(44.192.112.123) 您好!臺灣時間:2021/03/07 18:00
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:安沙帝
研究生(外文):FAISAL ASADI
論文名稱:卷積神經網絡(CNN)與傳統圖像處理在瘧疾和急性白血病疾病分類中的比較
論文名稱(外文):Comparison of Convolutional Neural Network (CNN) and Traditional Image Processing at Malaria Disease and Acute Leukemia Disease Classification
指導教授:陳瓊安
指導教授(外文):CHEN , CHIUNG-AN
口試委員:林祖賢林明義姜惟元
口試委員(外文):LIN , SZU-YINLIN , MING-YICHANG , WEI-YUAN
口試日期:2020-03-11
學位類別:碩士
校院名稱:明志科技大學
系所名稱:電機工程系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:英文
論文頁數:109
中文關鍵詞:生物醫學影像細胞圖像分類卷積神經網絡深度學習瘧疾細胞圖像技術自主
外文關鍵詞:Biomedical imagingcell image classificationconvolutional neural networkdeep learningmalaria cell imagestechnology autonomous
ORCID或ResearchGate:orcid.org/0000-0001-5702-7149
IG URL:Nasution Faisal A
Facebook:Faisal Asadi Nasution
相關次數:
  • 被引用被引用:0
  • 點閱點閱:193
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:70
  • 收藏至我的研究室書目清單書目收藏:0
Abstract
Cerebrospinal fluid, Chest X-Ray, blood smear analysis, and bone marrow examination are several standards to uphold the diagnosis of some diseases. The most important how to uphold leukemia and malaria disease has counted the total numbers of white blood cells (WBC) under a microscope. The several procedures and standards of how to uphold the diseases were not comfortable to do caused a time-consuming and tedious process. Nowadays there are many pieces of research in recent years that have tried to solve the problem of how to uphold and diagnosing quickly the diseases. This research paper proposed a comparative study of convolutional neural network (CNN) and traditional image processing within cell imagery extraction. The types of diseases that we did in this research are Malaria cell classification (infected and uninfected) and Acute leukemia disease (ALL and AML). In case of the Malaria cells classification we got high accuracy about 95%, with simple four layers of the CNN. At the end of this research, we can conclude that a convolutional neural network (CNN) better a method for image classification in big data cases compared with traditional image processing. The accuracy of those experiments in CNN-Malaria has satisfactorily achieved accuracy above 95% while Acute leukemia-LVQ.1 got accuracy about 73% with traditional image processing.

Table of Contents
Ming Chi University of Technology Recommendation Letter from the Thesis Advisor………………………………………………………. i
Ming Chi University of Technology Thesis/Dissertation Oral Defense Committee Certification…………………………………………….. ii
Abstract iii
Table of Contents iv
List of Figures vii
List of Tables ix
Chapter 1 1
Introduction 1
1.1 Artificial Intelligence (AI) 1
1.2 Objectives 3
1.2.1 Objectives of CNN - Malaria 3
1.2.2 Objectives of Traditional Image Processing – Acute Leukemia 4
1.3 Outline 5
Chapter 2 6
Literature Review 6
2.1 Artificial Intelligence in Biomedical Engineering 6
2.2 Machine Learning (ML) 8
2.2.1 Data 9
2.2.2 Model 9
2.2.3 Learning 10
2.3 Deep Learning (DL) 11
2.3.1 Inside a Deep Neural Network 12
2.3.2 Deep Learning Algorithm 13
2.3.3 Artificial Intelligence - Machine Learning - Deep Learning 14
2.3.4 Convolutional Neural Network (CNN) 15
2.3.5 Parameters for Measurement of the Accuracy 22
2.4 Digital Image Processing 26
2.4.1 Data Acquisition 27
2.4.2 Image Pre-Processing 27
2.4.3 Feature Selection and Extraction 28
2.4.4 Color Feature Extraction 28
2.4.5 Texture Feature Extraction 30
2.5 Learning Vector Quantization (LVQ) 32
2.5.1 Algorithm of Learning Vector Quantization (LVQ 1) 33
2.6 Related Research Work in Malaria Disease 34
2.7 Related Research Work in Acute Leukemia Disease Case 35
Chapter 3 38
Experimental Procedure 38
3.1 Flowchart of the classification cell of malaria using CNN 38
3.1.1 Data Collecting and Data Modeling 39
3.1.2 Model Architecture of Convolutional Neural Network 42
3.2 Flowchart of the Acute Leukemia using LVQ.1 algorithm 45
3.2.1 Data Collecting 46
3.2.2 Data Acquisition 47
3.2.3 Data Division 47
3.2.4 Identification Process 48
Chapter 4 73
Result and Discussion 73
4.1 Malaria Disease Using CNN Algorithm 73
4.1.1 Classification Results Interface 74
4.1.2 Accuracy of The CNN’s Algorithm 76
4.1.3 Conclusion of Accuracy Testing Results 82
4.2 Acute Leukemia Disease Using Learning Vector Quantization.1 82
4.2.1 Classification Results Interface 82
4.2.2 Accuracy of The LVQ.1 Algorithm 86
4.2.3 Conclusions of Accuracy Testing Result 92
Chapter 5 93
Conclusion 93
5.1 Malaria Disease Using CNN Algorithm 93
5.2 Acute Leukemia Disease Using Learning Vector Quantization.1 94
5.3 Comparison Methods and Results 95
References 96

List of Figures
Figure 2.1 Simulation of AI in Medicine Fields 7
Figure 2.2 Comparison of Classic and Modern Programming 9
Figure 2.3 Architecture of Deep Learning algorithm in Case 12
Figure 2.4 Detail Architecture of Deep Learning algorithm in Case 12
Figure 2.5 Network Architecture of Deep Learning 13
Figure 2.6 How Deep Learning Works 14
Figure 2.7 Relations of AI, ML, and DL 15
Figure 2.8 Architecture of CNN (Feature Detection) 16
Figure 2.9 Architecture of CNN (Feature Detection / Feature Maps) 17
Figure 2.10 Example of a Convolutional Layer Operation 18
Figure 2.11 The Curve of ReLU Activation Function 19
Figure 2.12 Example of Pooling With A Stride and Filter Size of Two 19
Figure 2.13 Example of Two Fully-Connected Networks 20
Figure 2.14 Architecture of CNN (Classification) 21
Figure 2.15 Schema Classification of a Test Dataset Produces 22
Figure 2.16 Schema Calculating of Error Rate 23
Figure 2.17 Schema Calculating of Accuracy (ACC) 24
Figure 2.18 Schema Calculating of Sensitivity or Recall (REC) 24
Figure 2.19 Schema Calculating of Specificity 25
Figure 2.20 Schema Calculating of Precision 25
Figure 2.21 Corresponding of Distance and Angel of Matrix 3×3 31
Figure 2.22 Network Structure of LVQ.1 32
Figure 2.23 Samples Single-Cell of Malaria Disease 41
Figure 2.24 Architecture of Convolutional Neural Network (CNN) 42
Figure 4.1 Interface of Commond-promt Running Program .……… 74
Figure 4.2 Interface Directory File of The Program …………….…. 75
Figure 4.3 Interface of The Cell Image ……………………….…… 76
Figure 4.4 Interface of The Curve of Training Program ……….….. 76
Figure 4.5 Interface of The Image Database 83
Figure 4.6 Interface While Before Training Data 84
Figure 4.7 Interface Doing Learning Process 85
Figure 4.8 Interface Final Result of The Classification 85

List of Tables
Table 3.1 Data modeling For Training and Testing 42
Table 3.2 Network Details 43
Table 3.5 Flowchart Research of Acute Leukemia – LVQ.1 45
Table 3.4 Matrix Work Area 1 58
Table 3.5 Matrix co-occurrence with angle 00 59
Table 3.6 Matrix co-occurrence with angle 450 60
Table 3.7 Matrix co-occurrence with angle 900 62
Table 3.8 Matrix co-occurrence with angle 1350 63
Table 3.9 Values of Spatial Relationship with angle
References
[1]W. Yuan, P. Deng, T. Taleb, S. Member, J. Wan, and C. Bi, “An Unlicensed Taxi Identification Model Based on Big Data Analysis,” IEEE Trans. Intell. Transp. Syst., vol. 17, no. 6, pp. 1703–1713, 2016.
[2]J. Chung and K. Sohn, “Image-Based Learning to Measure Traffic Density Using a Deep Convolutional Neural Network,” IEEE Trans. Intell. Transp. Syst., vol. 19, no. 5, pp. 1670–1675, 2018.
[3]D. Jo, B. Yu, H. Jeon, and K. Sohn, “Image-to-Image Learning to Predict Traffic Speeds by Considering Area-Wide Spatio-Temporal Dependencies,” IEEE Trans. Veh. Technol., vol. 68, no. 2, pp. 1188–1197, 2019.
[4]S. Sharaf and N. F. Shilbayeh, “A Secure G-Cloud-Based Framework for Government Healthcare Services,” IEEE Access, vol. 7, pp. 37876–37882, 2019.
[5]D. Jeong and S. Lee, “High-Speed Searching Target Data Traces Based on Statistical Sampling for Digital Forensics,” IEEE Access, vol. 7, pp. 172264–172276, 2019.
[6]J. E. Auerbach, A. Concorde, P. M. Kornatowski, D. Floreano, and S. Member, “Inquiry-Based Learning With RoboGen : An Open-Source Software and Hardware Platform for Robotics and Artificial Intelligence,” IEEE Trans. Learn. Technol., vol. 12, no. 3, pp. 356–369, 2019.
[7]A. U. L. Haq et al., “Feature Selection Based on L1-Norm Support Vector Machine and Effective Recognition System for Parkinson ’ s Disease Using Voice Recordings,” vol. 7, 2019.
[8]X. Chen, “SPECIAL SECTION ON SECURITY AND PRIVACY IN EMERGING DECENTRALIZED Using AI to Attack VA : A Stealthy Spyware Against Voice Assistance in Smart Phones,” IEEE Access, vol. 7, pp. 153542–153554, 2019.
[9]A. Khotanzad and E. Zink, “Contour Line and Geographic Feature Extraction from USGS Color Topographical Paper Maps,” vol. 25, no. 1, pp. 18–31, 2003.
[10]S. Liu, J. Jia, Y. D. Zhang, and Y. Yang, “Image Reconstruction in Electrical Impedance Tomography Based on Structure-Aware,” IEEE Trans. Med. Imaging, vol. 37, no. 9, pp. 2090–2102, 2018.
[11]L. Yuan, X. Wei, H. Shen, L. L. Zeng, and D. Hu, “Multi-center brain imaging classification using a novel 3d cnn approach,” IEEE Access, vol. 6, pp. 49925–49934, 2018.
[12]L. Fang, S. Member, C. Wang, and S. Li, “Attention to Lesion : Lesion-Aware Convolutional Neural Network for Retinal Optical Coherence Tomography Image Classification,” IEEE Trans. Med. Imaging, vol. 38, no. 8, pp. 1959–1970, 2019.
[13]A. J. Sang, K. A. I. M. Tay, and C. P. Lim, “Application of a Genetic-Fuzzy FMEA to Rainfed Lowland Rice Production in Sarawak : Environmental , Health , and Safety Perspectives,” vol. 6, no. iii, 2018.
[14]H. Su, C. Yang, G. Ferrigno, and E. De Momi, “Improved Human – Robot Collaborative Control of Redundant Robot for Teleoperated Minimally,” IEEE Robot. Autom. Lett., vol. 4, no. 2, pp. 1447–1453, 2019.
[15]Y. Hu, W. Li, L. Zhang, and G. Yang, “Designing , Prototyping , and Testing a Flexible Suturing Robot for Transanal Endoscopic Microsurgery,” IEEE Robot. Autom. Lett., vol. 4, no. 2, pp. 1669–1675, 2019.
[16]Q. Zheng et al., “Safety Tracking Motion Control Based on Forbidden Virtual Fixtures in Robot Assisted Nasal Surgery,” IEEE Access, vol. 6, pp. 44905–44916, 2018.
[17]S. B. Shafiei and A. A. L. Y. Hussein, “Relationship Between Surgeon ’ s Brain Functional Network Reconfiguration and Performance Level During Robot-Assisted Surgery,” IEEE Access, vol. 6, pp. 33472–33479, 2018.
[18]Y. Liu and F. Long, “Acute lymphoblastic leukemia cells image analysis with deep bagging ensemble learning,” bioRxiv, no. http://dx.doi.org/10.1101/580852. The, 2019.
[19]C. Matek, S. Schwarz, K. Spiekermann, and C. Marr, “Human-level recognition of blast cells in acute myeloid leukemia with convolutional neural networks,” bioRxiv, vol. 49, no. 0, pp. 1–11, 2019.
[21]F. Chollet, Deep Learning with Python. 2016.
[22]MATLAB, “Practical Deep Learning Examples with MATLAB,” 2018.
[23]J. Zhang, Y. Xia, Y. Xie, M. Fulham, and D. D. Feng, “Classification of Medical Images in the Biomedical Literature by Jointly Using Deep and Handcrafted Visual Features,” IEEE J. Biomed. Heal. Informatics, vol. 22, no. 5, pp. 1521–1530, 2018.
[24]MATLAB, “Introducing Machine Learning,” 2016.
[25]S. Raschka, Python Machine Learning. PACKT-Publishing, 2015.
[26]N. Mattsson, “Classification Performance of Convolutional Neural Networks,” UPPSALA Univ., 2016.
[27]D. P. Kingma and J. L. Ba, “ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION,” ICLR 2015, pp. 1–15, 2015.
[28]Gonzalez, R.C, Woods, RE, 2008, Digital Image Processing Third Edition. [Pearson Prentice Hall. London].
[29] K. Sirinukunwattana, S. E. A. Raza, Y. W. Tsang, D. R. J. Snead, I. A. Cree, and N. M. Rajpoot, “Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1196–1206, 2016.
[30]C. Matek, S. Schwarz, K. Spiekermann, and C. Marr, “Human-level recognition of blast cells in acute myeloid leukemia with convolutional neural networks,” bioRxiv, vol. 49, no. 0, pp. 1–11, 2019.
[31] C. T. Sari and C. Gunduz-Demir, “Unsupervised Feature Extraction via Deep Learning for Histopathological Classification of Colon Tissue Images,” IEEE Trans. Med. Imaging, vol. 38, no. 5, pp. 1139–1149, 2019.
[32] S. Rajaraman et al., “Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images,” PeerJ, pp. 1–17, 2018.
[33]D. Bibin, M. S. Nair, S. Member, and P. Punitha, “Malaria Parasite Detection From Peripheral Blood Smear Images Using Deep Belief Networks,” IEEE Access, vol. 5, pp. 9099–9108, 2017.
[34]W. D. Pan, Y. Dong, and D. Wu, “Classification of Malaria-Infected Cells Using Deep Convolutional Neural Networks,” IntechOpen, vol.8 Chapter 8, 2018.
[35]F. M. Azif, H. A. Nugroho, and S. Wibirama, “Detection of malaria parasites in thick blood smear : A review,” Commun. Sci. Technol., vol. 3, no. 1, pp. 27–35, 2018.
[36]S. Kunwar and R. M. Shikhrakar, “Malaria Detection Using Image Processing and Machine Learning.”
[37]A. A. Khashman and H. H. Abbas, “Blood Smear Images and a Neural Classifier,” Springer-Verlag Berlin Heidelb., pp. 80–81, 2013.
[38]M. Adjouadi, M. Ayala, M. Cabrerizo, N. Zong, G. Lizarraga, and M. Rossman, “Classification of leukemia blood samples using neural networks,” Ann. Biomed. Eng., vol. 38, no. 4, pp. 1473–1482, 2010.
[39] C. J. Huang and W. C. Liao, “Application of probabilistic neural networks to the class prediction of leukemia and embryonal tumor of central nervous system,” Neural Process. Lett., vol. 19, no. 3, pp. 211–226, 2004.
[40] S. Mohapatra, S. S. Samanta, D. Patra, and S. Satpathi, “Fuzzy based Blood Image Segmentation for Automated Leukemia Detection,” 2011 Int. Conf. Devices Commun., pp. 1–5, 2011.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔