請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81083完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 莊曜宇(Eric Y. Chuang) | |
| dc.contributor.author | Yu-Heng Tseng | en |
| dc.contributor.author | 曾昱衡 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:29:41Z | - |
| dc.date.available | 2022-02-16 | |
| dc.date.available | 2022-11-24T03:29:41Z | - |
| dc.date.copyright | 2022-02-16 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-02-11 | |
| dc.identifier.citation | [1] Heart Foundation. (2021). How The Heart Works. https://www.heartfoundation.org.nz/your-heart/how-the-heart-works [2] World Health Organization. (2021). Cardiovascular Diseases (CVDs). https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(CVDs) [3] Narayana Health. (2021). Blocked Heart Arteries: Sympoten, Prevention, Diagnosis, and Treatment. https://www.narayanahealth.org/coronary-artery-disease [4] European Society of Cardiology. (2020). ESC Guidelines for The Diagnosis and Management of Chronic Coronary Syndromes. Eur Heart J, 41, 407-477. [5] Neglia, D., Rovai, D., Caselli, C., Pietila, M., Teresinska, A., Aguadé-Bruix, S., ... Knuuti, J. (2015). Detection of Significant Coronary Artery Disease By Noninvasive Anatomical and Functional Imaging. Circulation: Cardiovascular Imaging, 8(3), e002179. [6] Lilly, Leonard S, ed. (2016). Pathophysiology of Heart Disease: A Collaborative Project of Medical Students and Faculty (sixth ed.). Lippincott Williams Wilkins. p. 74. ISBN 978-1451192759. [7] Wikipedia (2021). Electrocardiography. https://en.wikipedia.org/wiki/Electrocardiography. [8] Yao, Q., Wang, R., Fan, X., Liu, J., Li, Y. (2020). Multi-Class Arrhythmia Detection from 12-Lead Varied-Length ECG Using Attention-Based Time-Incremental Convolutional Neural Network. Information Fusion, 53, 174-182. [9] Wilson, F. N., Johnston, F. D., Macleod, A. G., Barker, P. S. (1934). Electrocardiograms That Represent The Potential Variations of A Single Electrode. American Heart Journal, 9(4), 447-458. [10] Goldberger, E. (1942). The aVL, aVR, and aVF leads: A Simplification of Standard Lead Electrocardiography. American Heart Journal, 24(3), 378-396. [11] Klabunde, R. (2011). Cardiovascular Physiology Concepts. Lippincott Williams Wilkins. https://www.cvphysiology.com/ [12] Emery, C., Torreton, E., Briere, J. B., Evers, T., Fagnani, F. (2020). Economic Burden of Coronary Artery Disease or Peripheral Artery Disease in Patients at High Risk of Ischemic Events in The French Setting: A Claims Database Analysis. Journal of Medical Economics, 23(5), 513-520. [13] Mahmoodzadeh, S., Moazenzadeh, M., Rashidinejad, H., Sheikhvatan, M. (2011). Diagnostic Performance of Electrocardiography in The Assessment of Significant Coronary Artery Disease and Its Anatomical Size in Comparison with Coronary Angiography. Journal of Research in Medical Sciences: The Official Journal of Isfahan University of Medical Sciences, 16(6), 750. [14] Attia, Z. I., Noseworthy, P. A., Lopez-Jimenez, F., Asirvatham, S. J., Deshmukh, A. J., Gersh, B. J., ... Friedman, P. A. (2019). An Artificial Intelligence-Enabled ECG Algorithm for The Identification of Patients with Atrial Fibrillation During Sinus Rhythm: A Retrospective Analysis of Outcome Prediction. The Lancet, 394(10201), 861-867. [15] Adedinsewo, D., Carter, R. E., Attia, Z., Johnson, P., Kashou, A. H., Dugan, J. L., ... Noseworthy, P. A. (2020). Artificial Intelligence-Enabled ECG Algorithm to Identify Patients with Left Ventricular Systolic Dysfunction Presenting to The Emergency Department with Dyspnea. Circulation: Arrhythmia and Electrophysiology, 13(8), e008437. [16] Chokmani, K., Khalil, B., Ouarda, T. B. M. J., Bourdages, R. (2007). Estimation of River Ice Thickness Using Artificial Neural Networks. In Proc. 14th Workshop Hydraulics Ice Covered Rivers. CGU HS/CRIPE (p. 12). [17] Choi, R. Y., Coyner, A. S., Kalpathy-Cramer, J., Chiang, M. F., Campbell, J. P. (2020). Introduction to Machine Learning, Neural Networks, and Deep Learning. Translational Vision Science Technology, 9(2), 14-14. [18] Gao, P., Zhang, Q., Wang, F., Xiao, L., Fujita, H., Zhang, Y. (2020). Learning Reinforced Attentional Representation for End-To-End Visual Tracking. Information Sciences, 517, 52-67. [19] Nwankpa, C., Ijomah, W., Gachagan, A., Marshall, S. (2018). Activation Functions: Comparison of Trends in Practice and Research for Deep Learning. arXiv preprint arXiv:1811.03378. [20] Handl, J., Knowles, J., Kell, D. B. (2005). Computational Cluster Validation in Post-Genomic Data Analysis. Bioinformatics, 21(15), 3201-3212. [21] Liu, Q., Zhang, N., Yang, W., Wang, S., Cui, Z., Chen, X., Chen, L. (2017, August). A Review of Image Recognition with Deep Convolutional Neural Network. In International Conference on Intelligent Computing (pp. 69-80). Springer, Cham. [22] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... Rabinovich, A. (2015). Going Deeper with Convolutions. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-9). [23] Simonyan, K., Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556. [24] He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep Residual Learning for Image Recognition. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition (pp. 770-778). [25] Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K. Q. (2017). Densely Connected Convolutional Networks. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition (pp. 4700-4708). [26] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. (2016). Rethinking The Inception Architecture for Computer Vision. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition (pp. 2818-2826). [27] Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A. A. (2017, February). Inception-V4, Inception-Resnet, and The Impact of Residual Connections on Learning. In Thirty-First AAAI Conference on Artificial Intelligence. [28] Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition (pp. 1251-1258). [29] F. Chollet. (2015). Keras Applications. https://keras.io/api/applications/ [30] Banerjee, R., Ghose, A., Mandana, K. M. (2020, July). A Hybrid CNN-LSTM Architecture for Detection of Coronary Artery Disease from ECG. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE. [31] Hanley, J. A., McNeil, B. J. (1982). The Meaning and Use of The Area Under A Receiver Operating Characteristic (ROC) Curve. Radiology, 143(1), 29-36. [32] Edouard Belval. (2017). Pdf2image. https://github.com/Belval/pdf2image [33] Lin, M., Chen, Q., Yan, S. (2013). Network in Network. arXiv preprint arXiv:1312.4400. [34] Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. R. (2012). Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors. arXiv preprint arXiv:1207.0580. [35] Ioffe, S., Szegedy, C. (2015, June). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning (pp. 448-456). PMLR. [36] Xu, B., Wang, N., Chen, T., Li, M. (2015). Empirical Evaluation of Rectified Activations in Convolutional Network. arXiv preprint arXiv:1505.00853. [37] Graham, B. (2014). Fractional Max-Pooling. arXiv preprint arXiv:1412.6071. [38] Stephanie G. (2019). ROC Curve Explained in One Picture. https://www.datasciencecentral.com/profiles/blogs/roc-curve-explained-in-one-picture [39] Swets, J. A. (2014). Signal Detection Theory and ROC Analysis in Psychology and Diagnostics: Collected Papers. Psychology Press. [40] Obuchowski, N. A. (2003). Receiver Operating Characteristic Curves and Their Use in Radiology. Radiology, 229(1), 3-8. [41] Spackman, K. A. (1989, January). Signal Detection Theory: Valuable Tools for Evaluating Inductive Learning. In Proceedings of The Sixth International Workshop on Machine Learning (pp. 160-163). Morgan Kaufmann. [42] Richard E. K. (2019). Cardiovascular Physiology Concepts – Electrocardiogram (EKG, ECG). https://www.cvphysiology.com/Arrhythmias/A009 [43] Ranya NS, Arif J. (2020). Acute Myocardial Infarction (MI). MSD Manual. https://www.msdmanuals.com/professional/cardiovascular-disor [44] Knuuti, J., Wijns, W., Saraste, A., Capodanno, D., Barbato, E., Funck-Brentano, C., ... Bax, J. J. (2020). 2019 ESC Guidelines for The Diagnosis and Management of Chronic Coronary Syndromes: The Task Force for The Diagnosis and Management of Chronic Coronary Syndromes of The European Society of Cardiology (ESC). European heart journal, 41(3), 407-477. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81083 | - |
| dc.description.abstract | "冠狀動脈疾病(coronary artery disease, CAD)是由供應心臟肌肉血液的血管 阻塞引起的一種心血管疾病(cardiovascular disease, CVD)。據世界衛生組織 (World Health Organization, WHO)統計，心血管疾病是全球排名第一的死因， 心血管疾病的主要死因之一就是冠狀動脈阻塞引起的急性心肌梗塞(acute myocardial infarction, AMI)。 標準 12 導聯心電圖 (electrocardiography, ECG) 是最廣泛使用的心血管疾病檢 測方法之一，因為其便宜、非侵入性且快速，使其成為心臟內科初始檢查的標準。 此後，醫生會根據這些數據對患者進行適當的治療或更深入的檢查。以冠狀動脈 疾病診斷為例，要診斷和定位冠狀動脈疾病，必須先通過 12 導聯心電圖檢查，再 通過冠狀動脈造影進行確認。冠狀動脈造影又稱心導管手術，是一種侵入性且具 有風險的檢測方式。其他造影方式，如核醫心肌灌注掃描、單光子電腦斷層掃描、 心臟核磁振造影以及冠狀動脈電腦斷層造影，則是需要專門的醫療儀器才能進行， 成本相對高昂，且有輻射暴露的風險。 根據相關研究指出，受過專業訓練的醫師以上述造影方式檢測冠狀動脈疾病 的敏感性以及特異性大約落在 70~95%之間。因此可得知有部分非冠狀動脈疾病 患者需要承擔額外的侵入性檢查風險。而且，在冠狀動脈造影時，由於缺乏阻塞 位置的資訊醫生必須檢查所有冠狀動脈才能確定阻塞位置，此過程將不可避免地 提升風險。 為了解決以上的問題，我們提出了一種基於深度學習模型的基於人工智慧的 心電圖算法，用於預測和定位經血管造影證實的冠狀動脈疾病。我們還構建了一 個用於數據預處理的圖形化使用者界面 (graphical user interface, GUI) 工具。此工 具可以將病人的 ECG 報告轉換為一維時間序列形式或二維圖像形式。藉此醫院的 ECG 報告就可以轉化為人工智能計算的數據，並為醫院發展人工智能技術提供一 個重要的利器。" | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:29:41Z (GMT). No. of bitstreams: 1 U0001-2801202211184400.pdf: 12859718 bytes, checksum: 91fbf688da1d2b0e9b5807306c36307c (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | "誌謝 ....... i 中文摘要 ....... ii ABSTRACT ....... iii CONTENTS ....... v LIST OF FIGURES ....... ix LIST OF TABLES ....... xii Chapter 1 INTRODUCTION ....... 1 1.1 Coronary artery ....... 1 1.2 Coronary artery disease ....... 2 1.3 CAD diagnosis ....... 3 1.4 Electrocardiography ....... 4 1.5 ECG morphological features for CAD detection ....... 8 1.6 Artificial-intelligence-enabled ECG algorithm ....... 10 1.7 Deep learning ....... 11 1.7.1 Fully connected layer ....... 14 1.7.2 Convolutional layer ....... 14 1.7.3 Pooling layer ....... 16 1.7.4 Activation function ....... 17 1.7.5 Loss function ....... 18 1.7.6 Optimizer ....... 18 1.8 Well-known DCNN architectures ....... 20 1.8.1 VGGNet ....... 21 1.8.2 ResNet ....... 21 1.8.3 DenseNet ....... 23 1.8.4 GoogLeNet ....... 23 1.8.5 Xception ....... 25 Chapter 2 MATERIALS AND METHODS ....... 26 2.1 Materials ....... 26 2.1.1 Study population ....... 26 2.1.2 Data collection and parsing ....... 27 2.1.3 Dataset preparation and data analysis ....... .28 2.2 Data preprocessing ....... 30 2.2.1 Data type ....... 30 2.2.2 Data transformation ....... 32 2.2.3 Background removal ....... 33 2.2.4 Time-series data transformation ....... 33 2.3 Graphical user interface (GUI) ....... 35 2.4 Deep convolutional neural networks ....... 37 2.4.1 Image input models ....... 37 2.4.2 Time-series data input models ....... 38 2.4.3 One-dimensional CNN model architectures ....... 39 2.4.4 The environment of training model, evaluation, and inference ....... 41 2.5 Model tuning and evaluation metrics ....... 41 2.5.1 Hyperparameter settings ....... 42 2.5.2 Evaluation metrics ....... 43 Chapter 3 RESULTS ....... 48 3.1 Deep learning models ....... 48 3.1.1 Image input model ....... 48 3.1.2 Time-series data input models ....... 50 3.1.3 1D convolution kernel optimization ....... 51 3.2 Down-sampling subsets ....... 53 3.2.1 Random selection ....... 53 3.2.2 Test for AMI and ischemia ECG ....... 56 3.2.3 Grad-CAM analysis ....... 60 3.3 Graphical user interface ....... 61 3.3.1 Basic interface ....... 61 3.3.2 Table interactivity ....... 63 3.3.3 Image and time-series data display control ....... 63 3.3.4 Setting and save function ....... 65 3.3.5 Data formats ....... 67 Chapter 4 DISCUSSION ....... 69 4.1 Deep learning models ....... 69 4.1.1 Image input models ....... 69 4.1.2 Time series data input model ....... 70 4.1.3 1D convolutional kernel size optimization ....... 71 4.2 Down-sampling subsets ....... 72 4.2.1 Random selection ....... 72 4.2.2 Test for AMI and ischemia ECG ....... 73 4.2.3 Grad-CAM analysis ....... 74 4.3 Comparisons ....... 74 4.3.1 Obstructed vessel prediction ....... 74 4.3.2 Input data types ....... 75 4.3.3 12-lead versus single-lead ECG ....... 77 4.4 Future researches ....... 77 4.4.1 AI ECG algorithm generalization ....... 77 4.4.2 Potential applications ....... 78 Chapter 5 CONCLUSION ....... 80 REFERENCES ....... 81 APPENDICES ....... 86" | |
| dc.language.iso | en | |
| dc.subject | 圖形化使用者介面工具 | zh_TW |
| dc.subject | 冠狀動脈疾病 | zh_TW |
| dc.subject | 人工智慧 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 心電圖 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | 12-lead ECG | en |
| dc.subject | coronary artery disease | en |
| dc.subject | artificial intelligence | en |
| dc.subject | graphical user interface tool | en |
| dc.title | 基於人工智能的 ECG 演算法用於預測及定位經血管造影證實的冠狀動脈疾病 | zh_TW |
| dc.title | An artificial intelligence-enabled ECG algorithm for the prediction and localization of angiography-proven coronary artery disease | en |
| dc.date.schoolyear | 110-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.author-orcid | 0000-0001-8385-6477 | |
| dc.contributor.oralexamcommittee | 蔡佳醍(Kai-Yu Hsieh),蔡孟勳(Li-ming Chen),賴亮全,盧子彬 | |
| dc.subject.keyword | 冠狀動脈疾病,人工智慧,深度學習,心電圖,圖形化使用者介面工具, | zh_TW |
| dc.subject.keyword | coronary artery disease,artificial intelligence,deep learning,12-lead ECG,graphical user interface tool, | en |
| dc.relation.page | 88 | |
| dc.identifier.doi | 10.6342/NTU202200250 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-02-12 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 生醫電子與資訊學研究所 | zh_TW |
| 顯示於系所單位： | 生醫電子與資訊學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2801202211184400.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 12.56 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。