基於條件式生成對抗網路之資料擴增於思覺失調症自動判別

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：54

、訪客IP：3.12.136.218

姓名

陳昌浩(Chang-Hao Chen) 查詢紙本館藏

畢業系所

電機工程學系

論文名稱

基於條件式生成對抗網路之資料擴增於思覺失調症自動判別
(Automatic Schizophrenia Discrimination using cGAN-based Data Augmentation)

相關論文

★ 多重嵌入增強式門控圖序列神經網路之中文健康照護命名實體辨識	★ 基於腦電圖小波分析之中風病人癲癇偵測研究
★ 標籤圖卷積增強式超圖注意力網路之中文健康照護文本多重分類	★ 運用合成器混合注意力改善BERT模型於科學語言編輯
★ 強化領域知識語言模型於中文醫療問題意圖分類	★ 管道式語言轉譯器之中文健康照護開放資訊擷取
★ 運用句嵌入向量重排序器增進中文醫療問答系統效能	★ 利用雙重註釋編碼器於中文健康照護實體連結
★ 聯合詞性與局部語境於中文健康照護實體關係擷取	★ 運用異質圖注意力網路於中文醫療答案擷取式摘要
★ 學習使用者意圖於中文醫療問題生成式摘要	★ 標籤強化超圖注意力網路模型於精神疾病文本多標籤分類
★ 上下文嵌入增強異質圖注意力網路模型於心理諮詢文本多標籤分類	★ 基於階層式聚類注意力之編碼解碼器於醫療問題多答案摘要
★ 探索門控圖神經網路於心理諮詢文字情感強度預測

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2026-9-27以後開放)

摘要(中)

思覺失調症 (Schizophrenia, SZ) 是心智的異常狀態，特徵為無法區分何者為真實，主要病徵包含妄想以及幻覺。我們使用病患的功能性磁振造影 (functional Magnetic Resonance Imaging, fMRI)，藉由自動解剖標籤 (Automated Anatomical Labeling) 將大腦分區，計算每個區域之間的相關係數，形成功能性連結矩陣 (Functional Connectivity Matrix)，將不同分區的特徵用在不同的模型進行判別，作為精神科醫師的決策支援輔助，藉以提升臨床診斷準確率。
研究的實驗資料來自臺北榮民總醫院精神科，包含220筆思覺失調症患者及220筆健康者(Healthy Control, HC) 的功能性磁振造影，性別及年齡比例相似非常接近。我們使用功能性連接矩陣探討不同種大腦分區方式、不同機器學習分類器、不同年齡層、不同性別間判別的效果。在大腦分區方式以AAL-3為最優秀，分類器則是使用支持向量機最好，準確率可達85.50%，而不同年齡及性別所比較出來的結果也顯示，同性質的資料所訓練的分類器能夠有較好的判別效果。
我們為求達到更好的判別效果，希望能以更多的資料來訓練模型，但是醫療相關影像的取得較難，成本也較高，因此希望能在有限的標記資料下能夠擴增成更大的資料集。功能性連接矩陣並不像一般影像資料集，能經由傳統的資料擴增方式如旋轉、鏡像或平移等進行擴充，因此我們希望能藉由生成對抗網路自訓練集的學習，生成更多樣本以訓練模型讓其能涵蓋不同的資料分布，提升判別的效果，在十次的實驗中訓練完生成對抗網路後，以擴增後的資料集進行訓練，羅吉斯回歸分類器的準確率能自84.77% 提升到87.05%，支援向量機的準確率能自85.23% 提升到86.36%。

摘要(英)

Schizophrenia is an abnormal state of the brain and mind with main symptoms including delusions and hallucinations so that fail to distinguish the real and virtual worlds. We use functional Magnetic Resonance Imaging (fMRI) to partition the brain by automatic anatomical labeling, calculate the correlation coefficient for each pair of ROIs, and form a functional connectivity matrix. The features of different parcellations are used in different models for Schizophrenia discrimination. The experimental data came from Taipei Veterans General Hospital, Taiwan. A total of 440 resting fMRIs were originated from 220 patients diagnosed with schizophrenia and 220 patients as healthy controls, in which the gender, and age distributions were very close. We use the functional connectivity matrix to explore the effects of different brain parcellation methods, different machine-learning classifiers, different age and gender groups. We find that using a support vector machine model with AAL-3 achieves the best accuracy score of 85.50%. The results also reveal that different classification models trained on the same ages and genders group had better performance. In order to achieve a better discrimination performance, we augment the dataset with more labeled data using a conditional Generative Adversarial Network (cGAN). By the cGAN-based data argumentation, the accuracy of the logistic regression classifier can be improved from 84.77% to 87.05%, and the support vector machine can be enhanced from 85.23% to 86.36%.

關鍵字(中)

★ 功能性磁振造影
★ 功能性連接矩陣
★ 機器學習
★ 生成對抗網路

關鍵字(英)

★ functional magnetic resonance imaging
★ functional connectivity matrix
★ machine learning
★ generative adversarial network

論文目次

目錄
摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 v
表目錄 vi
第一章緒論 1
1-1 研究背景 1
1-2 研究動機 3
1-3 章節概要 4
第二章相關研究 5
2-1 fMRI用於判別精神疾病任務 5
2-2 生成對抗網路 6
第三章模型架構 9
3-1 生成器網路架構 11
3-2 鑑別器網路架構 14
3-3 損失函數 16
第四章實驗與結果 17
4-1 實驗資料 17
4-2 實驗設定 19
4-3 效能評估 21
4-4 不同大腦分區比較 23
4-5 不同機器學習模型比較 25
4-6 不同性別資料訓練效果比較 27
4-7 不同年齡資料訓練效果比較 29
4-8 不同資料數量比較 31
4-9 生成對抗網路資料生成結果 34
第五章結論與未來展望 45
參考文獻 46

參考文獻

[1] C. A. Ross, R. L. Margolis, S. A.J. Reading, M. Pletnikov, and J. T. Coyle “Neurobiology of schizophrenia,” Neuron, vol. 52, no.1 ,pp. 139-153, Oct. 2006.
[2] Y. Tang, L. Wang, F. Cao and L. Tan, “Identify schizophrenia using resting-state functional connectivity: an exploratory research and analysis,”Biomed Eng Online, vol. 11, no. 50, Aug. 2012.
[3] D. Lei, W. H. L. Pinaya, T. Amelsvoor , M. Marcelis, G. Donohoe, D. O. Mothersill, A. Corvin, M. Gill, S. Vieira, X. Huang, S. Lui, C. Scarpazza, J. Young, C. Arango, E. Bullmore, G. Qiyong, P. McGuire, and A. Mechelli, ”Detecting schizophrenia at the level of the individual: relative diagnostic value of wholebrain images, connectome-wide functional connectivity and graph-based metrics,” Psychological Medicine, vol. 50, no. 11, pp. 1852–1861, Aug. 2020.
[4] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A.Courville and Y. Bengio, “Generative Adversarial Nets,” Advances in Neural Information Processing Systems 27, 2014.
[5] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein generative adversarial networks,” Proceedings of the 34th International Conference on Machine Learning, vol.70, pp.214-223, 2017.
[6] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin and A. Courville, “Improved Training of Wasserstein GANs,” 2017, arXiv:1704.00028
[7] T. Miyato, T. Kataoka, M. Koyama and Y. Yoshida, “Spectral Normalization for Generative Adversarial Networks,” ICLR, 2018.
[8] M. Mirza and S. Osindero, “Conditional Generative Adversarial Nets,” 2014, arXiv:1411.1784
[9] T. Chavdarova and F. Fleuret, “SGAN: An Alternative Training of Generative Adversarial Networks,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 9407-9415
[10] T. Miyato and M. Koyama, “cGANs with Projection Discriminator,” In ICLR, 2018.
[11] V. Dumoulin, J. Shlens, and M. Kudlur, “A learned representation for artistic style” In ICLR, Nov. 2017.
[12] J. Zhao, J. Huang, D. Zhi, W. Yan, X. Mad, X. Yang, X. Lif, Q. Keg, T. Jiang, V. D. Calhounh and J. Suib, “Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders,” Journal of Neuroscience Methods, vol.341, pp.108756, July, 2020.
[13] E. T. Rolls, C.-C. Huang, C.-P. Lin, J. Feng, and M. Joliot, “Automated anatomical labelling atlas 3,” NeuroImage, vol. 206, pp. 116189, Aug. 2020.
[14] E. Rolls, M. Joliot, and N. Tzourio-Mazoyer, “Implementation of a new parcellation of the orbitofrontal cortex in the automated anatomical labeling atlas,” NeuroImage, vol. 122, pp. 1-5, Nov. 2015.
[15] X. Shen, F. Tokoglu, X. Papademetris, and R. T. Constable, “Groupwise whole-brain parcellation from resting-state fMRI data for network node identification, ” NeuroImage, vol. 82, pp. 403-415., Nov. 2013.
[16] C.-C. Chang and C.-J. Lin, “LIBSVM: A library for support vector machines,” ACM Trans. Intelligent Syst. Technol., vol. 2, no. 3, pp.1–27, 2011.
[17] H.-F. Yu, F.-L. Huang and C.-J. Lin, "Dual coordinate descent methods for logistic regression and maximum entropy models," Machine Learning , vol. 85, no. 1–2, pp. 41–75, Oct. 2011.
[18] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no.1, pp.5-32, Oct. 2001.
[19] H. Xiao, K. Rasul and R. Vollgraf, “Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms,” 2017, arXiv:1708.07747
[20] A. Coates, H. Lee and A. Y. Ng, ” An Analysis of Single-Layer Networks in Unsupervised Feature Learning,” Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, vol.15, pp.215-223, 2011

指導教授

李龍豪(Lung-Hao Lee)

審核日期

2021-9-27

推文