Automatic Detection of Alzheimer’s Disease from Magnetic Resonance Images Using a Hybrid Deep Learning Approach

Öz

Alzheimer’s disease is one of the most serious diseases of our age. Early diagnosis is very important in this almost incurable disease. The progress of this disease will be slowed down by early diagnosis. This study goals to identify Alzheimer’s disease based on deep learning from Magnetic Resonance (MR) images. Convolutional Neural Networks (CNN), one of the deep learning algorithms, can automatically extract features from images. In this study, eight different CNN architectures were used to detect Alzheimer’s disease from MR images. NasNetMobile, the most successful of these architectures, was used as an automatic feature extractor, and 1056 features were extracted from its last layer. These features were classified through machine learning algorithms: Deep Neural Network (DNN), Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbor, and Artificial Neural Network (ANN). Although high accuracy was achieved at this stage of the study, the minimum Redundancy Maximum Relevance (mRMR) approach was used for selecting features and robust results. Thus, 1056 features were reduced to 250. As a result, the classification performance of machine learning algorithms improved. The NasNetMobile-mRMR-DNN hybrid algorithm was the most successful in the detection of Alzheimer’s disease with an accuracy rate of 90.68%.

Anahtar Kelimeler

• Alzheimer’s Disease
• Deep Learning
• Machine Learning
• Feature Selection
• Classification.

Alzheimer Hastalığının Manyetik Rezonans Görüntülerden Hibrit Derin Öğrenme Yaklaşımı ile Otomatik Tespiti

Öz

Alzheimer hastalığı, çağın en ciddi hastalıkları arasında yer almaktadır. Tedavisinin neredeyse bulunmadığı bu hastalıkta erken teşhis çok önemlidir. Erken teşhis edilmesi durumunda bu hastalığın ilerlemesi yavaşlayacaktır. Bu çalışmada, Alzheimer hastalığının derin öğrenme aracılığı ile Manyetik Rezonans (MR) görüntüler üzerinden tespit edilmesi amaçlanmıştır. Derin öğrenme algoritmalarından olan Evrişimli Sinir Ağları (ESA), görüntülerden otomatik özellik çıkarabilme yeteneğine sahiptir. Bu çalışmada, Alzheimer hastalığını MR görüntülerinden tespit etmede sekiz farklı ESA mimarisi kullanılmıştır. Bu mimarilerden en başarılı test sonucu veren NasNetMobile, otomatik özellik çıkarıcı olarak kullanılmış ve son katmanından 1056 özellik elde edilmiştir. Bu özellikler makine öğrenme algoritmalarından Derin Sinir Ağı (DSA), Destek Vektör Makinesi (DVM), Karar Ağacı, K-En Yakın Komşu, Yapay Sinir Ağı (YSA) ile sınıflandırılmıştır. Çalışmanın bu aşamasında yüksek doğruluk oranı elde edilse de sağlam sonuçlar için özellik seçim yöntemlerinden minimum Artıklık Maksimum İlişki (mRMR) yaklaşımından yararlanılmıştır. Böylece 1056 özellik 250’ye indirgenmiştir. Sonuç olarak, makine öğrenme algoritmalarının sınıflandırma performansı artmıştır. Alzheimer hastalığının tespitinde %90,68’lik doğruluk oranı ile en başarılı sonuç veren NasNetMobile-mRMR-DSA hibrit algoritması olmuştur.

Anahtar Kelimeler

• Alzheimer Hastalığı
• Derin Öğrenme
• Makine Öğrenmesi
• Özellik Seçimi
• Sınıflandırma

Kaynakça

1. Aydın S, Taşyürek M, Öztürk C. MR Görüntüleri Ön İşlenerek Derin Ağlar ile Alzheimer Hastalık Tespiti. In: International Conference On Emerging Sources In Science, 2022.
2. Brun A, Liu X, Erikson C. Synapse loss and gliosis in the molecular layer of the cerebral cortex in Alzheimer’s disease and in frontal lobe degeneration. Neurodegeneration 1995; 4(2): 171-177.
3. Wang S, Kong X, Chen Z, Wang G, Zhang J, Wang J. Role of Natural Compounds and Target Enzymes in the Treatment of Alzheimer’s Disease. Molecules 2022; 27(13): 4175.
4. Noetzli M, Eap CB. Pharmacodynamic, pharmacokinetic and pharmacogenetic aspects of drugs used in the treatment of Alzheimer’s disease. Clin Pharmacokinet 2013; 52(4): 225-241.
5. Armstrong RA. What causes Alzheimer’s disease?. Folia Neuropathol 2013; 51(3): 169-188.
6. Gaugler J, James TB, Reimer J, Weuve J. Alzheimer’s Association. 2021 Alzheimer’s Disease Facts and Figures. Alzheimers Dement 2021; 17: Chicago, IL, USA.
7. Subasi A, Subasi TN, Ozaltin O. Artificial intelligence in diagnosis of neural disorders using biosignals and imaging. In: Advances in Artificial Intelligence: Elsevier, 2024; 523-560.
8. Bagcı U, Bai L. Manyetik Rezonans Beyin Imgelerinden Alzheimer Hastalığı Tanısında Gabor Dalgacıkları Kullanımı Detecting Alzheimer Disease in Magnetic Resonance Brain Images Using Gabor Wavelets.

9. Yin C, Li S, Zhao W, Feng J. Brain imaging of mild cognitive impairment and Alzheimer’s disease. Neural Regen Res 2013; 8(5): 435-444.
10. Öziç MÜ, Özşen S. 3B Alzheimer MR Görüntülerinin Hacimsel Kayıp Bölgelerindeki Voksel Değerleri Kullanılarak Sınıflandırılması. El-Cezerî J Sci Eng 2020; 7(3): 1152-1166.
11. Türk Ö. MR Görüntülerinden Alzheimer Tespitinde Boyut Azaltma ve Derin Öğrenme Yaklaşımlarının Karşılaştırılması. Dicle Univ J Eng 2022; 13(3): 485-491.
12. Aslan Z. EEG Sinyallerini Kullanarak Alzheimer Hastalığının Otomatik Tespiti İçin Bilgisayar Destekli Tanı Sistemi. Dicle Univ J Eng 2022; 13(2): 213-220.
13. Karabay GS, Çavaş M. Derin Öğrenme Yöntemiyle Alzheimer Hastalığının Tespiti. Fırat Univ J Eng Sci 2022; 34(2): 879-887.
14. Özkaya A, Cebeci U. A Model Suggestion For Alzheimer’s Disease Diagnosis By Using Deep Learning. Eur J Sci Technol 2022; (37): 123-130.
15. Sadık EŞ. Comparison Of Machine Learning Algorithms In The Detection Of Alzheimer’s Disease. Eur J Sci Technol 2022; (42): 1-5.
16. Karakaya F, Gurkan C, Budak A, Karataş H. Classification and Segmentation of Alzheimer Disease in MRI Modality using the Deep Convolutional Neural Networks. Eur J Sci Technol 2022; (40): 99-105.
17. Eren HA, Okyay S, Adar N. Adoken: MR İçin Derin Öğrenme Tabanlı Karar Destek Yazılımı. J Eng Sci Design 2021; 9(2): 406-413.
18. Okyay S. Beyin Görüntüleme Tekniklerinin Alzheimer Hastalığı Erken Tanı Tahmininde Kullanılması. Anadolu Univ, 2016.
19. Sertkaya ME, Ergen B. Alzheimer Hastalığının Erken Teşhisinin Çoklu Değişken Kullanarak Tespiti. Eur J Sci Technol 2022; (35): 306-314.
20. Bhardwaj S, Kaushik T, Bisht M, Gupta P, Mundra S. Detection of Alzheimer Disease Using Machine Learning. In: Smart Systems: Innovations in Computing: Springer, 2022; 443-450.
21. Mathew NA, Vivek R, Anurenjan P. Early diagnosis of Alzheimer’s disease from MRI images using PNN. In: 2018 Int CET Conf Control Commun Comput:IEEE, 2018; 161-164.
22. Shanmugam JV, Duraisamy B, Simon BC, Bhaskaran P. Alzheimer’s disease classification using pre-trained deep networks. Biomed Signal Process Control 2022; 71: 103217.
23. Loddo A, Buttau S, Di Ruberto C. Deep learning based pipelines for Alzheimer’s disease diagnosis: a comparative study and a novel deep-ensemble method. Comput Biol Med 2022; 141: 105032.
24. Helaly HA, Badawy M, Haikal AY. Deep learning approach for early detection of Alzheimer’s disease. Cogn Comput 2022; 14(5): 1711-1727.
25. Arslan NN, Ozdemir D. Analysis of CNN models in classifying Alzheimer’s stages: comparison and explainability examination of the proposed separable convolution-based neural network and transfer learning models. Signal Image Video Process 2024; 1-15.
26. Tüzün BN, Özdemir D. Classification of Brain Tumors With Deep Learning Models. J Sci Rep-A 2023; (054): 296-306.
27. Dörterler S, Dumlu H, Özdemir D, Temurtaş H. Hybridization of Meta-heuristic Algorithms with K-Means for Clustering Analysis: Case of Medical Datasets. Gazi J Eng Sci 2024; 10(1).
28. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neur Inf Proc Syst 2012; 25: 1097-1105.
29. Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proc AAAI Conf Art Intell 2017; 31(1).
30. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc IEEE Conf Comp Vis Pat Rec 2016; 770-778.
31. Peng S, Huang H, Chen W, Zhang L, Fang W. More trainable inception-ResNet for face recognition. Neurocomputing 2020; 411: 9-19.
32. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proc IEEE Conf Comp Vis Pat Rec 2016; 2818-2826.
33. Szegedy C ve diğerleri. Going deeper with convolutions. In: Proc IEEE Conf Comp Vis Pat Rec 2015; 1-9.
34. Zoph B, Vasudevan V, Shlens J, Le QV. Learning transferable architectures for scalable image recognition. In: Proc IEEE Conf Comp Vis Pat Rec 2018; 8697-8710.
35. Addagarla SK, Chakravarthi GK, Anitha P. Real time multi-scale facial mask detection and classification using deep transfer learning techniques. Int J 2020; 9(4): 4402-4408.
36. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360, 2016.
37. Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proc IEEE Conf Comp Vis Pat Rec 2017; 1251-1258.
38. Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995; 20(3): 273-297.
39. Jiang H. Machine Learning Fundamentals: A Concise Introduction. Cambridge Univ Press
40. Quinlan JR. C4. 5: Programs for Machine Learning. Elsevier, 2014.
41. Subasi A, Balfaqih M, Balfagih Z, Alfawwaz K. A Comparative Evaluation of Ensemble Classifiers for Malicious Webpage Detection. Procedia Computer Science 2021; 194: 272-279.
42. Albayrak AS, Yilmaz SK. Veri Madenciliği: Karar Ağacı Algoritmaları ve İMKB Verileri Üzerine Bir Uygulama. Suleyman Demirel Univ J Fac Econ Adm Sci 2009; 14(1).
43. Özaltın Ö. Biyomedikal Görüntülerin Sınıflandırılması İçin Yeni Bir Evrişimli Sinir Ağı Mimarisi. Doktora Tezi, Hacettepe Üniversitesi, Ankara, 2023.
44. Keller JM, Gray MR, Givens JA. A fuzzy k-nearest neighbor algorithm. IEEE Trans Syst Man Cybern 1985; (4): 580-585.
45. Cover T, Hart P. Nearest neighbor pattern classification. IEEE Trans Inf Theory 1967; 13(1): 21-27.
46. McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 1943; 5: 115-133.
47. Dolatabadi M, Zakariazadeh A, Borghetti A, Siano P. Distributed energy and reserve scheduling in local energy communities using L-BFGS optimization. CSEE J Power Energy Syst 2024.
48. Eroglu Y, Yildirim M, Cinar A. mRMR‐based hybrid convolutional neural network model for classification of Alzheimer’s disease on brain magnetic resonance images. Int J Imaging Syst Technol 2022; 32(2): 517-527.
49. Ozaltin O, Coskun O, Yeniay O, Subasi A. A deep learning approach for detecting stroke from brain CT images using OzNet. Bioengineering 2022; 9(12): 783.
50. Li BQ, Zheng LL, Feng KY, Hu LL, Huang GH, Chen L. Prediction of linear B-cell epitopes with mRMR feature selection and analysis. Curr Bioinform 2016; 11(1): 22-31.
51. Girgin ABA, Şahin S. Improving the Performance of Sentiment Analysis by Ensemble Hybrid Learning Algorithm With NLP And Cascaded Feature Extraction. Int J Adv Eng Pure Sci 2023; 35(1): 125-141.
52. Narin A. Detection of Focal and Non-focal Epileptic Seizure Using Continuous Wavelet Transform-Based Scalogram Images and Pre-trained Deep Neural Networks. IRBM 2020.
53. Xu X, Liu H. ECG heartbeat classification using convolutional neural networks. IEEE Access 2020; 8: 8614-8619.
54. Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006; 27(8): 861-874.
55. Başer BÖ, Yangın M, Sarıdaş ES. Makine öğrenmesi teknikleriyle diyabet hastalığının sınıflandırılması. Süleyman Demirel Univ J Sci Inst 2021; 25(1): 112-120.
56. Sertkaya ME, Ergen B. Alzheimer Hastalığının Teşhisinde Görüntü Dönüştürücü (Vision Transformer) Yaklaşımı: Yenilikçi Bir İnceleme. Fırat Univ J Eng Sci 2024; 36(2): 609-619.
57. Toshkhujaev S, Lee KH, Choi KY, Lee JJ, Kwon GR, Gupta Y, Lama RK. Classification of Alzheimer’s disease and mild cognitive impairment based on cortical and subcortical features from MRI T1 brain images utilizing four different types of datasets. J Healthc Eng 2020; 2020(1): 3743171.
58. Suganthe R, Geetha M, Sreekanth G, Gowtham K, Deepakkumar S, Elango R. Multiclass classification of Alzheimer’s disease using hybrid deep convolutional neural network. NVEO Nat Volat Essent Oils J 2021; 145-153.
59. Oh K, Chung YC, Kim KW, Kim WS, Oh IS. Classification and visualization of Alzheimer’s disease using volumetric convolutional neural network and transfer learning. Sci Rep 2019; 9(1): 18150.