為了探討深度學習技術判讀醫學圖像的可能性，我們與國立成功大學心臟內科合作。我們概述了醫學圖像處理和圖像分析的機器學習中的一些相關挑戰。通過對大量醫學圖像的多卷積運算，從圖像中提取目標的特徵圖來做模組訓練。之後，我們得到一個預測模組，可用於協助醫學研究或醫學診斷。因為深度學習是一個廣泛而快速發展的領域，在本研究中我們將重心放在對心電圖的深度卷積網路學習。
我們從數據庫中提取單一疾病 - 房室折返性心動過速(AVRT)的傳統12導層心電圖，希望根據患者的心電圖預處理數據，將圖像識別和深度學習技術應用於心電圖疾病預測，並區分病患的心電圖和正常的心電圖兩者之間的特徵差異。我們生成深度學習模型以交叉對齊這些心電圖，並訓練模型以通過心電圖的特徵來學習圖像識別。運用這種方法，在預測正常人心電圖和有疾病但未發病的AVRT患者心電圖時，我們獲得96％的準確度。另外，對有疾病且發病的AVRT患者心電圖建構另一個訓練模型，得到82％的準確度。我們的目標是將深度學習應用於醫療過程，以協助醫療診斷和治療過程。

To explore the possibilities of deep learning techniques for interpreting medical images, we work with the Division of Cardiology within the Department of Internal Medicine of National Cheng Kung University Hospital. We outline some related challenges in machine learning for medical image processing and image analysis. Through multi-convolution operation with a large number of medical images, the target feature map is extracted from the images. After that, we get a prediction model which could be used to assist medical researches or medical diagnoses. We pay attention to the deep learning of electrocardiogram (ECG) since deep learning is an extensive and fast-developing field.
We extract the electrocardiogram of the single disease-atrioventricular reentrant tachycardia (AVRT) from the database, hope to pre-process the data according to patient's electrocardiogram, apply image recognition and deep learning techniques to the ECG disease prediction and distinguish the characteristic differences between the onset and the normal ECG.
We produce a deep learning model to cross-align these ECGs, and train the model to learn image recognition by the characteristics of the ECGs. By this method, we can obtain a prediction model with the accuracy of 96%, which predicts ECGs of a normal person and ECGs of AVRT patients before the attack. Also, we make another model be trained with ECGs of AVRT patients after the attack, we get another prediction model with the accuracy of 82%. Our goal is to apply deep learning to medical processes to assist medical diagnosis and treatment course.

[1] Baldi, P., & Sadowski, P. (2014). The dropout learning algorithm. Artificial intelligence, 210, 78-122.
[2] Carneiro, G., Chan, A. B., Moreno, P. J., & Vasconcelos, N. (2007). Supervised learning of semantic classes for image annotation and retrieval. IEEE transactions on pattern analysis and machine intelligence, 29(3), 394-410.
[3] Chen, M., Hao, Y., Hwang, K., Wang, L., & Wang, L. (2017). Disease prediction by machine learning over big data from healthcare communities. Ieee Access, 5, 8869-8879.
[4] Chou, Y. M., Chan, Y. M., Lee, J. H., Chiu, C. Y., & Chen, C. S. (2018). Unifying and merging well-trained deep neural networks for inference stage. arXiv preprint arXiv:1805.04980.
[5] Ding, J., Chen, B., Liu, H., & Huang, M. (2016). Convolutional neural network with data augmentation for SAR target recognition. IEEE Geoscience and remote sensing letters, 13(3), 364-368.
[6] Du, C., & Gao, S. (2017). Image segmentation-based multi-focus image fusion through multi-scale convolutional neural network. IEEE access, 5, 15750-15761.
[7] Fadlullah, Z. M., Tang, F., Mao, B., Kato, N., Akashi, O., Inoue, T., & Mizutani, K. (2017). State-of-the-art deep learning: Evolving machine intelligence toward tomorrow’s intelligent network traffic control systems. IEEE Communications Surveys & Tutorials, 19(4), 2432-2455.
[8] Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., & Ng, A. Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine, 25(1), 65.
[9] Hatcher, W. G., & Yu, W. (2018). A survey of deep learning: platforms, applications and emerging research trends. IEEE Access, 6, 24411-24432.
[10] Hohman, F. M., Kahng, M., Pienta, R., & Chau, D. H. (2018). Visual analytics in deep learning: An interrogative survey for the next frontiers. IEEE transactions on visualization and computer graphics.
[11] Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
[12] L’heureux, A., Grolinger, K., Elyamany, H. F., & Capretz, M. A. (2017). Machine learning with big data: Challenges and approaches. IEEE Access, 5, 7776-7797.
[13] Li, D., Zhang, J., Zhang, Q., & Wei, X. (2017, October). Classification of ECG signals based on 1D convolution neural network. In 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom) (pp. 1-6). IEEE.
[14] Mach, P., & Becvar, Z. (2017). Mobile edge computing: A survey on architecture and computation offloading. IEEE Communications Surveys & Tutorials, 19(3), 1628-1656.
[15] Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016). Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Scientific reports, 6, 26094.
[16] Neagoe, V. E., Stoica, R. M., Ciurea, A. I., Bruzzone, L., & Bovolo, F. (2014). Concurrent self-organizing maps for supervised/unsupervised change detection in remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(8), 3525-3533.
[17] O'Shea, K., & Nash, R. (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458.
[18] Tuia, D., Volpi, M., Copa, L., Kanevski, M., & Munoz-Mari, J. (2011). A survey of active learning algorithms for supervised remote sensing image classification. IEEE Journal of Selected Topics in Signal Processing, 5(3), 606-617.
[19] Salamon, J., & Bello, J. P. (2017). Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Processing Letters, 24(3), 279-283.
[20] Sarkar, S., & Soundararajan, P. (2000). Supervised learning of large perceptual organization: Graph spectral partitioning and learning automata. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(5), 504-525.
[21] Shrestha, A., & Mahmood, A. (2019). Review of Deep Learning Algorithms and Architectures. IEEE Access, 7, 53040-53065.
[22] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.
[23] Wu, J. (2017). Introduction to convolutional neural networks. National Key Lab for Novel Software Technology. Nanjing University. China, 5, 23.
[24] Xia, W., Li, H., & Li, B. (2016, December). A control strategy of autonomous vehicles based on deep reinforcement learning. In 2016 9th International Symposium on Computational Intelligence and Design (ISCID) (Vol. 2, pp. 198-201). IEEE.
[25] Zeiler, M. D., & Fergus, R. (2014, September). Visualizing and understanding convolutional networks. In European conference on computer vision (pp. 818-833). Springer, Cham.
[26] Zhang, Q., Yang, L. T., Yan, Z., Chen, Z., & Li, P. (2018). An efficient deep learning model to predict cloud workload for industry informatics. IEEE transactions on industrial informatics, 14(7), 3170-3178.