(3.238.130.97) 您好!臺灣時間:2021/05/15 14:20
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:::

: 
twitterline
研究生:吳昱賢
研究生(外文):Yu-shien Wu
論文名稱:使用支持向量機評估肥胖細胞症病患接受UVA1紫外光照治療後之效果
論文名稱(外文):Quantitative Assessment of Irradiation Therapy on Cutaneous Mastocytosis – an Image Analysis Using Support Vector Machine
指導教授:張財榮張財榮引用關係
指導教授(外文):Tsai-Rong Chang
學位類別:碩士
校院名稱:南台科技大學
系所名稱:資訊工程系
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:102
畢業學年度:101
語文別:中文
論文頁數:72
中文關鍵詞:倒傳遞類神經網路連通元件標示法支持向量機
外文關鍵詞:Back propagation Neural NetworkSupport Vector MachineConnective Component Labeling
相關次數:
  • 被引用被引用:0
  • 點閱點閱:116
  • 評分評分:
  • 下載下載:8
  • 收藏至我的研究室書目清單書目收藏:0
隨著電腦科技的發展,醫學影像的應用逐漸普及且重要。因肥胖細胞在真皮層中所占的密度、面積及數目,可反應出肥胖細胞症的嚴重度,幫助臨床醫師診斷疾病與分析治療成效。本研究將肥胖細胞症病患,利用其組織病理學檢查(Histopathologic examination)的標本為研究之材料。因此安排肥胖細胞症病患之病灶,在接受UVA1照射治療之前、中、後,各進行皮膚切片檢查。應用各種特殊染色技術,以真皮中肥胖細胞為主要研究的標的。並利用色彩空間,類神經網路,支持向量機,形態學及聯通元件等機器學習與影像處理技術,在切片影像中,計算肥胖細胞所佔真皮部分之面積,觀察肥胖細胞的浸潤情形(Infiltration),並加以計數統計分析。本研究結果顯示:在Leder stain與Toludine Blue Stain上,電腦化細胞影像分析肥胖細胞細胞質顆粒,其準確性(accuracy)、敏感度(sensitivity)、有效性(specificity)與重複性(repetition)都比專業醫師與非專業的色彩研究員之分析結果為高。但在Giemsa stain上其效果則較人為肉眼主觀評估為低。最後將使用倒傳遞類神經網路(Back Propagation Neural Network)、支持向量機(Support Vector Machine)、形態學處理分析與計算出肥胖細胞面積的大小,利用醫師所提供的正確答案與位置,比較倒傳遞類神經與支持向量機面積與位置的正確率比較。本研究利用電腦計算病灶面積,輔助醫師在臨床治療的療效評估做為其他延伸研究的基礎。例如:治療的原理。
The severity and outcome of mastocytosis are known to be related to the number and size of mast cells. The standard treatment of this rare dermatological disorder is phototherapy with UVA1 irradiation. Here, the treatment effects were evaluated during the course of phototherapy on a patient with mastocytosis (urticaria pigmentosa). Photomicrographs of CD117 antibody-stained histological sections of the dermis were analyzed using image software programmed with Back Propagation Neural Network and Support Vector Machine. The artificial neural networks analyzed the color feature of epidermis, dermis, and mast cells. First, mast cells were isolated from epidermis and dermis, and RGB pixels converted to HSV Color space for Back Propagation Neural Network and Support Vector Machine training. Secondly, morphology and connective component labeling were used in epidermal pixels classification to determine the scope of dermal areas. Thirdly, regional separation isolated the dermis for the mast cell analysis. Specifically the number and size of mast cells were quantified. The method has good reproducibility compared with other methods which had larger variance and lower accuracy. We found also that the UVA1 phototherapy was effective as indicated by a post-treatment change in the ratio of mast cell surface to cell number. In addition, we compared similar results based on subjective visual inspection (from 10 human subjects). Both methods of analysis showed a reduction in the number and size of mast cells after phototherapy. But compared with human judgment, the computerized method was superior in accuracy, sensitivity, specificity and reproducibility of the findings.
摘 要 IV
ABSTRACT V
致 謝 VI
目  次 VII
表目錄 X
圖目錄 XI
第一章 緒論 1
1.1 研究動機 1
1.2 研究背景 2
1.3 論文架構 5
第二章 文獻探討 6
2.1 病理組織切片與染色 6
2.2 病理切片的細胞分割與辨識 7
2.3 類神經網路分類 8
第三章 系統架構 11
3.1 系統概述 11
3.2 肥胖細胞、表皮層與真皮層樣本擷取 12
3.3 樣本色彩空間分析 12
3.3.1 RGB色彩空間 13
3.3.2 HSV色彩空間 15
3.4 分類演算法 19
3.4.1 倒傳遞類神經網路 (Back propagation Neural Network) 19
3.4.2 倒傳遞類神經網路的訓練 22
3.4.3 支持向量機(Support Vector Machine) 23
3.4.4 支持向量機的訓練 29
3.5 表皮層分割 30
3.5.1 形態學處理 31
3.5.2 連通元件標示法 36
3.6 真皮層定位 37
3.6.1 遺失的真皮層 38
3.7 肥胖細胞定位 41
3.8 肥胖細胞面積之換算 42
第四章 實驗探討 46
4.1 色素性蕁麻疹的病患與切片來源 46
4.1.1 切片來源 46
4.1.2 實驗切片 48
4.2 實驗設計 53
4.3 實驗結果 61
4.3.1 敏感性與特異性 62
4.3.2 照光治療的治癒曲線 64
4.3.3 照光治療的治癒率 66
第五章 結論與未來工作 68
5.1 結論 68
5.2 未來工作 68
參考文獻 69
1.J. Eduardo Calonje MD DipRCPath, Thomas Brenn MD PhD FRCPath, Alexander J Lazar MD PhD, Phillip H. McKee MD FRCPath ,Saunders, 2011.
2.Lei He, Long L.R., Antani S. and Thoma G.R., “Local and global Gaussian mixture models for hematoxylin and eosin stained histology image segmentation” International Conference on Hybrid Intelligent Systems, 2010, pp.223-228.
3.Mete M. and Topaloglu U., “Statistical comparison of color model-classifier pairs in hematoxylin and eosin stained histological images” Computational Intelligence in Bioinformatics and Computational Biology, 2009, Vol. 9, pp. 284-291.
4.Sulaiman S.N., Isa N.A.M., Othman N.H. and Noor N.M., “Pseudo Color Features Extraction technique for cervical cancer of Pap smear images” Intelligent Systems Design and Applications, 2010, pp. 314-319.
5.Sheeba F., Thamburaj R., Nagar A.K. and Mammen J.J., “Segmentation of Peripheral Blood Smear Images Using Tissue-Like P Systems” International Conference on Bio-Inspired Computing, 2011, pp. 257-261.
6.Makkapati V., Agrawal R. and Acharya R., “Segmentation and classification of tuberculosis bacilli from ZN-stained sputum smear images” IEEE Conference on Automation Science and Engineering Bangalore, 2009, pp. 217-220.
7.Theera-Umpon N. and Dhompongsa S., “Morphological Granulometric Features of Nucleus in Automatic Bone Marrow White Blood Cell Classification” Transactions on Information Technology in Biomedicine, 2007, pp. 353-359.
8.Song L., Mundra P.A. and Rajapakse J.C., “Features for cells and nuclei classification” International Conference of the IEEE Engineering in Medicine and Biology Society, 2011, pp.6601-6604.
9.Yampri P., Pintavirooj C., Daochai S. and Teartulakarn S., “White Blood Cell Classification based on the Combination of Eigen Cell and Parametric Feature Detection” Industrial Electronics and Applications, 2006, pp. 1-4.
10.Plissiti M.E., Nikou C. and Charchanti A., “Watershed-based segmentation of cell nuclei boundaries in Pap smear images” Information Technology and Applications in Biomedicine, 2010, pp. 1-4.
11.Jinping Fan, Ruichun Wang, Shiguo Li and Chunxiao Zhang, “Automated cervical cell image segmentation using level set based active contour model ” International Conference on Control Automation Robotics & Vision, pp. 877 - 882, 2012.
12.Guimaraes L.V., Suzim A.A. and Maeda J., “A New Automatic Circular Decomposition Algorithm Applied to Blood Cells Image” Bio-Informatics and Biomedical Engineering, 2000, pp.277-280.
13.Scotti F., “Automatic morphological analysis for acute leukemia identification in peripheral blood microscope images” IEEE International Conference on Computational Intelligence for Measurement Systems and Applications Giardini Naxos, 2005, pp.96-101.
14.Al-Kofahi Y., Lassoued W., Lee W. and Roysam B., “Improved automatic detection and segmentation of cell nuclei in histopathology images” IEEE Transactions on Biomedical English, 2010, Vol. 57, pp. 841-852.
15.Plissiti M.E. and Nikou C., “Overlapping Cell Nuclei Segmentation Using a Spatially Adaptive Active Physical Model” IEEE Transactions on Image Processing, 2012, Vol. 21, pp. 1568-1580.
16.Xin Qi, Fuyong Xing, Foran D.J. and Lin Yang, “Robust Segmentation of Overlapping Cells in Histopathology Specimens Using Parallel Seed Detection and Repulsive Level Set” Transactions on Biomedical Engineering, 2012, Vol. 59, pp. 754-765.
17.Y. Liu, L. Kang, “A New Algorithm of Image Segmentation Based on Bidirectional Search Pulse-Coupled Neural Network” International Conference on Computational Aspects of Social Networks, 2010, pp. 101-104.
18.Su Mao-jun, Wang Zhao-bin, Zhang Hong-juan and Ma Yi-de, “A New Method for Blood Cell Image Segmentation and Counting Based on PCNN and Autowave” Control and Signal Processing, 2008, pp.6-9.
19.Wei-Liang Tai, Rouh-Mei Hu, Hsiao H.C.W., Rong-Ming Chen and Tsai J.J.P., “Blood Cell Image Classification Based on Hierarchical SVM ” IEEE International Symposium Multimedia, 2011, pp. 129-136.
20.Fan Di, Wang Wei, Cao Maoyong and Lv Changzhi, “Wall-Adherent Cells Segmentation Based on SVM ” Intelligent Systems, 2009, Vol. 4, pp. 552-556.
21.Xingbo Sun, Yi Wan and Rong Guo, “Chinese Wine Classification Using BPNN through Combination of Micrographs' Shape and Structure Features” International Conference on Natural Computation, 2009, Vol. 2, pp. 379-384.
22.Yingying Jiao, Xiaopei Wu and Xiaojing Guo, “Motor imagery classification based on the optimized SVM and BPNN by GA” International Conference on Intelligent Control and Information Processing, 2010, pp. 344-347.
23.Theera-Umpon N. and Gader P.D., “System-level training of neural networks for counting white blood cells” IEEE Transactions on Systems Applications and Reviews, 2002, Vol. 32, pp. 48-53.
24.F. Qiang ,Y. Shenglin ,W. Huaiyin , “An New Automatic Nucleated Cell Counting Method With Improved Cellular Neural Networks (ICNN)” International Workshop on Cellular Neural Networks and Their Applications, 2006, pp. 1-4.
25.Nasution A.M.T. and Suryaningtyas E.K. , “Comparison of Red Blood Cells Counting using two Algorithms: Connected Component Labeling and Backprojection of Artificial Neural Network” IEEE IPGC, 2008, pp.1-4.
26.Sheikh H., Zhu B. and Micheli-Tzanakou E., “Blood Cell Identification using Neural Networks” Bioengineering Conference, 1996, pp. 119-120.
27.Su Mao-jun , Zhang Hong-juan and Ma Yi-de, “A new method for blood cell image segmentation and counting based on PCNN and autowave” Control and Signal Processing, 2008, pp. 6-9.
28.Sheng-Fang Huang, Yen-Ching Chen and Woo Kyung Moon, “Neural network analysis applied to tumor segmentation on 3D breast ultrasound images” Biomedical Imaging, 2008, pp. 1303-1306.
29.Chuan-Yu Chang, Yi-Lian Wu and Yuh-Shyan Tsai, “Integrating the Validation Incremental Neural Network and Radial-Basis Function Neural Network for Segmenting Prostate in Ultrasound Images” Ninth International Conference on Hybrid Intelligent Systems, 2009, Vol. 1, pp. 198-203.
30.Carneiro G., Nascimento J. and Freitas A., “Robust Left Ventricle Segmentation from Ultrasound Data using Deep Neural Networks and Efficient Search Methods” Biomedical Imaging, 2010, pp. 1085-1088.
31.Xu Feng, Shan Daguo and Yang Hongchen, “Image Edge Detection Based on Improved PCNN” Information Science and Engineering, 2010, pp. 3757-3760.
32.Jing Jiao and Yuanyuan Wang, “Automatic Boundary Detection in Breast Ultrasound Images based on Improved Pulse Coupled Neural Network and Active Contour Model” Bioinformatics and Biomedical Engineering, 2011, pp. 1-4.
33.http://zh.wikipedia.org/wiki/File:RGB_color_solid_cube.png
34.http://zh.wikipedia.org/wiki/HSL_%E8%89%B2%E5%BD%A9%E7%A9%BA%E9%97%B4
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊