ADNet: A CNN MODEL FOR ALZHEIMER'S DISEASE DIAGNOSIS ON OASIS-1 DATASET

Ahmet Samed Saraçoğlu; Ayse Merve Acılar; Özlem Erdaş Çiçek

doi:10.17780/ksujes.1534327

TR EN

ADNet: OASIS-1 VERİ KÜMESİ ÜZERİNDE ALZHEİMER HASTALIĞI TEŞHİSİ İÇİN BİR CNN MODELİ

Öz

Alzheimer hastalığı (AD), hafıza, düşünme ve davranış üzerinde ciddi etkileri olan kronik bir nörodejeneratif hastalıktır. Evrişimli Sinir Ağları (CNN) gibi derin öğrenme modelleri, beyin manyetik rezonans görüntüleri (MRI) kullanılarak AD'nin erken aşamalarda tespit edilmesinde umut verici sonuçlar göstermektedir. Bu çalışmada, Alzheimer teşhisi için OASIS-1 veri seti kullanılarak eğitilen ADNet adlı bir CNN modeli önerilmiştir. ADNet'in performansını değerlendirmek için, ilk olarak, her bireyin MR görüntüsünden alınan sagittal düzlemdeki 128 dilimin ilk çeyreğinden, ortasından ve üçüncü çeyreğinden alınan dilimler kullanılarak üç farklı veri seti hazırlanmış ve en bilgilendirici dilim hangisi araştırılmıştır. Her veri seti %80 eğitim ve %20 test olarak ayrılmış ve ilk çeyrek dilimin en iyi performansı gösterdiği saptanmıştır. Ek olarak, elde edilen modelin transfer öğrenme modeli olarak kullanılıp kullanılamayacağı incelenmiştir. Bunun için düşük performanslı bir model, ADNet transfer öğrenme modeli kullanılarak yeniden eğitilmiş ve sonuçların oldukça iyileştiği gözlemlenmiştir. Son olarak, modelin dayanıklılığı 5 katlı çapraz doğrulama ile üç kez tekrarlanarak daha ayrıntılı bir değerlendirmeye tabi tutulmuş ve %95,36 ortalama doğruluk elde edilmiştir. Sonuç olarak, ADNet’in klinik ortamlarda Alzheimer taramasında kullanılabileceği ve hastaların daha erken tedavi almasını sağlayabileceği düşünülmektedir.

Anahtar Kelimeler

ADNet: A CNN MODEL FOR ALZHEIMER'S DISEASE DIAGNOSIS ON OASIS-1 DATASET

Abstract

Alzheimer's disease (AD) is a chronic neurodegenerative disorder affecting memory, thinking, and behavior. Deep learning models, particularly CNNs, have shown promise in detecting AD at initial stages using the brain's magnetic resonance images (MRI). In this study, a CNN model called ADNet, trained using the OASIS-1 dataset, was proposed. The experimental approaches for evaluating the performance of ADNet are as follows: First, three different datasets were prepared using slices taken from the first quarter, middle, and third quarter of the sagittal plane from each MRI, to determine the most informative slice among the 128 slices. Each dataset was split into 80% training and 20% testing. It was found that the first quarter slice showed the best performance. The potential use of the obtained model as a transfer learning model was also examined. For this, a low-performance model was retrained using ADNet as a transfer learning model, and significant improvements in the results were observed. At last, the model’s robustness was evaluated in a more detailed evaluation, using 5-fold cross-validation repeated three times, resulting in a mean accuracy of 97.05%. As a result, ADNet can be used for Alzheimer's screening in clinical settings and could enable patients to receive earlier treatment.

Keywords

Supporting Institution

Coordinatorship of Scientific Research Projects of Necmettin Erbakan University

Project Number

23GAP19015

Thanks

This study has been financially supported by the Coordinatorship of Scientific Research Projects of Necmettin Erbakan University [Project no: 23GAP19015].

References

Afzal, S., Maqsood, M., Khan, U., Mehmood, I., Nawaz, H., Aadil, F., & Nam, Y. (2021). Alzheimer Disease Detection Techniques and Methods : A Review. 6, 26–38. https://doi.org/10.9781/ijimai.2021.04.005
Alroobaea, R., & Bragazzi, N. L. (2021). Alzheimer ’ s Disease Early Detection Using Machine Learning Techniques. 1–16.
Alzeimer’s Association. (2023). 2023 Alzheimer’s disease facts and figures. Alzheimer’s Dement., 19(4)(February), 1598–1695. https://doi.org/10.1002/alz.13016
Avots, E., Jafari, A., Ozcinar, C., & Anbarjafari, G. (2024). Comparative efficacy of histogram-based local descriptors and CNNs in the MRI-based multidimensional feature space for the differential diagnosis of Alzheimer’s disease: a computational neuroimaging approach. Signal, Image and Video Processing, 18(1), 1–13. https://doi.org/10.1007/s11760-023-02942-z
Baglat, P., Salehi, A. W., Gupta, A., & Gupta, G. (2020). Multiple Machine Learning Models for Detection of Alzheimer’s Disease Using OASIS Dataset. In S. K. Sharma, Y. K. Dwivedi, B. Metri, & N. P. Rana (Eds.), Re-imagining Diffusion and Adoption of Information Technology and Systems: A Continuing Conversation. TDIT 2020. IFIP Advances in Information and Communication Technology (Vol. 617, pp. 614–622). https://doi.org/10.1007/978-3-030-64849-7_54
Balasundaram, A., Srinivasan, S., Prasad, A., Malik, J., & Kumar, A. (2023). Hippocampus Segmentation-Based Alzheimer’s Disease Diagnosis and Classification of MRI Images. Arabian Journal for Science and Engineering. https://doi.org/10.1007/s13369-022-07538-2
Bendlin, B. B., Carlsson, C. M., Gleason, C. E., Johnson, S. C., Sodhi, A., Puglielli, L., … Wharton, W. (2011). Midlife predictors of Alzheimer’s disease. Maturitas, 65(2), 131–137. https://doi.org/10.1016/j.maturitas.2009.12.014.Midlife
Breijyeh, Z., & Karaman, R. (2020). Comprehensive Review on Alzheimer’s Disease : Causes and Treatment. Molecules, 25(5789), 1–28.

Chui, K. T., Gupta, B. B., Alhalabi, W., & Alzahrani, F. S. (2022). An MRI Scans-Based Alzheimer’s Disease Detection via Convolutional Neural Network and Transfer Learning. Diagnostics, 12(1531), 1–14.
Ghosh, T., Palash, M. I. A., Yousuf, M. A., Hamid, M. A., Monowar, M. M., & Alassafi, M. O. (2023). A Robust Distributed Deep Learning Approach to Detect Alzheimer’s Disease from MRI Images. Mathematics, 11(12), 2633. https://doi.org/10.3390/math11122633
Gramfort, A., Luessi, M., Larson, E., Engemann, D. A., Strohmeier, D., Garcia, S., … I, B. L. (2013). MEG and EEG data analysis with MNE-Python. Frontiers in Neuroscience, 7(December), 1–13. https://doi.org/10.3389/fnins.2013.00267
Hajamohideen, F., Shaffi, N., Mahmud, M., Subramanian, K., Al Sariri, A., Vimbi, V., & Abdesselam, A. (2023). Four-way classification of Alzheimer’s disease using deep Siamese convolutional neural network with triplet-loss function. Brain Informatics, 10(1). https://doi.org/10.1186/s40708-023-00184-w
Helaly, H. A., Badawy, M., & Haikal, A. Y. (2022). Deep Learning Approach for Early Detection of Alzheimer ’ s Disease. Cognitive Computation, (September 2021), 1711–1727. https://doi.org/10.1007/s12559-021-09946-2
Jadhao, P., Palsodkar, P., Raut, R., Chaube, K., Rathod, D., & Palsodkar, P. (2023). Prediction of Early Stage Alzheimer ’ s using Machine Learning Algorithm. 2023 4th International Conference for Emerging Technology (INCET), 1–5. https://doi.org/10.1109/INCET57972.2023.10170583
Khagi, B., & Kwon, G. R. (2019). CNN model performance analysis on MRI images of an OASIS dataset for distinction between healthy and Alzheimer’s patients. IEIE Transactions on Smart Processing and Computing, 8(4), 272–278. https://doi.org/10.5573/IEIESPC.2019.8.4.272
Krüger, F. (2016). Activity, Context, and Plan Recognition with Computational Causal Behaviour Models. Faculty of Computer Science and Electrical Engineering, University of Rostock, Phd Thesis, p:71-72.
Lu, B., Li, H., Chang, Z., Li, L., Chen, N., Zhu, Z., & Zhou, H. (2022). A practical Alzheimer ’ s disease classifier via brain imaging-based deep learning on 85 , 721 samples.
Marcus, D. S., Wang, T. H., Parker, J., Csernansky, J. G., Morris, J. C., Data, C. M. R. I., … Buckner, R. L. (2007). Open Access Series of Imaging Studies ( OASIS ): Cross-sectional MRI Data in Young , Middle Aged , Nondemented , and Demented Older Adults Citation Open Access Series of Imaging Studies ( OASIS ): Nondemented , and Demented Older Adults. Journal of Cognitive Neuroscience, 19(9), 1498–1507. https://doi.org/10.1162/jocn.2007.19.9.1498
Mendoza-Leon, R., Puentes, J., Felipe, L., & Hern, M. (2020). Single-slice Alzheimer ’ s disease classification and disease regional analysis with Supervised Switching Autoencoders. Computers in Biology and Medicine, 116(October 2019), 1–14. https://doi.org/10.1016/j.compbiomed.2019.103527
Mohammed, B. A., Senan, E. M., Rassem, T. H., Makbol, N. M., Alanazi, A. A., Al-Mekhlafi, Z. G., … Ghaleb, F. A. (2021). Multi-method analysis of medical records and mri images for early diagnosis of dementia and alzheimer’s disease based on deep learning and hybrid methods. Electronics (Switzerland), 10(22). https://doi.org/10.3390/electronics10222860
Neffati, S., Ben Abdellafou, K., Jaffel, I., Taouali, O., & Bouzrara, K. (2019). An improved machine learning technique based on downsized KPCA for Alzheimer’s disease classification. International Journal of Imaging Systems and Technology, 29(2), 121–131. https://doi.org/10.1002/ima.22304
Ovsepian, S. V, Leary, V. B. O., Zaborszky, L., & Ntziachristos, V. (2019). HHS Public Access. 25(4), 288–297. https://doi.org/10.1177/1073858418791128.Amyloid
Porsteinsson, A. P., Isaacson, R. S., Knox, S., Sabbagh, M. N., & Rubino, I. (2021). Diagnosis of Early Alzheimer’s Disease: Clinical Practice in 2021. 3(8), 371–386.
Rajayyan, S., & Mustafa, S. M. M. (2023). Prediction of dementia using machine learning model and performance improvement with cuckoo algorithm. International Journal of Electrical and Computer Engineering, 13(4), 4623–4632. https://doi.org/10.11591/ijece.v13i4.pp4623-4632
Salami, F., Bozorgi-Amiri, A., Hassan, G. M., Tavakkoli-Moghaddam, R., & Datta, A. (2022). Designing a clinical decision support system for Alzheimer’s diagnosis on OASIS-3 data set. Biomedical Signal Processing and Control, 74(September 2021), 1–7. https://doi.org/10.1016/j.bspc.2022.103527
Salhi, S., Kora, Y., Ham, G., Zadeh, H., Id, H., & Simon, C. (2023). Network analysis of the human structural connectome including the brainstem. PLoS ONE, 18(4), 1–20. https://doi.org/10.1371/journal.pone.0272688
Saratxaga, C. L., Moya, I., Picón, A., Acosta, M., Moreno-Fernandez-de-leceta, A., Garrote, E., & Bereciartua-Perez, A. (2021). Mri deep learning-based solution for alzheimer’s disease prediction. Journal of Personalized Medicine, 11(9). https://doi.org/10.3390/jpm11090902
Scheltens, P., Strooper, B. De, Kivipelto, M., Holstege, H., Chételat, G., Teunissen, C. E., … Flier, W. M. Van Der. (2022). Alzheimer ’ s disease. 397(10284), 1577–1590. https://doi.org/10.1016/S0140-6736(20)32205-4.Alzheimer
Shrivastava, R. K., Singh, S. P., & Kaur, G. (2023). shrivastava.pdf. In D. Koundal, D. K. Jain, Y. Guo, A. S. Ashour, & A. Zaguia (Eds.), Data Analysis for Neurodegenerative Disorders. Cognitive Technologies. (pp. 111–126). https://doi.org/10.1007/978-981-99-2154-6_6

Details

Primary Language

English

Subjects

Pattern Recognition , Deep Learning , Neural Networks

Journal Section

Research Article

Authors

Ahmet Samed Saraçoğlu
0009-0003-7835-4191
Türkiye

Ayse Merve Acılar ^*
0000-0002-0133-2694
Türkiye

Özlem Erdaş Çiçek
0000-0003-4019-7744
Türkiye

Publication Date

March 3, 2025

Submission Date

August 20, 2024

Acceptance Date

November 14, 2024

Published in Issue

Year 2025 Volume: 28 Number: 1

DOI

https://doi.org/10.17780/ksujes.1534327

IZ

https://izlik.org/JA36FD89MX

Cite

RIS / Bibtex

APA

Saraçoğlu, A. S., Acılar, A. M., & Erdaş Çiçek, Ö. (2025). ADNet: A CNN MODEL FOR ALZHEIMER’S DISEASE DIAGNOSIS ON OASIS-1 DATASET. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 487-504. https://doi.org/10.17780/ksujes.1534327