
• magnetic resonance imaging
• convolutional neural network
• recurrent neural network
• capsule network

References

1. Alzheimer’s Association Report. 2017 Alzheimer's disease facts and figures. Alzheimer’s & Dementia 2017; 13(4): 325-373.
2. Haux R. Health information systems - past, present, future. Int J Med Inform 2006; 75(3-4): 268-281.
3. Janghel RR, Rathore YK. Deep convolution neural network based system for early diagnosis of alzheimer’s disease. IRBM 2021; 42(4): 258-267.
4. Ebrahimighahnavieh MA, Luo S, Chiong R. Deep learning to detect Alzheimer’s disease from neuroimaging: a systematic literature review. Computer Methods and Programs in Biomedicine 2020; 187: 105242.
5. Kivistö J, Soininen H, Pihlajamaki M. Functional MRI in Alzheimer’s Disease. Advanced Brain Neuroimaging Topics in Health and Disease - Methods and Applications. InTech; 2014.
6. Jie B, Liu M, Shen D. Integration of temporal and spatial properties of dynamic connectivity networks for automatic diagnosis of brain disease. Med Image Anal 2018; 47:81-94.
7. Parmar H, Nutter B, Long R, Antani S, Mitra S. Spatiotemporal feature extraction and classification of alzheimer’s disease using deep learning 3D-CNN for fMRI data. Journal of Medical Imaging 2020; 7(5): 056001.
8. Jie B, Zhang D, Wee CY, Shen D. Topological graph kernel on multiple thresholded functional connectivity networks for mild cognitive impairment classification. Hum Brain Mapp 2014; 35(7):2876-2897.

9. Bi XA, Shu Q, Sun Q, Xu Q. Random support vector machine cluster analysis of resting-state fMRI in alzheimer’s disease. PLoS One 2018; 13(3): e0194479.
10. He Y, Wu J, Zhou L, Chen Y, Li F, Qian H. Quantification of cognitive function in alzheimer’s disease based on deep learning. Front Neurosci 2021; 15: 651920.
11. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv 2017; 1704.04861.
12. Duc NT, Ryu S, Qureshi MNI, Choi M, Lee KH, Lee B. 3D-deep learning based automatic diagnosis of alzheimer’s disease with joint mmse prediction using resting-state fMRI. Neuroinformatics 2020; 18(1), 71-86.
13. Chan TH, Jia K, Gao S, Lu J, Zeng Z, Ma Y. PCANet: a simple deep learning baseline for ımage classification? IEEE Transactions on Image Processing 2015; 24(12): 5017-5032.
14. Wang Y, Liu X, Yu C. Assisted diagnosis of alzheimer’s disease based on deep learning and multimodal feature fusion. Complexity 2021; 2021: 6626728.
15. Lin K, Jie P, Dong P, Ding X, Bian W, Liu M. Convolutional recurrent neural network for dynamic functional mrı analysis and brain disease ıdentification. Front Neurosci 2022; 16: 933660.
16. Jiang L, Zuo XN. Regional homogeneity: a multimodal, multiscale neuroimaging marker of the human connectome. Neuroscientist 2016; 22(5): 486-505.
17. Jia H, Lao H. Deep learning and multimodal feature fusion for the aided diagnosis of alzheimer’s disease. Neural Comput Appl 2022; 34(22): 19585-19598.
18. Mirakhorli J, Amindavar H, Mirakhorli M. A new method to predict anomaly in brain network based on graph deep learning. Rev Neurosci 2020; 31(6): 681-689.
19. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. ArXiv 2014; 1406.2661.
20. Ghafoori S, Shalbaf A. Predicting conversion from MCI to AD by integration of rs-fMRI and clinical information using 3D-convolutional neural network. Int J Comput Assist Radiol Surg 2022; 17(7): 1245-1255.
21. Wang M, Lian C, Yao D, Zhang D, Liu M, Shen D. Spatial-temporal dependency modeling and network hub detection for functional MRI analysis via convolutional-recurrent network. IEEE Trans Biomed Eng 2020; 67(8): 2241-2252.
22. Li W, Lin X, Chen X. Detecting alzheimer’s disease based on 4D fMRI: an exploration under deep learning framework. Neurocomputing 2020; 388: 280-287.
23. Sabour S, Frosst N, Hinton GE. Dynamic routing between capsules. In: Proceedings of the 31st International Conference on Neural Information Processing Systems; 4-9 December 2017; Long Beach, California, USA: Curran Associates Inc. pp. 3859–3869.
24. Schmidt RM, Recurrent neural networks (RNNs): a gentle introduction and overview. ArXiv 2019; 1912.05911.
25. Mueller SG, Weiner MW, Thal LJ, Petersen RC, Jack CR, Jagust W, Trojanowski JQ, Toga AW, et al. Ways toward an early diagnosis in alzheimer's disease: the alzheimer's disease neuroimaging ınitiative (ADNI). Alzheimers Dement. 2005; 1(1): 55-66.
26. The FIL Methods Group and honorary members, SPM12 Manual. Functional Imaging Laboratory, Institute of Neurology, UCL, 2015, http://www.fil.ion.ucl.ac.uk/spm/doc/manual.pdf.
27. Afshar P, Mohammadi A, Plataniotis KN. Brain tumor type classification via capsule networks. In: 25th IEEE International Conference on Image Processing (ICIP): 07-10 October 2018; Athens, Greece: IEEE. pp. 2381-8549.
28. Goceri E. Analysis of capsule networks for image classification. In: International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing: IADIS. pp. 53-60.