請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72432
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳右穎(You-Yin Chen) | |
dc.contributor.author | Yu-Hsueh Wu | en |
dc.contributor.author | 吳侑學 | zh_TW |
dc.date.accessioned | 2021-06-17T06:42:16Z | - |
dc.date.available | 2021-08-19 | |
dc.date.copyright | 2018-08-19 | |
dc.date.issued | 2018 | |
dc.date.submitted | 2018-08-15 | |
dc.identifier.citation | [1] NINDS. (June 25). Parkinson's Disease Information Page. Available: https://www.ninds.nih.gov/Disorders/All-Disorders/Parkinsons-Disease-Information-Page
[2] S. Sveinbjornsdottir, 'The clinical symptoms of Parkinson's disease,' Journal of neurochemistry, vol. 139, pp. 318-324, 2016. [3] C. Fitzmaurice, C. Allen, and R. Barber, 'A systematic analysis for the Global Burden of Disease Study,' JAMA Oncol, vol. 3, no. 4, pp. 524-548, 2017. [4] S. L. Kowal, T. M. Dall, R. Chakrabarti, M. V. Storm, and A. Jain, 'The current and projected economic burden of Parkinson's disease in the United States,' Movement Disorders, vol. 28, no. 3, pp. 311-318, 2013. [5] D. L. Murman, 'Early treatment of Parkinson's disease: opportunities for managed care,' The American journal of managed care, vol. 18, no. 7 Suppl, pp. S183-8, 2012. [6] L. Findley et al., 'Direct economic impact of Parkinson's disease: a research survey in the United Kingdom,' Movement disorders, vol. 18, no. 10, pp. 1139-1145, 2003. [7] A. Abós et al., 'Discriminating cognitive status in Parkinson’s disease through functional connectomics and machine learning,' Scientific reports, vol. 7, p. 45347, 2017. [8] H. Choi, S. Ha, H. J. Im, S. H. Paek, and D. S. Lee, 'Refining diagnosis of Parkinson's disease with deep learning-based interpretation of dopamine transporter imaging,' NeuroImage: Clinical, vol. 16, pp. 586-594, 2017. [9] R. Erro, S. A. Schneider, N. P. Quinn, and K. P. Bhatia, 'What do patients with scans without evidence of dopaminergic deficit (SWEDD) have? New evidence and continuing controversies,' J Neurol Neurosurg Psychiatry, pp. jnnp-2014-310256, 2015. [10] F. D. Bowman, D. F. Drake, and D. E. Huddleston, 'Multimodal imaging signatures of Parkinson's disease,' Frontiers in neuroscience, vol. 10, p. 131, 2016. [11] S. D. R. R. Prashanth, P.K. Mandal, S. Ghosh, 'High-Accuracy detection of early parkinson’s disease through multimodal features and machine learning,' Int. J. Med. Inform., vol. 90, pp. 13-21, 2016. [12] MayoClinic. (June 25). Parkinson's Disease: Diagnosis and Treatment. Available: https://www.mayoclinic.org/diseases-conditions/parkinsons-disease/diagnosis-treatment/drc-20376062 [13] Parkinson'sUK. (June 25). How is Parkinson's diagnosed. Available: https://www.parkinsons.org.uk/information-and-support/how-parkinsons-diagnosed [14] A. Cherubini et al., 'Magnetic resonance support vector machine discriminates essential tremor with rest tremor from tremor‐dominant Parkinson disease,' Movement Disorders, vol. 29, no. 9, pp. 1216-1219, 2014. [15] S. Haller et al., 'Differentiation between Parkinson disease and other forms of Parkinsonism using support vector machine analysis of susceptibility-weighted imaging (SWI): initial results,' European radiology, vol. 23, no. 1, pp. 12-19, 2013. [16] Y. Zhang, 'Can a Smartphone Diagnose Parkinson Disease? A Deep Neural Network Method and Telediagnosis System Implementation,' Parkinson’s Disease, vol. 2017, 2017. [17] S. W. Clayton Pereira et al., 'Deep Learning-Aided Parkinson's Disease Diagnosis from Handwritten Dynamics,' presented at the 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2016. [18] R. B. Postuma et al., 'MDS clinical diagnostic criteria for Parkinson's disease,' Movement Disorders, vol. 30, no. 12, pp. 1591-1601, 2015. [19] M. D. S. T. F. o. R. S. f. P. s. Disease, 'The unified Parkinson's disease rating scale (UPDRS): status and recommendations,' Movement Disorders, vol. 18, no. 7, pp. 738-750, 2003. [20] M. M. Hoehn and M. D. Yahr, 'Parkinsonism: onset, progression, and mortality,' Neurology, vol. 50, no. 2, pp. 318-318, 1998. [21] V. Kotagal, 'Is PIGD a legitimate motor subtype in Parkinson disease?,' Annals of clinical and translational neurology, vol. 3, no. 6, pp. 473-477, 2016. [22] W. Maier, R. Buller, M. Philipp, and I. Heuser, 'The Hamilton Anxiety Scale: reliability, validity and sensitivity to change in anxiety and depressive disorders,' Journal of affective disorders, vol. 14, no. 1, pp. 61-68, 1988. [23] Z. S. Nasreddine et al., 'The Montreal Cognitive Assessment, MoCA: a brief screening tool for mild cognitive impairment,' Journal of the American Geriatrics Society, vol. 53, no. 4, pp. 695-699, 2005. [24] V. C. Pangman, J. Sloan, and L. Guse, 'An examination of psychometric properties of the mini-mental state examination and the standardized mini-mental state examination: implications for clinical practice,' Applied Nursing Research, vol. 13, no. 4, pp. 209-213, 2000. [25] R. S. Desikan et al., 'An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest,' Neuroimage, vol. 31, no. 3, pp. 968-980, 2006. [26] B. Fischl, 'FreeSurfer,' Neuroimage, vol. 62, no. 2, pp. 774-781, 2012. [27] M. W. Woolrich et al., 'Bayesian analysis of neuroimaging data in FSL,' Neuroimage, vol. 45, no. 1, pp. S173-S186, 2009. [28] R. W. Cox, 'AFNI: software for analysis and visualization of functional magnetic resonance neuroimages,' Computers and Biomedical research, vol. 29, no. 3, pp. 162-173, 1996. [29] Q.-H. Zou et al., 'An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: fractional ALFF,' Journal of neuroscience methods, vol. 172, no. 1, pp. 137-141, 2008. [30] S. M. Smith et al., 'Correspondence of the brain's functional architecture during activation and rest,' Proceedings of the National Academy of Sciences, vol. 106, no. 31, pp. 13040-13045, 2009. [31] Y. Zang et al., 'Regional homogeneity approach to fMRI data analysis,' Neuroimage, vol. 22, no. 1, pp. 394-400, 2004. [32] M. J. Hoptman et al., 'Amplitude of low-frequency oscillations in schizophrenia: a resting state fMRI study,' Schizophrenia research, vol. 117, no. 1, pp. 13-20, 2010. [33] Y. Han et al., 'Frequency-dependent changes in the amplitude of low-frequency fluctuations in amnestic mild cognitive impairment: a resting-state fMRI study,' Neuroimage, vol. 55, no. 1, pp. 287-295, 2011. [34] M. Abadi et al., 'Tensorflow: a system for large-scale machine learning,' in OSDI, 2016, vol. 16, pp. 265-283. [35] I. V. Tetko et al., 'Neural network studies. 1. Comparison of overfitting and overtraining,' Journal of chemical information and computer sciences, vol. 35, no. 5, pp. 826-833, 1995. [36] N. Srivastava et al., 'Dropout: a simple way to prevent neural networks from overfitting,' The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014. [37] T. Rocktäschel, E. Grefenstette, K. M. Hermann, T. Kočiský, and P. Blunsom, 'Reasoning about entailment with neural attention,' arXiv preprint arXiv:1509.06664, 2015. [38] A. M. Rush et al., 'A neural attention model for abstractive sentence summarization,' arXiv preprint arXiv:1509.00685, 2015. [39] D. Bahdanau et al., 'Neural machine translation by jointly learning to align and translate,' arXiv preprint arXiv:1409.0473, 2014. [40] K. M. Hermann et al., 'Teaching machines to read and comprehend,' in Advances in Neural Information Processing Systems, pp. 1693-1701, 2015. [41] J. Håstad and M. Goldmann, 'On the power of small-depth threshold circuits,' Computational Complexity, vol. 1, no. 2, pp. 113-129, 1991. [42] G. F. Montufar et al., 'On the number of linear regions of deep neural networks,' in Advances in neural information processing systems, pp. 2924-2932, 2014. [43] K. Simonyan and A. Zisserman, 'Very deep convolutional networks for large-scale image recognition,' arXiv preprint arXiv:1409.1556, 2014. [44] C. Szegedy et al., 'Going deeper with convolutions,' in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015. [45] X. Glorot and Y. Bengio, 'Understanding the difficulty of training deep feedforward neural networks,' in Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp. 249-256, 2010. [46] R. K. Srivastava et al., 'Highway networks,' arXiv preprint arXiv:1505.00387, 2015. [47] D. E. Rumelhart et al., 'Learning representations by back-propagating errors,' nature, vol. 323, no. 6088, p. 533, 1986. [48] R. Kohavi, 'A study of cross-validation and bootstrap for accuracy estimation and model selection,' in Ijcai, vol. 14, no. 2, pp. 1137-1145, 1995. [49] J. Lee Rodgers and W. A. Nicewander, 'Thirteen ways to look at the correlation coefficient,' The American Statistician, vol. 42, no. 1, pp. 59-66, 1988. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72432 | - |
dc.description.abstract | 帕金森氏症的電腦輔助診斷一直都是一項重要的研究議題,好的電腦輔助診斷系統能輸出正確的預測診斷結果,不僅可以加速醫師診斷的效率,還可以為臨床診斷減少人為的疏失,提升品質。
本論文基於傳統的電腦輔助診斷並加以精煉,提出了能同時輸出「預測診斷」以及產生統一帕金森病評定量表(Unified Parkinson's Disease Rating Scale Scores ,UPDRS)的系統。由於臨床量表對於帕金森氏症的診斷來說,是最為耗時卻又最為準確的醫療資訊,本研究能大大的節省醫師、病患以及醫療人員的時間,同時又能提供給醫師更豐富的醫療資訊做為診斷基礎。除此之外整個系統採用多模態輸入的模型,因此整個電腦輔助診斷的過程能夠綜合多種臨床資訊並做出更全面、更有可信度的預測診斷。 本論文透過類神經網路來開發此電腦輔助診斷系統,並且設計了主要由生成器(Generator)和分類器(Classifier)構成的兩段式結構模型。生成器綜合不同模態的原始臨床資訊,做出判斷並生成預測臨床量表;分類器則根據生成器輸出的臨床量表來分類受試者,輸出預測診斷結果。本論文以全腦的T1加權影像與靜息態功能性磁振影像,做為訓練模型的原始臨床資訊,在進入類神經網路的訓練階段之前,我們會先針對兩者做以腦區為基礎的資料前處理,T1加權影像透過Freesurfer分析,抽取出各個腦區的特徵值,髓質的部分包括體素數目、體積、強度平均值、強度標準差、強度最小值、強度最大值和強度範圍七項;皮質的部分包括頂點數目、表面積、體積、厚度平均值、厚度標準差、平均曲率和高斯曲率這七項;靜息態功能性磁振影像則透過FSL和AFNI兩種函式庫來分析,每個腦區會計算出三種特徵值,分別是fALFF、ICA maps和ReHo。前處理過後的特徵值會經過一層投影層,目的是將不同向量空間的輸入模態投影到相同的向量空間。接著,投影過後的特徵值會輸入生成器中,生成器又可分為兩個部分,分別是Attention Layer 和Highway Network,前者目的是讓模型去主動學習對於診斷相對重要的腦區,後者則負責生成預測臨床量表,它是一種類神經網路的變形,目的是讓生成器的網路結構可以堆疊的更深。最後,由簡單類神經網路構成的分類器,會根據生成的預測臨床量表做出預測診斷,將受試者分類成「僵直病患」、「震顫病患」以及「健康受試者」三類。 網路的訓練數據由45位受試者構成,包含了26名帕金森氏症患者和19名健康受試者,26名患者又可依症狀分為僵直組20人和震顫組6人。 模型的訓練與測試採用了三次交叉驗證的方法,在預測診斷的正確率上達到了91%的正確率,並在預測臨床量表與真實臨床量表的相關係數上達到0.92的高度相關。此外,本論文對於模型進行了剝離測試,驗證了模型中的各個組件和多模態輸入都有其必要性,能夠幫助模型有更好的表現;同時,我們透過層數測試的實驗,證實了類神經網路的深度直接影響了預測診斷的正確率,層數越深,正確率越高。 本論文針對帕金森氏症,建立了在預測診斷結果有高準確度、在預測臨床量表有高相似性之電腦輔助診斷系統,此系統能基於多模態的輸入資訊做出更完善的輔助診斷,並且模態的數目與種類具有極高的可擴充性。 | zh_TW |
dc.description.abstract | Computer aided diagnosis(CAD) is very important for Parkinson’s Disease since CAD can not only generate accurate diagnostic prediction but improve quality of diagnosis.
In this study, we proposed a refined CAD system. Our system generated both diagnostic prediction and predicted Unified Parkinson's Disease Rating Scale (UPDRS) scores in order to provide doctors with more medical information and made diagnosis more efficient. Furthermore, the whole system was designed as a multimodal model which made the decision process more comprehensive. We implemented a refined CAD system by proposing an innovative two-staged neural network model composed by the Generator and the Classifier. The Generator integrated medical information from different modalities and generated predicted clinical scales. The Classifier made diagnostic prediction based on predicted clinical scales from the Generator. We used whole brain T1 weighted images and resting state functional MRI as the raw data to train our model. But before training phase, we carried out a ROI based preprocessing. T1 weighted images were preprocessed using Freesurfer. Freesurfer extracted features from each ROI. For subcortex, the features included voxel number, volume, average intensity, standard deviation of intensity, minimum intensity, maximum intensity, intensity range; for cortex, the features included vertex number, surface area, volume, average thickness, standard of thickness, average curvature, Gaussian curvature. Resting state functional MRI were preprocessed using FSL and AFNI library. Each ROI contained 3 different features including fALFF, ICA maps and ReHo. After preprocessing, the Projection Layer would project features from different modalities into the same vector space. Then, the Generator would generate predicted clinical scales based on those projected features. The Generator was composed of two part, the Attention Layer and the Highway Network. The Attention Layer focused on learning the importance of each ROI for diagnosis; the Highway Network was a transformation of neural network specialized in stacking network deeper, and its main target was to generate predicted clinical scales. At last, the Classifier, which was actually a basic neural network structure, would make diagnostic prediction based on predicted clinical scales, and classified subjects into 3 types: PD Tremor, PD Rigidity and health control. The dataset we used in this paper contained 45 subjects including 26 Parkinson’s disease patients and 19 health control subjects. Also, we separated 26 patients into two groups, PD Tremor and PD Rigidity, consisting of 6 and 20 patients respectively. We trained and tested our model using 3-fold cross validation. Our model reached 91% accuracy on diagnostic prediction, and the correlation coefficient between real clinical scales and predicted clinical scales achieved 0.92. Moreover, the ablation test we carried out on this model proved that each component we designed, as well as the multimodal input mechanism, could improve our model. And the layer test proved that the deeper the neural network was, the better our model performed. As a result, we successfully build up a multimodal CAD system for Parkinson’s disease with high accuracy on diagnostic prediction and high correlation on predicted clinical scales. Moreover, the scalability of input modality was unlimited. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T06:42:16Z (GMT). No. of bitstreams: 1 ntu-107-R05548020-1.pdf: 2460407 bytes, checksum: c8902159753ebacca538f16b55a4c3f4 (MD5) Previous issue date: 2018 | en |
dc.description.tableofcontents | 第一章 緒論 1
1.1 研究背景與動機 1 1.2 研究目的 3 1.3 帕金森氏症診斷之簡介 4 1.3.1 帕金森氏症之臨床診斷 4 1.3.2 帕金森氏症之電腦輔助診斷與其困難 5 第二章 材料與方法 6 2.1 系統架構 6 2.2 訓練資料 8 2.2.1 疾病組 8 2.2.1.1 臨床量表評估 8 2.2.1.2 核磁共振影像數據收集 9 2.2.2 健康對照組 10 2.2.2.1 臨床量表評估 10 2.2.2.2 核磁共振影像數據收集 10 2.3 資料前處理 11 2.3.1 T1 加權影像 11 2.3.2 靜息態功能性核磁共振影像 13 2.4 類神經網路模型 14 2.4.1 投影層 14 2.4.2 生成器 17 2.4.2.1 Attention Layer 19 2.4.2.2 Highway Network 19 2.4.3 分類器 25 第三章 實驗結果 27 3.1 實驗評估標準 27 3.1.1 交叉驗證 27 3.1.2 準確率分析 27 3.1.3 相似性分析 28 3.2 完整模型分析 29 3.2.1 診斷結果準確率分析 29 3.2.2 臨床量表相似性分析 30 3.3 Ablation Study剝離測試 31 3.3.1 輔助性組件剝離測試 31 3.3.2 輸入模態剝離測試 32 3.4 生成器網路層數準確率分析 33 第四章 討論 34 4.1 完整模型表現 34 4.1.1 診斷結果表現 34 4.1.2 臨床量表表現 34 4.2 輔助性組件之重要性 35 4.3 多模態輸入之重要性 36 4.4 類神經網路層數之重要性 37 第五章 結論與未來發展 38 參考文獻 39 附錄一 : 腦區ROI列表 43 | |
dc.language.iso | zh-TW | |
dc.title | 以多模態深度學習網路進行帕金森氏症磁振影像之電腦輔助診斷 | zh_TW |
dc.title | Deep Neural Networks for Computer Aided Diagnosis of Parkinson’s Disease Using Multimodal MR Images | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 趙福杉(Fu-Shan Jaw) | |
dc.contributor.oralexamcommittee | 羅?君(Yu-Chun Lo) | |
dc.subject.keyword | 電腦輔助診斷,帕金森氏症,統一帕金森病評定量表,深度學習,類神經網路, | zh_TW |
dc.subject.keyword | Computer Aided Diagnosis,Parkinson’s Disease,Deep Learning,Neural Network, | en |
dc.relation.page | 43 | |
dc.identifier.doi | 10.6342/NTU201803387 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2018-08-15 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 醫學工程學研究所 | zh_TW |
顯示於系所單位: | 醫學工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-1.pdf 目前未授權公開取用 | 2.4 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。