請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/50750
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳中平(Chung-Ping Chen) | |
dc.contributor.author | Chun-Yi Wu | en |
dc.contributor.author | 吳駿逸 | zh_TW |
dc.date.accessioned | 2021-06-15T12:56:12Z | - |
dc.date.available | 2021-07-26 | |
dc.date.copyright | 2016-07-26 | |
dc.date.issued | 2016 | |
dc.date.submitted | 2016-07-15 | |
dc.identifier.citation | [1] S.C Lai. (2006). 食物品味的變遷與現代台灣的社會文化轉型. 台灣社會學會年會會議.
[2] Cleveland_Clinic. (2015). Colorectal Cancer-Care & Treatment. Available: https://my.clevelandclinic.org/health/diseases_conditions/hic-colorectal-cancer/hic_Detecting_and_Treating_Diseases_of_the_Colon_and_Rectum. [3] Jeffrey M. Fox and Neil H. Stollman. (2015). Diverticular Disease of the Colon. [4] American Cancer Society, cancer facts and figure2016. p. 10, Atlanta: American Cancer Society, 2016. [5] Health Promotion Administration Ministry, CANCER REGISTRY ANNUAL REPORT. p. 2-5, Health Promotion Administration Ministry, 2015. [6] National Health Insurance Administration. 十大癌症醫療支出. 2014. Available: http://www.nhi.gov.tw/information/NewsDetail.aspx?menu=9&menu_id=544&No=1271. [7] American Cancer Society, cancer facts and figure2016, p. 12-13, Atlanta: American Cancer Society, 2016. [8] Majumdar, Sumit R., Robert H. Fletcher, and Arthur T. Evans. 'How does colorectal cancer present ? symptoms, duration, and clues to location.' The American journal of gastroenterology 94.10 (1999): 3039-3045. [9] Olympus American INC., Olympic_Series_Colonoscopes. 2014. [10] N.T.U. Hospital. 大腸鏡說明暨同意書. 2015. Available: https://www.ntuh.gov.tw/OPD/checkDoc/inst025.pdf. [11] Schoenfeld, Philip S., and Jonathan Cohen. 'Quality indicators for colorectal cancer screening for colonoscopy.' Techniques in gastrointestinal endoscopy15.2 (2013): 59-68. [12] Lieberman, David A., et al. 'Guidelines for colonoscopy surveillance after screening and polypectomy: a consensus update by the US Multi-Society Task Force on Colorectal Cancer.' Gastroenterology 143.3 (2012): 844-857. [13] Lim, Gary, et al. 'A prospective study of endoscopist-blinded colonoscopy withdrawal times and polyp detection rates in a tertiary hospital.' The New Zealand Medical Journal (Online) 125.1356 (2012): 52. [14] Schoenfeld, Philip S., and Jonathan Cohen. “Quality Indicators for Colorectal Cancer Screening for Colonoscopy,.” Techniques in gastrointestinal endoscopy15.2 (2013): 59–68. PMC. Web. 16 June 2016. [15] 邱瀚模, 李宜家, “如何提升大腸內視鏡品質─實證與指引”. 2013.pp2, pp66. [16] Baxter, Nancy N., et al. 'Analysis of administrative data finds endoscopist quality measures associated with postcolonoscopy colorectal cancer.'Gastroenterology 140.1 (2011): 65-72. [17] Rex, Douglas K. 'Still photography versus videotaping for documentation of cecal intubation: a prospective study.' Gastrointestinal endoscopy 51.4 (2000): 451-459. [18] ACS Surgery News, Completion study key after incomplete colonoscopy. 2013. Available:http://www.acssurgerynews.com/index.php?id=14929&tx_ttnews%5Btt_news%5D=143567&cHash=d34795c09817555826a0df04d60dfb2b. [19] Chen, Dongqing, et al. 'Variational Approach Based Image Pre-Processing Techniques for Virtual Colonoscopy.' Biomedical Image Analysis and Machine Learning Technologies: Applications and Techniques: Applications and Techniques (2009): 78. [20] Ming-Hung, Tsai, Liu Chung-Fan, and Shen Wei-Chih. 'Computer Aided Diagnosis for Evaluating Colorectal Mucosal Lesions Using Narrow-Band Imaging.' Genetic and Evolutionary Computing (ICGEC), 2011 Fifth International Conference on. IEEE, 2011. [21] Kominami, Yoko, et al. 'Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy.' Gastrointestinal endoscopy (2015). [22] Juchems, M. S., et al. 'A retrospective evaluation of patient acceptance of computed tomography colonography (“virtual colonoscopy”) in comparison with conventional colonoscopy in an average risk screening population.' Acta radiologica 46.7 (2005): 664-670. [23] Summers, Ronald M., et al. ' Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population.' Gastroenterology129.6 (2005): 1832-1844. [24] Robinson, C., et al. 'CT colonography: computer-assisted detection of colorectal cancer.' The British journal of radiology (2014). [25] Powell, Nick. “The Use of Cecal and Terminal Lleal Images for Verifying the Completion of Colonoscopy.” Gastroenterology & Hepatology 7.8 (2011): 536–539. Print. [26] Colorectal Specialists, Tour of the colon. Available: http://www.colorectalsite.com/Tour%20of%20the%20colon.htm. [27] Jayasekeran, V., B. Holt, and M. Bourke. 'Normal adult colonic anatomy in colonoscopy.' Video Journal and Encyclopedia of GI Endoscopy 1.2 (2013): 390-392. [28] Cirocco, William C., and Lawrence C. Rusin. 'The reliability of cecal landmarks during colonoscopy.' Surgical endoscopy 7.1 (1993): 33-36. [29] Cirocco, W.C. and L.C. Rusin, Confirmation of cecal intubation during colonoscopy. Dis Colon Rectum, 1995. 38(4): p. 402-6. [30] Prakash, Ravi, Sebastian N. Abadie, and Kevin D. Mullen. 'T1419: Prospective Study of Photo-Identification of Cecal Landmarks: Does Level of Training Really Matter?.' Gastrointestinal Endoscopy 71.5 (2010): AB272. [31] Charles Boncelet (2005). 'Image Noise Models'. In Alan C. Bovik. Handbook of Image and Video Processing. Academic Press. ISBN 0-12-119792-1.. [32] R. Fisher, S.P., A. Walker and E. Wolfart., Noise Generation. 2003. Available: http://homepages.inf.ed.ac.uk/rbf/HIPR2/noise.htm. [33] R. Fisher, S.P., A. Walker and E. Wolfart, Gaussian Smoothing. 2003. Available: http://homepages.inf.ed.ac.uk/rbf/HIPR2/gsmooth.htm. [34] Zhang, Deng, and Toshi Hiro Nishimura. 'Medical image noise reduction using Radon transform and Walsh list in Laplacian pyramid domain.' Consumer Electronics, 2009. ISCE'09. IEEE 13th International Symposium on. IEEE, 2009. [35] Alemán-Flores, Miguel, et al. 'Medical image noise reduction and region contrast enhancement using partial differential equations.' IADIS AC (2). 2009. [36] Ganz, Melanie, Xiaoyun Yang, and Greg Slabaugh. 'Automatic segmentation of polyps in colonoscopic narrow-band imaging data.' Biomedical Engineering, IEEE Transactions on 59.8 (2012): 2144-2151. [37] PHYS.ORG. Edge-crucial-eyesight. 2009. Available: http://phys.org/news/2009-10-edge-crucial-eyesight.html. [38] Canny, John. 'A computational approach to edge detection.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 6 (1986): 679-698. [39] Gregori, E., Building Machines That See: Finding Edges in Images. Available: http://www.embedded-vision.com/platinum-members/bdti/embedded-vision-training/documents/pages/building-machines-see-finding-edges-i. [40] Hough, Paul VC. Method and means for recognizing complex patterns. No. US 3069654. 1962. [41] Duda, Richard O., and Peter E. Hart. 'Use of the Hough transformation to detect lines and curves in pictures.' Communications of the ACM 15.1 (1972): 11-15. [42] Jessee, Emily, and Eric Wiebe. 'Visual perception and the HSV color system: exploring color in the communications technology classroom.' The Technology Teacher68.1 (2008): 7-12. [43] Uwimana, Epaphrodite. Automatic Medical Image Classification for Content-based Image Retrieval Systems. ProQuest, 2007. [44] Mewes, Philip W., et al. 'Automatic region-of-interest segmentation and pathology detection in magnetically guided capsule endoscopy.' Medical Image Computing and Computer-Assisted Intervention–MICCAI 2011. Springer Berlin Heidelberg, 2011. 141-148. [45] Kekre, H. B., and Kavita Patil. 'Standard deviation of mean and variance of rows and columns of images for cbir.' International Journal of Computer, Information, and Systems Science, and Engineering 3.1 (2009). [46] Yue, Jun, et al. 'Content-based image retrieval using color and texture fused features.' Mathematical and Computer Modelling 54.3 (2011): 1121-1127. [47] Shapiro, Linda, and George C. Stockman. 'Computer vision. 2001.' ed: Prentice Hall (2001). [48] Haralick, Robert M., Karthikeyan Shanmugam, and Its' Hak Dinstein. 'Textural features for image classification.' Systems, Man and Cybernetics, IEEE Transactions on 6 (1973): 610-621. [49] Hall-Beyer, M., The GLCM Tutorial. 2008. Available: http://www.fp.ucalgary.ca/mhallbey/tutorial.htm. [50] Conners, Richard W., Mohan M. Trivedi, and Charles A. Harlow. 'Segmentation of a high-resolution urban scene using texture operators.' Computer Vision, Graphics, and Image Processing 25.3 (1984): 273-310. [51] Sobri, Zuriani, and Harsa Amylia Mat Sakim. 'Texture Color Fusion Based Features Extraction for Endoscopic Gastritis Images Classification.'International Journal of Computer and Electrical Engineering 4.5 (2012): 674. [52] Ameling, Stefan, et al. 'Texture-based polyp detection in colonoscopy.'Bildverarbeitung für die Medizin 2009. Springer Berlin Heidelberg, 2009. 346-350. [53] Lima, C. S., et al. 'Texture classification of images from Endoscopic Capsule by using MLP and SVM-A comparative approach.' World Congress on Medical Physics and Biomedical Engineering, September 7-12, 2009, Munich, Germany. Springer Berlin Heidelberg, 2009. [54] Del Moral, Pierre. 'Non-linear filtering: interacting particle resolution.' Markov processes and related fields 2.4 (1996): 555-581. [55] Brauer, J., Particle Filter. 2013. Available: http://www.juergenwiki.de/work/wiki/doku.php?id=public:particle_filter. [56] Otsu, Nobuyuki. 'A threshold selection method from gray-level histograms.'Automatica 11.285-296 (1975): 23-27. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/50750 | - |
dc.description.abstract | 針對大腸鏡篩檢的影像,本論文提出了擷取盲腸與非盲腸之結構特徵的分析系統,利用特徵在兩者臨床照片中表現之不同,找出多維度的特徵向量,作為我們建立之分類系統的訓練資料,用以提升分類器之準確性和強健性,以及利用影像處理之結果,協助醫師判斷之目的。
近年來,人類的飲食習慣與生活與過去越來越不同,社會大眾對於自身的腸胃道系統也日益重視,消化系統相關的疾病儼然成為重要的課題,其中,又以大腸癌為國人罹患人數前三名以及高花費的病症。為了預防大腸癌以及維持良好的腸胃環境,國內外定期大腸鏡篩檢的需求量也不斷成長。然而為了達到有效的篩檢目的,完整的檢查程序是必須的,其中盲腸到達率(CIR)是檢查品質判斷一項非常重要的指標,故本論文注重於探討CIR以提升大腸鏡檢查的整體效益。我們提出一個系統架構,能夠基於影像處理的演算法,自動地辨識出影像中盲腸(Cecum)的結構表現,如回盲瓣Ileocecal Valve (ICV) 、微笑紋路Tri-radiate Fold、闌尾孔Appendiceal Orifice,另外,非盲腸部分的結構表現也是系統的擷取目標,並基於兩者的表現差異,找出多面向並且具有區別力的特徵,做為分類的依據。 本論文提出一套大腸鏡影像分析方法,包括有效地抑制如反光、血管、積水和糞便等雜訊,並找出適當的特徵值區別盲腸與非盲腸的結構表現,產生多維度特徵向量,提供整個大腸鏡影像分類系統的辨識。在此篇論文中,我們改良了先前研究單純針對單一亮度作為特徵擷取的演算法,提出Particle Filter將亮度特徵做一最佳化的擷取,另外,我們從Edge-Based、Histogram-Based 以及Texture-Based等不同方面進行大腸鏡影像的分析,包括Feature Extraction和Image Segmentation。最後我們另一位計畫夥伴將進一步以AdaBoost Machine Learning的方式進行特徵訓練,並得到一個將醫師上傳之大腸鏡影像分為盲腸或非盲腸之分類器。本論文提出的演算法,以臺大醫院提供之臨床影像,總共包含664位病人資料,我們隨機挑選出1009張盲腸與997張非盲腸影像作為訓練與測試,將結果與整體系統整合之後,最後我們得到了平均94.0%與最佳96.9%分類的準確率,並且基於這些特徵自動地標記出大腸鏡影像中之重要結構提供醫生作為判斷時之第三方參考。 | zh_TW |
dc.description.abstract | We proposed an analysis system to extract the features of cecum and non-cecum structures of clinical colonoscopy images. We found out the different expression of these two cases and obtained multiple features after extraction as the training data for our classifier of system. The proposed algorithm helped improve the accuracy and robustness compared to the previous work. Besides, we also provided assistance to doctors for their judgments with the result of image processing on colonoscopy images.
In recent years, the dietary habit and life of people had become very different nowadays, and the concerns of the digestive system related diseases had become more and more serious issue to people. Among these, colorectal cancer has the high incident rate and high cost within the top ranks in our country. To prevent colorectal cancer and maintain good digestive environment, the demand of regular colonoscopy is increasing around the world. However, to achieve the purpose of the examination effectively, complete procedure is essential. The cecal intubation rate (CIR) is the critical quality indicator of colonoscopy completion, which is our system mainly focus on. We proposed an image processing based system, which could automatically recognize the landmarks of cecum images such as Ileocecal valve (ICV), Tri-radiate Fold and Appendiceal Orifice. In addition, we also found the structures of non-cecum images. And we determined the features to demonstrate the difference between these two cases performance for our classification accordance. We developed an approach to analyze colonoscopy images, including reducing the noises such as reflection, veins and dirt of excrements. Further, we extracted vector of multiple features to describe cecum and non-cecum structures’ performance properly for the classification and recognition in our system. In this thesis, we applied Particle Filter algorithm to have better result compared to previous work, which used merely single lightness threshold as the classification feature. Moreover, Edge-Based, Histogram-Based and Texture-Based are the additional aspects we utilized to extract our features for colonoscopy images analysis, including classification and segmentation. Finally, we pass our feature vector as training data to another partner in our project, who is focus on developing Machine Learning using Adaboost algorithm for the classification dealing with the photos uploaded by doctors. The material of our experiment was provided by NTU hospital, which were totally 664 patients’ folder of clinical colonoscopy images. We randomly selected from it and got 1009 cecum images and 997 non-cecum images for our training and testing purpose. At last, we not only got average 94.0% and best 96.9% accuracy of classification performance, but also marked the vital landmark of cecum and non-cecum structures for doctors’ analysis. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T12:56:12Z (GMT). No. of bitstreams: 1 ntu-105-R03945034-1.pdf: 3988133 bytes, checksum: df1078b6b7260ca1d280acafe4c02916 (MD5) Previous issue date: 2016 | en |
dc.description.tableofcontents | 口試委員會審定書 ii
誌謝 iv 中文摘要 vi ABSTRACT viii CONTENTS x LIST OF FIGURES xii LIST OF TABLES xvi Chapter 1 Introduction 2 1.1 Intestinal Diseases 2 1.2 Colorectal Cancer and Colonoscopy 6 1.3 Quality of colonoscopy 8 1.3.1 Quality indicators 8 1.3.2 Cecal Intubation Rates 9 1.4 Objective and Contributions 11 1.5 Thesis Organization 13 Chapter 2 Related Work and Knowledge 14 2.1 About Colonoscopy 14 2.1.1 Computer-Aided Diagnosis for colonoscopy 14 2.1.2 Anatomical landmark of the colonoscopy images 16 2.2 Noise Reduction 19 2.3 Feature Extraction and Description 21 2.3.1 Edge-Based features 21 2.3.2 Color-Based and statistics features 25 2.3.3 Texture-Based features 28 Chapter 3 Proposed Methodology 34 3.1 Image Pre-Processing 34 3.1.1 Image Cutting 35 3.1.2 Reflection Regions Filling 37 3.2 First Part of Feature Extraction 38 3.2.1 Fold-Structure Finding 39 3.2.2 Hole-Structure Finding 43 3.2.3 Lightness Histogram 48 3.3 Second Part of Feature Extraction 49 3.3.1 Image Types determination 50 3.3.2 ROI Texture Analysis 51 3.3.3 Texture-Based Image Segmentation 56 Chapter 4 Experiment and Result 65 4.1 Materials and Environment 66 4.2 Performance of Features 66 4.2.1 Result of First Part Feature Extraction 69 4.2.2 Result of Second Part Feature Extraction 72 4.3 Validation of Proposed Features 73 4.4 Marked Structures of Colonoscopy Images 74 Chapter 5 Conclusion and Future Work 78 5.1 Conclusion 78 5.2 Future Work 79 REFERENCE 80 | |
dc.language.iso | en | |
dc.title | 大腸鏡臨床影像自動多維度特徵擷取與辨識分析 | zh_TW |
dc.title | Automatic Multi-Feature Extraction for Clinical Colonoscopy Image Analysis and Recognition | en |
dc.type | Thesis | |
dc.date.schoolyear | 104-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 傅楸善(Chiou-Shann Fuh),邱瀚模(Han-Mo Chiu) | |
dc.subject.keyword | 大腸鏡影像,盲腸到達率,影像處理,影像辨識,粒子濾波器,紋理分析,特徵擷取,影像切割, | zh_TW |
dc.subject.keyword | Colonoscopy Image,Cecal Intubation Rate,Image Processing,Pattern Recognition,Particle Filter,Texture Analysis,Feature Extraction,Image Segmentation, | en |
dc.relation.page | 85 | |
dc.identifier.doi | 10.6342/NTU201600802 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2016-07-15 | |
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 | |
---|---|---|---|
ntu-105-1.pdf 目前未授權公開取用 | 3.89 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。