A Comparative Study on Data Balancing Methods for Alzheimer's Disease Classification

Year 2024, , 489 - 501, 11.07.2024

Esma Öter , Yahya Doğan

https://doi.org/10.21605/cukurovaumfd.1514553

Abstract

Alzheimer's disease is a prevalent neurological disorder affecting millions of people worldwide, often associated with the aging process, leading to the death of nerve cells in the brain and loss of connections. Recently, promising results have been demonstrated in diagnosing Alzheimer's disease using deep learning models, and various approaches for early diagnosis have been proposed. However, the imbalance in health datasets, particularly those containing rare cases, can lead to performance losses and misleading results during model training. This study focuses on these imbalance issues, evaluating the effectiveness of different balancing methods using the Alzheimer's MRI dataset. In this context, the performance of SMOTE, ADASYN, and Weight Balancing methods is compared using a custom model. Experimental results indicate that, compared to the original imbalanced dataset, Weight balancing outperforms in terms of accuracy, precision, recall, and F1 score. While SMOTE and ADASYN show improvement in various metrics, they are considered inferior to the Weight Balancing method. This study contributes to selecting data-balancing methods to enhance the accuracy of deep learning models in Alzheimer's disease classification and emphasizes the importance of addressing class imbalances in health datasets.

Keywords

Deep learning, Convolutional neural networks, SMOTE, ADASYN, Weight balancing

Alzheimer Hastalığı Sınıflandırması için Veri Dengeleme Yöntemlerinin Karşılaştırmalı Bir Çalışması

Abstract

Alzheimer hastalığı, dünya genelinde milyonlarca insanı etkileyen yaygın bir nörolojik bozukluktur ve genellikle yaşlanma süreciyle ilişkilidir; beyinde sinir hücrelerinin ölümüne ve bağlantı kaybına neden olur. Son zamanlarda, derin öğrenme modelleri kullanılarak Alzheimer hastalığının teşhisi konusunda umut verici sonuçlar elde edilmiş ve erken teşhis için çeşitli yaklaşımlar önerilmiştir. Ancak, özellikle nadir durumları içeren sağlık veri setlerindeki dengesizlik, model eğitimi sırasında performans kayıplarına ve yanıltıcı sonuçlara yol açabilir. Bu çalışma, bu dengesizlik sorunlarına odaklanarak, Alzheimer MRI veri seti için farklı dengeleme yöntemlerinin etkinliğini değerlendirmektedir. Bu bağlamda, özel bir model kullanılarak SMOTE, ADASYN ve Ağırlık Dengesi yöntemlerinin performansı karşılaştırılmaktadır. Deneysel sonuçlar, orijinal dengesiz veri setine kıyasla Ağırlık Dengesi yönteminin doğruluk, hassasiyet, geri çağrı ve F1 skoru açısından daha üstün olduğunu göstermektedir. SMOTE ve ADASYN, çeşitli metriklerde iyileşme göstermesine rağmen, Ağırlık Dengesi yöntemine kıyasla daha düşük performansa sahip oldukları gözlemlenmiştir. Bu çalışma, Alzheimer hastalığı sınıflandırmasında derin öğrenme modellerinin doğruluğunu artırmak için veri dengeleme yöntemlerinin seçimine katkıda bulunur ve sağlık veri setlerinde sınıf dengesizliğinin ele alınmasının önemini vurgular.

Keywords

Derin öğrenme, Evrişimsel sinir ağları, SMOTE, ADASYN, Ağırlık dengeleme

References

• 1. Nawaz, H., Maqsood, M., Afzal, S., Aadil, F., Mehmood, I., Rho, S., 2021. A Deep Feature-Based Real-Time System for Alzheimer Disease Stage Detection. Multimedia Tools and Applications, 80, 35789-35807.
• 2. Aditya Shastry, K., Sanjay, H.A., 2023. Artificial Intelligence Techniques for the Effective Diagnosis of Alzheimer’s Disease: A Review. Multimedia Tools and Applications, 83(13), 40057-40092.
• 3. Yao, Z., Mao, W., Yuan, Y., Shi, Z., Zhu, G., Zhang, W., Wang, Z., Zhang, G., 2023. Fuzzy-VGG: A Fast Deep Learning Method for Predicting the Staging of Alzheimer's Disease Based on Brain MRI. Information Sciences, 642, 119129.
• 4. Özdemir, C., 2023. Designing Effective Models for COVID-19 Diagnosis through Transfer Learning and Interlayer Visualization. Balkan Journal of Electrical and Computer Engineering, 11(4), 340-345.
• 5. Sivari, E., Civelek, Z., Sahin, S., 2024. Determination and Classification of Fetal Sex on Ultrasound Images with Deep Learning. Expert Systems with Applications, 240, 122508.
• 6. Kılıç, Ş., Doğan, Y., 2023. Deep Learning Based Gender Identification Using ear Images. Traitement du Signal, 40(4), 1629-1639.
• 7. Ozdemir, C., 2023. Classification of Brain Tumors from MR Images Using a New CNN Architecture. Traitement du Signal, 40(2), 611-618.
• 8. Assmi, A., Elhabyb, K., Benba, A., Jilbab, A., 2024. Alzheimer’s Disease Classification: A Comprehensive Study. Multimedia Tools and Applications, 1-24.
• 9. Mujahid, M., Rehman, A., Alam, T., Alamri, F. S., Fati, S. M., Saba, T., 2023. An Efficient Ensemble Approach for Alzheimer’s Disease Detection Using an Adaptive Synthetic Technique and Deep Learning. Diagnostics, 13(15), 2489.
• 10. Borkar, P., Wankhede, V.A., Mane, D.T., Limkar, S., Ramesh, J.V.N., Ajani, S.N., 2023. Deep Learning and Image Processing-Based Early Detection of Alzheimer Disease in Cognitively Normal Individuals. Soft Computing, 1-23.
• 11. Thangavel, P., Natarajan, Y., Preethaa, K.S., 2023. EAD-DNN: Early Alzheimer's Disease Prediction Using Deep Neural Networks. Biomedical Signal Processing and Control, 86, 105215.
• 12. Lu, D., Popuri, K., Ding, G.W., Balachandar, R., Beg, M.F., 2018. Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease Using Structural MR and FDG-PET Images. Scientific Reports, 8(1), 5697.
• 13. Ahmed, S., Choi, K.Y., Lee, J.J., Kim, B.C., Kwon, G.R., Lee, K.H., Jung, H.Y., 2019. Ensembles of Patch-Based Classifiers for Diagnosis of Alzheimer Diseases. IEEE Access, 7, 73373-73383.
• 14. Liu, C.F., Padhy, S., Ramachandran, S., Wang, V.X., Efimov, A., Bernal, A., Shi, L., Vaillant, M., Ratnanather, J.T., Faria, A.V., 2019. Using Deep Siamese Neural Networks for Detection of Brain Asymmetries Associated with Alzheimer's Disease and Mild Cognitive Impairment. Magnetic Resonance Imaging, 64, 190-199.
• 15. Sarraf, S., DeSouza, D.D., Anderson, J., Tofighi, G., 2016. DeepAD: Alzheimer’s Disease Classification via Deep Convolutional Neural Networks Using MRI and fMRI. BioRxiv, 070441.
• 16. Alzheimer MRI Preprocessed Dataset, https://www.kaggle.com/datasets/sachinkumar413/alzheimer-mri-dataset, Access date: 08.01.2024.
• 17. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P., 2002. SMOTE: Synthetic Minority Over-Sampling Technique. Journal of Artificial Intelligence Research, 16, 321-357.
• 18. He, H., Bai, Y., Garcia, E.A., Li, S., 2008. ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning. In 2008 IEEE International Joint Conference on Neural Networks, Hong Kong, China.
• 19. Chawla, N.V., Lazarevic, A., Hall, L.O., Bowyer, K.W., 2003. SMOTEBoost: Improving Prediction of the Minority Class in Boosting. In Knowledge Discovery in Databases: PKDD 2003: 7th European Conference on Principles and Practice of Knowledge Discovery in Databases, Cavtat-Dubrovnik, Croatia.
• 20. Guo, H., Viktor, H.L., 2004. Learning from Imbalanced Data Sets with Boosting and Data Generation: The DataBoost-IM Approach. ACM SigKDD Explorations Newsletter, 6(1), 30-39.
• 21. Du, M., Tatbul, N., Rivers, B., Gupta, A.K., Hu, L., Wang, W., Marcus, R., Zhou, S., Lee, I., Gottschlich, J., 2020. A Skew-Sensitive Evaluation Framework for Imbalanced Data Classification. arXiv preprint arXiv:2010. 05995.
• 22. Kingma, D.P., Ba, J., 2014. Adam: A Method for Stochastic Pptimization. arXiv preprint arXiv:1412.6980.