阿茲海默症(即失智症的一種)不僅會導致患者的記憶力衰退，而且對於認知功能及專注度等行為表現均有相當程度的影響。更加嚴重的事，阿茲海默症對於目前的醫學技術而言是一種不可逆的疾病。一旦被醫師確診為重度阿茲海默症，以現今的醫學技術並無法有效治癒阿茲海默症，能夠為患者做的就只有減緩其惡化的速度。再加上現今的醫學界對阿茲海默症的成因並不清楚，且診斷方式往往僅憑醫師的主觀認定，不夠客觀。有鑑於全球罹患阿茲海默症的人口日益增長，且對人類的影響性越來越大，本論文將透過功能性磁振造影(Function Magnetic Resonance Imaging，fMRI)圖像資料，以深度學習的方式客觀地找出阿茲海默症病理腦的共通性，以及與正常腦之間的差別。

Alzheimer's disease (a type of dementia) not only causes a decline in the memory of patients, but also has a considerable effect on behaviors such as cognitive function and concentration. More seriously, Alzheimer's disease is an irreversible disease for current medical technology. Once a doctor is diagnosed with severe Alzheimer's disease, today's medical technology cannot effectively cure Alzheimer's disease. All that can be done for patients is to slow down the rate of deterioration. In addition, the cause of Alzheimer's disease in the current medical community is not clear, and the diagnosis method is often based on the subjective identification of the doctor, which is not objective enough. In view of the increasing number of people suffering from Alzheimer's disease worldwide and the increasing impact on humans, this paper will use the function Magnetic Resonance Imaging (fMRI) image data to objectively find out A The commonness of the pathological brain in Zheimer's disease and the difference between it and normal brain.

目錄
論文審定書 i
摘要 ii
Abstract iii
圖目錄 vi
表目錄 vi
第一章 導論 1
1.1. 研究背景與目的 1
1.2. 阿茲海默症介紹 2
1.3. 阿茲海默症磁振造影資料 5
1.4. 論文架構 6
1.5. 貢獻 7
第二章 文獻探討 8
第三章 研究方法 10
3.1. 阿茲海默症患者fMRI圖像資料前處理 11
3.2. 使用5-fold切割訓練資料集與測試資料集 13
3.3. 以不同輸入型態輸入不同層數架構的CNN 14
3.4. 使用CNN擷取fMRI圖像特徵再透過SVM和RBF分類 15
3.5. 找出海馬迴中對阿茲海默症分類相對重要的腦區 16
3.6. 從完整的三維輸入中進一步精簡輸入的資料量 17
第四章 實驗結果 19
4.1. 準確度衡量依據 20
4.2. 以不同輸入型態輸入不同層數架構的CNN 21
4.3. 使用CNN擷取fMRI圖像特徵再透過SVM和RBF分類 25
4.4. 從完整的三維輸入中進一步精簡輸入的資料量 26
4.5. 方法比較 30
4.6. 透過權重找出海馬迴中對阿茲海默症分類相對重要的腦區 32
4.7. 結論 34
4.8. 未來研究方向 34
參考文獻 36

[1] Zvěřová, M. (2019). Clinical aspects of Alzheimer's disease. Clinical biochemistry.
[2] Alexiou, A., Kamal, M. A., & Ashraf, G. M. (2019). Alzheimer's Disease as a Current Challenge. Frontiers in neuroscience, 13, 768.
[3] Chang, Y. L., Chen, T. F., Shih, Y. C., Chiu, M. J., Yan, S. H., & Tseng, W. Y. I. (2015). Regional cingulum disruption, not gray matter atrophy, detects cognitive changes in amnestic mild cognitive impairment subtypes. Journal of Alzheimer's Disease, 44(1), 125-138.
[4] Proitsi, P., Kim, M., Whiley, L., Simmons, A., Sattlecker, M., Velayudhan, L., ... & Tsolaki, M. (2017). Association of blood lipids with Alzheimer's disease: A comprehensive lipidomics analysis. Alzheimer's & Dementia, 13(2), 140-151.
[5] Rosen, W. G., Mohs, R. C., & Davis, K. L. (1984). A new rating scale for Alzheimer's disease. The American journal of psychiatry.
[6] Hardy, J. A., & Higgins, G. A. (1992). Alzheimer's disease: the amyloid cascade hypothesis. Science, 256(5054), 184-186.
[7] Li, X., Dvornek, N. C., Papademetris, X., Zhuang, J., Staib, L. H., Ventola, P., & Duncan, J. S. (2018, April). 2-channel convolutional 3D deep neural network (2CC3D) for fMRI analysis: ASD classification and feature learning. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) (pp. 1252-1255). IEEE.
[8] Hazlett, H. C., Gu, H., Munsell, B. C., Kim, S. H., Styner, M., Wolff, J. J., ... & Collins, D. L. (2017). Early brain development in infants at high risk for autism spectrum disorder. Nature, 542(7641), 348-351.
[9] Lawrence, S., Giles, C. L., Tsoi, A. C., & Back, A. D. (1997). Face recognition: A convolutional neural-network approach. IEEE transactions on neural networks, 8(1), 98-113.
[10] Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014). A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188.
[11] Nathawani, D., Sharma, T., & Yang, Y. (2016). Neuroscience meets deep learning.
[12] Hu, J., Kuang, Y., Liao, B., Cao, L., Dong, S., & Li, P. (2019). A multichannel 2D convolutional neural network model for task-evoked fMRI data classification. Computational intelligence and neuroscience, 2019.
[13] De Martino, F., Gentile, F., Esposito, F., Balsi, M., Di Salle, F., Goebel, R., & Formisano, E. (2007). Classification of fMRI independent components using IC-fingerprints and support vector machine classifiers. Neuroimage, 34(1), 177-194.
[14] Misaki, M., Kim, Y., Bandettini, P. A., & Kriegeskorte, N. (2010). Comparison of multivariate classifiers and response normalizations for pattern-information fMRI. Neuroimage, 53(1), 103-118.