本研究旨在利用深度學習方法對阿茲海默症患者進行分類，探索分析不同深度學
習模型在分類任務中的表現。
本研究收集了來自醫療公開數據庫來源的MRI影像數據，並使用多種深度學習方
法進行分析。具體而言，我們應用了Keras提供的卷積神經網路（CNN）的預訓練模
型，以提高分類的準確性和穩定性。在數據預處理階段，我們對數據進行了標準化處
理，並且用OpenCV此套件對數據影像進行切割腦室與海馬體。實驗結果表明，基於
深度學習的方法在阿茲海默症分類中具有顯著的優勢，能夠有效區分阿茲海默症患者。

With the acceleration of global aging, Alzheimer’s Disease (AD) has become a signifi
cant public health issue. Accurate classification of AD is crucial for developing personalized
treatment plans and prognosis evaluations.
This study aims to classify Alzheimer’s disease patients by using deep learning methods
and explore the performance of different deep learning models in classification tasks.
The study collected MRI image data from publicly available medical databases and an
alyzed it by using various deep learning methods. We applied pre-trained convolutional neu
ral network (CNN) models provided by Keras to improve classification accuracy and stability.
During the data preprocessing stage, we standardized the data and used the OpenCV library to
segment the ventricles and hippocampus in the images. The experimental results indicate that
deep learning-based methods have significant advantages in Alzheimer’s disease classification
and can effectively distinguish Alzheimer’s disease patients.

[1] M. Liu, F. Li, H. Yan, et al., “A multi-model deep convolutional neural network for automatic
hippocampus segmentation and classification in alzheimer＇s disease,” Neuroimage, vol. 208,
p. 116459, 2020.
[2] R. A. Morey, C. M. Petty, Y. Xu, et al., “A comparison of automated segmentation and manual
tracing for quantifying hippocampal and amygdala volumes,” Neuroimage, vol. 45, no. 3, pp. 855
866, 2009.
[3] N. An, H. Ding, J. Yang, R. Au, and T. F. Ang, “Deep ensemble learning for alzheimer’s disease
classification,” Journal of biomedical informatics, vol. 105, p. 103411, 2020.
[4] K. L. Lanctôt, J. Amatniek, S. Ancoli-Israel, et al., “Neuropsychiatric signs and symptoms of
alzheimer’s disease: New treatment paradigms,” Alzheimer’s & Dementia: Translational Research
&Clinical Interventions, vol. 3, no. 3, pp. 440–449, 2017.
[5] D.Carmo,B.Silva,C.Yasuda,L.Rittner,andR.Lotufo,“Hippocampussegmentationonepilepsy
and alzheimer’s disease studies with multiple convolutional neural networks,” Heliyon, vol. 7,
no. 2, 2021.
[6] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image
segmentation,” in Medical image computing and computer-assisted intervention–MICCAI 2015:
18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18,
Springer, 2015, pp. 234–241.
[7] M. A. Hossain and M. S. A. Sajib, “Classification of image using convolutional neural network
(cnn),” Global Journal of Computer Science and Technology, vol. 19, no. 2, pp. 13–14, 2019.
[8] K.I.Limited,Understandingconvolutionneural network(cnn) architecture–deep learning, 2023.
[Online]. Available: https://www.ksolves.com/blog/artificial-intelligence/
understanding-convolution-neural-network-architecture.
[9] A.D.NISHAD,Convolutionneuralnetwork,2020.[Online]. Available: https://www.kaggle.
com/discussions/general/171197.
[10] A.Jayasankha, Build your own model with convolutional neural networks, 2020. [Online]. Avail
able: https://medium.com/analytics-vidhya/build-your-own-model-with
convolutional-neural-networks-5ca0dd222c8f.
[11] D.P.KingmaandJ.Ba,“Adam:Amethodforstochasticoptimization,”arXivpreprintarXiv:1412.6980,
2014.
[12] J. Yousefi, “Image binarization using otsu thresholding algorithm,” Ontario, Canada: University
of Guelph, vol. 10, 2011.
[13] J. Lee, J. Oh, S. K. Shah, X. Yuan, and S. J. Tang, “Automatic classification of digestive organs
in wireless capsule endoscopy videos,” in Proceedings of the 2007 ACM symposium on Applied
computing, 2007, pp. 1041–1045.