臺灣博碩士論文加值系統

自從2019年COVID-19疫情爆發至今，全球醫療及經濟受到重大挑戰，為了減少醫療負擔，用於COVID-19檢測的深度學習研究備受關注。在本文中，我們使用胸部X射線數據集，比較限制對比度自適應直方圖均衡化(CLAHE)在數種基於注意力(Attention)的卷積神經網路上的影響。
本研究以深度學習之卷積神經網路進行COVID-19新冠肺炎偵測，並使用COVID-19、正常及病毒性肺炎三種分類的數據集，去評估當使用CLAHE之後，對深度學習分類效能之影響為何。本研究使用VGG16、VGG19、ResNet、NASNet、Xception等五種卷積神經網路架構，搭配ReLU、Mish、Swish三種激勵函數及Adam、Nadam、RMSProp三種優化器，並在全連接層前加入注意力層增加效能，以共45種組合比較使用CLAHE對分類檢測造成的差異，找出最適合運用CLAHE的演算法組合。

Since the outbreak of the COVID-19 epidemic in 2009, the global medical economy has faced major challenges. We are concerned about reducing medical loads and using them for COVID-19 detection and deep learning research. We will use the chest X-ray images data set in this article to compare the impact of Contrast Limited Adaptive Histogram Equalization (CLAHE) on several kinds of attention-based neural networks.
In this thesis, COVID-19 detection was carried out with the convolutional neural network of deep learning, and the effect of deep learning classification was assessed using data sets containing three categories: COVID-19, normal and viral pneumonia and evaluates the impact of CLAHE on the classification effect of the data.
This study employs VGG16, VGG19, ResNet, NASNet, and Xception five convolutional neural network architecture, using ReLU, Mish, Swish three activation functions and Adam, Nadam, RMSProp three optimizer, and in front of the full connection layer to add attention layer to increase performance, with a total of 45 combinations to compare the differences caused by CLAHE approach in classification detection, to find out the most suitable use of CLAHE in deep learning algorithm combination.

摘要 I
Abstract III
謝誌 IV
目錄 V
圖目錄 VIII
表目錄 X
第壹章 緒論 1
第一節 研究背景與動機 1
第二節 研究流程 4
第三節 研究範圍及限制 5
第四節 論文架構 5
第貳章 文獻探討 7
第一節 影像處理介紹 7
一、 直方圖均衡化 7
二、 自適應直方圖均衡化 8
三、 對比度受限自適應直方圖均衡化 9
第二節 卷積神經網路介紹 11
一、 卷積層 13
二、 線性整流層 14
三、 池化層 20
四、 全連接層 22
第三節 卷積神經網路架構 23
一、 VGG16及VGG19 23
二、 ResNet 24
三、 Xception 26
四、 NASNet 28
第四節 使用CLAHE應用於COVID-19檢測相關論文研究 31
第參章 研究方法 37
第一節 卷積神經網路之COVID-19辨識研究流程 37
第二節 研究方法概念 40
一、 影像預處理 40
二、 CLAHE 40
三、 卷積神經網路 42
四、 注意力機制 49
第三節 卷積神經網路於COVID-19之辨識步驟 49
一、 卷積神經網路訓練流程步驟 51
二、 卷積神經網路測試流程步驟 52
第四節 評估指標 53
一、 準確率(Accuracy) 53
二、 召回率(Recall) 53
三、 精確率(Precision) 53
四、 F-measure 53
五、 特異度(Specificity) 54
第肆章 實驗結果 55
第一節 實驗環境 55
第二節 COVID-19數據集 56
第三節 模型與參數設定 61
第四節 實驗結果 62
一、 以VGG16模型及各激勵函數與各優化器於CLAHE使用前後之分析 63
二、 以VGG19模型及各激勵函數與各優化器於CLAHE使用前後之分析 64
三、 以ResNet50模型及各激勵函數與各優化器於CLAHE使用前後之分析 66
四、 以Xception模型及各激勵函數與各優化器於CLAHE使用前後之分析 68
五、 以NASNet模型及各激勵函數與各優化器於CLAHE使用前後之分析 70
六、 各模型CLAHE使用後成效之比較 71
第伍章 結論與未來展望 78
第一節 結論 78
第二節 未來展望 81
參考文獻 82

英文文獻
[1] Al-Waisy, A. S., et al. (2020). "COVID-CheXNet: hybrid deep learning framework for identifying COVID-19 virus in chest X-rays images." Soft computing: 1-16.
[2] Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu,Hawaii,United States of America.1251-1258.
[3] Chowdhury, M. E., et al. (2020). "Can AI help in screening viral and COVID-19 pneumonia?" IEEE Access 8: 132665-132676.
[4] Deb, S. D. and R. K. Jha (2020). COVID-19 detection from chest X-Ray images using ensemble of CNN models. 2020 International Conference on Power, Instrumentation, Control and Computing (PICC), Thrissur, India, IEEE.1-5.
[5] Duran-Lopez, L., et al. (2020). "COVID-XNet: a custom deep learning system to diagnose and locate COVID-19 in chest X-ray images." Applied Sciences 10(16): 5683.
[6] El Asnaoui, K. and Y. Chawki (2020). "Using X-ray images and deep learning for automated detection of coronavirus disease." Journal of Biomolecular Structure and Dynamics: 1-12.
[7] Elfwing, S., et al. (2018). "Sigmoid-weighted linear units for neural network function approximation in reinforcement learning." Neural Networks 107: 3-11.
[8] Haghanifar, A., et al. (2020). "Covid-cxnet: Detecting covid-19 in frontal chest x-ray images using deep learning." arXiv preprint arXiv:2006.13807.
[9] Haritha, D., et al. (2020). Prediction of COVID-19 Cases Using CNN with X-rays. 2020 5th International Conference on Computing, Communication and Security (ICCCS), Patna, India, IEEE.1-6.
[10] He, K., et al. (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas,State of Nevada,United States of America.770-778.
[11] Hilmizen, N., et al. (2020). The Multimodal Deep Learning for Diagnosing COVID-19 Pneumonia from Chest CT-Scan and X-Ray Images. 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia, IEEE.26-31.
[12] Ibrahim, D. M., et al. (2021). "Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases." Computers in biology and medicine 132: 104348.
[13] Jiang, H., et al. (2021). "Deep learning for COVID-19 chest CT (computed tomography) image analysis: A lesson from lung cancer." Computational and Structural Biotechnology Journal 19: 1391-1399.
[14] Lee, K.-S., et al. (2020). "Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm." Journal of Personalized Medicine 10(4): 213.
[15] Lv, D., et al. (2020). "A cascade network for detecting covid-19 using chest x-rays." arXiv preprint arXiv:2005.01468.
[16] Maity, A., et al. (2020). "Image Pre-processing techniques comparison: COVID-19 detection through Chest X-Rays via Deep Learning." International Journal of Scientific Research in Science and Technology.113-123
[17] Misra, D. (2019). "Mish: A self regularized non-monotonic neural activation function." arXiv preprint arXiv:1908.08681 4.
[18] Nair, V. and G. E. Hinton (2010). Rectified linear units improve restricted boltzmann machines. Icml, Toronto,Canada.807-814
[19] Nigam, B., et al. (2021). "COVID-19: Automatic detection from X-ray images by utilizing deep learning methods." Expert Systems with Applications 176: 114883.
[20] Nwankpa, C., et al. (2018). "Activation functions: Comparison of trends in practice and research for deep learning." arXiv preprint arXiv:1811.03378.
[21] Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., ... & Zuiderveld, K. (1987). "Adaptive histogram equalization and its variations. " Computer vision, graphics, and image processing, 39(3), 355-368.
[22] Rahman, T., et al. (2021). "Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images." Computers in biology and medicine 132: 104319.
[23] Ramachandran, P., et al. (2017). "Searching for activation functions." arXiv preprint arXiv:1710.05941.
[24] Saiz, F. A. and I. Barandiaran (2020). "COVID-19 detection in chest X-ray images using a deep learning approach." International Journal of Interactive Multimedia and Artificial Intelligence, InPress (InPress) 1.
[25] Sanagavarapu, S., et al. (2021). COVID-19 Identification in CLAHE Enhanced CT Scans with Class Imbalance using Ensembled ResNets. 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), Toronto,Canada, IEEE.1-7.
[26] Siddhartha, M. and A. Santra (2020). "COVIDLite: A depth-wise separable deep neural network with white balance and CLAHE for detection of COVID-19." arXiv preprint arXiv:2006.13873.
[27] Simonyan, K. and A. Zisserman (2014). "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556.
[28] Singh, R. K., et al. (2021). "COVIDScreen: Explainable deep learning framework for differential diagnosis of COVID-19 using chest X-Rays." Neural Computing and Applications: 1-22.
[29] Siracusano, G., et al. (2020). "Pipeline for Advanced Contrast Enhancement (PACE) of Chest X-ray in Evaluating COVID-19 Patients by Combining Bidimensional Empirical Mode Decomposition and Contrast Limited Adaptive Histogram Equalization (CLAHE)." Sustainability 12(20): 8573.
[30] Szegedy, C., et al. (2016). Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas,State of Nevada,United States of America.2818-2826.
[31] Umri, B. K., et al. (2020). Detection of Covid-19 in Chest X-ray Image using CLAHE and Convolutional Neural Network. 2020 2nd International Conference on Cybernetics and Intelligent System (ICORIS), Manado, Indonesia, IEEE.1-5.
[32] Verma, P., et al. (2021). "Comparison of different optimizers implemented on the deep learning architectures for COVID-19 classification." Materials Today: Proceedings.
[33] Zoph, B. and Q. V. Le (2016). "Neural architecture search with reinforcement learning." arXiv preprint arXiv:1611.01578.
[34] Zoph, B., et al. (2018). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City,State of Utah,United States of America.8697.8710
[35] Zuiderveld, K. (1994). "Contrast limited adaptive histogram equalization." Graphics gems: Rectified Linear Units Improve Restricted Boltzmann Machines.474-485.
網站文獻
[36] 2019冠状病毒病. (2021, June 10). Retrieved from 维基百科, 自由的百科全书 : https://zh.wikipedia.org/w/index.php?title=2019%E5%86%A0
%E7%8A%B6%E7%97%85%E6%AF%92%E7%97%85&oldid=66014873
[37] 影像處理. (2021, February 7). Retrieved from維基百科,自由的百科全書: https://zh.wikipedia.org/w/index.php?title=%E5%9B%BE%E5%83%8F %E5%A4%84%E7%90%86&oldid=64163037
[38] Wikipedia contributors. (2021, March 15). Adaptive histogram equalization. In Wikipedia, The Free Encyclopedia. Retrieved 07:35, June 24, 2021, from https://en.wikipedia.org/w/index.php?title=Adaptive_histogram_equalization&oldid=1012259790
[39] BIMCV-COVID19, Datasets related to COVID19’s pathology course (BIMCV)：https://bimcv.cipf.es/bimcv-projects/bimcv-covid19/#1590858128006-9e640421-6711
[40] Chest X-Ray Images (Pneumonia)：https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
[41] COVID-19 Radiography Database：https://www.kaggle.com/tawsifurrahman/covid19-radiography-database
[42] COVID-19 image data collection：https://github.com/ieee8023/covid-chestxray-dataset
[43] RSNA Pneumonia Detection Challenge：https://www.kaggle.com/c/rsna-pneumonia-detection-challenge/data
[44] Società Italiana di Radiologia Medica e Interventistica (SIRM)：https://sirm.org/category/senza-categoria/covid-19/