SavedAdd your journal

Journals / Mühendislik Bilimleri ve Araştırmaları Dergisi / 2026 / Cilt: 8 Sayı: 1

Stage Classification of Alzheimer’s Disease MRI Data via Deep Neural Network Architectures

Derin Sinir Ağı Mimarileri ile Alzheimer Hastalığı MR Görüntülerinin Evre Sınıflandırılması

Aslıhan Güven(BALIKESİR ÜNİVERSİTESİ)0009-0001-9263-0215
Abdurrahim Hüseyin Ezirmik(BALIKESİR ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ)0000-0002-1154-1537
Mustafa Furkan Ceylan(BALIKESİR ÜNİVERSİTESİ)0009-0005-5609-395X
Fatih Aydın(BALIKESİR ÜNİVERSİTESİ)0000-0001-9679-0403
Pages
93–103
Publication Date
2026-04-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results show that InceptionV3 delivers the most reliable overall performance across disease stages.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study compares five deep learning architectures for Alzheimer's disease stage classification using structural magnetic resonance imaging (MRI) data.
📊
Key Findings & Data:Accuracy, F1 score, and macro-averaged ROC AUC are used to measure performance on the test set.
💡
Conclusion & Impact:The results show that InceptionV3 delivers the most reliable overall performance across disease stages.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Derin Öğrenme · Transfer Öğrenme · Alzheimer Hastalığı

Abstract

This study compares five deep learning architectures for Alzheimer's disease stage classification using structural magnetic resonance imaging (MRI) data. The experiments are conducted using the OASIS dataset, which comprises brain MRI scans representing multiple clinical stages of Alzheimer’s disease obtained from real-world clinical scenarios. In the preprocessing stage, three-dimensional MRI volumes are transformed into two-dimensional coronal slices for subsequent analysis. Deep learning models are trained and assessed using the same parameters to maintain consistency in comparison. Accuracy, F1 score, and macro-averaged ROC AUC are used to measure performance on the test set. Additionally, computational aspects such as training time and model complexity are taken into consideration. The results show that InceptionV3 delivers the most reliable overall performance across disease stages. MobileNetV2 performs similar test accuracy while requiring much lower computational cost, and it is a practical choice for deployment in resource constrained environments.

Özet

Bu çalışma, yapısal manyetik rezonans görüntüleme (MRI) verileri kullanılarak Alzheimer hastalığının evre sınıflandırması için beş derin öğrenme mimarisini karşılaştırmaktadır. Deneylerde, gerçek hayattaki dört farklı klinik Alzheimer evrelerinden elde edilmiş beyin MRI görüntülerini içeren OASIS veri seti kullanılmıştır. Üç boyutlu MR görüntüleri iki boyutlu koronal dilimlere dönüştürülmüştür. Karşılaştırmada tutarlılığı sağlamak amacıyla tüm modeller aynı parametrelerle eğitilmiştir. Performans değerlendirmesi, test kümesi üzerinde doğruluk, F1 skoru ve makro ortalamalı ROC AUC ölçütleri kullanılarak yapılmıştır. Ayrıca eğitim süresi ve model boyutu gibi hesaplama ile ilgili faktörler de dikkate alınmıştır. Sonuçlar, InceptionV3 modelinin hastalık evreleri genelinde en güvenilir performansı sunduğunu göstermektedir. MobileNetV2 ise benzer test doğruluğu elde ederken çok daha düşük hesaplama kaynağı gerektirmesi sayesinde kaynak kısıtlı ortamlarda dağıtım için pratik bir seçenek olarak öne çıkmaktadır.

🔖

Cite This Article

Güven, A., Ezirmik, A. H., Ceylan, M. F., Aydın, F. (2026). Stage Classification of Alzheimer’s Disease MRI Data via Deep Neural Network Architectures. Mühendislik Bilimleri ve Araştırmaları Dergisi, Cilt: 8 Sayı: 1, 93–103. https://doi.org/10.46387/bjesr.1869200

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (29)

  1. M. Prince, A. Wimo, M. Guerchet, G.-C. Ali, Y.-T. Wu, and M. Prina, “World Alzheimer Report 2015: The Global Impact of Dementia,” Alzheimer’s Disease International, 2015.
  2. World Health Organization, “Global status report on the public health response to dementia,” World Health Organization, Geneva, 2021. Accessed: Jan. 17, 2026. [Online]. Available: https://www.who.int/health-topics/dementia
  3. P. Scheltens et al., “Alzheimer’s disease,” The Lancet, vol. 397, no. 10284, pp. 1577–1590, 2021.
  4. B. Dubois et al., “Preclinical Alzheimer’s disease: Definition, natural history, and diagnostic criteria,” Alzheimer’s & Dementia, vol. 12, no. 3, pp. 292–323, 2016.
  5. C. R. Jack et al., “NIA-AA Research Framework: Toward a biological definition of Alzheimer’s disease,” Alzheimer’s & Dementia, vol. 14, no. 4, pp. 535–562, 2018.
  6. E. Westman, A. Simmons, J. S. Muehlboeck, and C. Tunnard, “AddNeuroMed and ADNI: Similarities and differences in MRI analysis results for Alzheimer’s disease,” Neuroimage, vol. 58, no. 3, pp. 818–828, 2011.
  7. L. Sorensen, M. Nielsen, and A. D. N. Initiative, “Ensemble support vector machine classification of dementia using structural MRI and mini-mental state examination,” J. Neurosci. Methods, vol. 302, pp. 66–74, 2018.
  8. G. Litjens et al., “A survey on deep learning in medical image analysis,” Med. Image Anal., vol. 42, pp. 60–88, 2017.
  9. D. Shen, G. Wu, and H. I. Suk, “Deep learning in medical image analysis,” Annu. Rev. Biomed. Eng., vol. 19, pp. 221–248, 2017.
  10. H.-I. Suk, S.-W. Lee, D. Shen, and A. D. N. I. (ADNI), “Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis,” Neuroimage, vol. 101, pp. 569–582, 2014.
  11. E. E. Bron et al., “Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge,” Neuroimage, vol. 111, pp. 562–579, 2015.
  12. A. Abedalla, M. Abdullah, M. Al-Ayyoub, and E. Benkhelifa, “Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures,” PeerJ Comput. Sci., vol. 7, pp. 1–36, Jun. 2021.
  13. A. Lundervold and A. S. Lundervold, “An overview of deep learning in medical imaging focusing on MRI,” Z. Med. Phys., vol. 29, no. 2, pp. 102–127, 2019.
  14. H. Wen, Y. Li, W. Chen, S. Song, Y. Qiao, and X. Li, “Convolutional Neural Networks for Classification of Alzheimer’s Disease: A Review,” Neurocomputing, vol. 394, pp. 41–53, 2020.
  15. S. Vieira, W. H. L. Pinaya, and A. Mechelli, “Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications,” Neurosci. Biobehav. Rev., vol. 74, pp. 58–75, 2017.
  16. M. B. Narnaware and T. A. Mulla, “Early detection of Multi-Class Alzheimer’s disease using Hybrid capsule auto encoder model,” Biomed. Signal Process. Control, vol. 110, no. 5, p. 108330, Dec. 2025.
  17. S. K. Lakshmanan et al., “Effective deep convolutional neural network with attention mechanism for Alzheimer disease classification,” Frontiers in Radiology, vol. 5, p. 1698760, Jan. 2026.
  18. S. Kumar, S. Shastri, V. Mansotra, and R. Salgotra, “MRI neuroimaging-based Alzheimer’s disease stage classification using deep neural network with convolutional block attention module and GAN-style noise injection,” Scientific Reports 2026 16:1, vol. 16, no. 1, pp. 6946-, Feb. 2026.
  19. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778, 2016.
  20. V. Muralidharan et al., “A scoping review of reporting gaps in FDA-approved AI medical devices,” NPJ Digit. Med., vol. 7, no. 1, p. 273, Dec. 2024.
  21. US Food and Drug Administration, “Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: List of Cleared or Approved Devices,” FDA, 2023. [Online]. Available: https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices
  22. G. B. Frisoni, N. C. Fox, C. R. Jack, P. Scheltens, and P. M. Thompson, “The Clinical Use of Structural MRI in Alzheimer Disease,” Nat. Rev. Neurol., vol. 6, no. 2, pp. 67–77, 2010.
  23. E. Topol, Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Basic Books, 2019.
  24. D. S. Marcus, T. H. Wang, J. Parker, J. G. Csernansky, J. C. Morris, and R. L. Buckner, “Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults,” J. Cogn. Neurosci., vol. 19, no. 9, pp. 1498–1507, Sep. 2007.
  25. C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2016. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/11231
  26. M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proceedings of the 36th International Conference on Machine Learning (ICML), 2019.
  27. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520, 2018.
  28. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, Cham, 2015, pp. 234–241, 2015.
  29. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal Loss for Dense Object Detection,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988, 2017.