Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19431
標題: 乳房X光片星狀物腫瘤輪廓之偵測
Contour Detection for Spiculation in Mammograms
作者: 張榮宗
Chang, Jung-Tsung
關鍵字: Breast cancer
乳癌
Mammography
Spiculation
Contour segmentation
乳房攝影
星狀物腫瘤
輪廓分割
出版社: 資訊科學系所
引用: 1.衛生署衛生統計資訊網,”臺灣地區女性主要癌症死亡原因─九十四年與九十三年之比較”, http://www.doh.gov.tw/statistic/data/死因摘要/94年/94.htm 2. Introduction to Breast Cancer and Mammography http://www.e-radiography.net/articles/mammo/mammo_introduction.htm 3.許桓銘,乳癌外科治療的趨勢,http://tsgh.ndmctsgh.edu.tw/commcpc/Doc/950110.pdf 4.張瑞峰 陳達人,”乳房超音波影像的分析與應用”,資訊與教育雜誌83期, 2001年6月 5.黃育仁 郭明怡 曾怡真 吳曉雯 郭芳甄 趙富雄,“乳房超音波影像腫瘤輪廓切割”, 東海科學第五卷:43−54 43 , 2003年7月 6. Control of Breast Cancer Through Early Detection (Mammogram, Ultrasound and Image Guided Biopsy) http//www.hkma.org/download/cmebulletin/cme200702.pdf 7. The mini-MIAS database of mammograms http://peipa.essex.ac.uk/info/mias.html 8. Sheng-Fang Huang, Ruey-Feng Chang, Dar-Ren Chen, and Woo Kyung Moon, “Characterization of Spiculation on Ultrasound Lesions”,IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 23, NO. 1, JANUARY 2004 9.于南書, “最佳特徵選擇:乳房X 光片腫瘤偵測”,國立成功大學資訊工程學系碩士論文, 2004年6月 10. Sheila Timp, Nico Karssemeijer,“A new 2D segmentation method based on dynamic programming applied to computer aided detectection in mammography”,Medical Physics ,May 2004 – Volume 31, Issue 5, pp. 958-971 11.臺灣癌症臨床研究合作組織乳癌研究委員會,”乳癌診斷與治療共識”, 國家衛生研究院,2004年3月 12.M. Kass, A. Witkin, and D. Terzopoulos,“Snakes: Active Contour models” ,International Journal of Computer Vision, pp. 321-331, 1988, http://www.behaviorworks.com/people/ckline/cornellwww/cs664/snakes/ 13 . Thor Ole Gulsrud, Kjersti Engan, and Thomas Hanstveit , “Watershed segmentation of detected masses in digital mammograms”, Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27 Annual Conference ,Shanghai, China, September 1-4, 2005 14. Denise Guliato, Rangaraj M. Rangayyan, Juliano Daloia de Carvalho , “Spiculation-preserving Polygonal Modeling of Contours of Breast Tumors”,Proceedings of the 28 IEEE EMBS Annual International Conference, New York City, USA, Aug 30-Sept 3, 2006 15. R. M. Rangayyan , D. Guliato, J. Daloia de Carvalho, S. A. Santiago,“Feature Extraction from the Turning Angle Function for the Classification of Contours of Breast Tumors “ ,IEEE Special Topic Symposium on Information Technology in Biomedicine, Iaonnina, Greece, October 2006, in press. 16. Nguyen, T.M. Rangayyan, R.M. , “Shape Analysis of Breast Masses in Mammograms via the Fractal Dimension”, Engineering in Medicine and Biology Society, Sep. 2005. IEEE-EMBS 2005. 27 Annual International Conference 17. W.K. Pratt,”Digital Image Processing 3ed”, New York, John Wiley & Sons, 2002 18. 繆紹綱,”影像增強” ,“影像分割”,數位影像處理-活用Matlab,全華書局,2004年4月 19 Ramesh Jain,Rangachar Kasturi,Brian G.Schunck ,”MACHINE VISION” ,McGraw-Hill Science ,March,1995 20. Mehul P. Sampat, Alan C. Bovik, “Detect ion of Spiculated Lesions in Mammograms , Annual International Conference of the IEEE EMBS ,Cancun, Mexico – September 17-21,2003 21. Alasdair McAndrew,徐曉珮,”數位影像處理”,高立圖書,2005年6月 22.蔡明倫,”二維點狀影像資訊之強化、特徵擷取及辨識─以X光乳房微鈣化檢測為案例”,大葉大學工業工程學系碩士學位論文 ,2001年 6月 23. R.C. Gonzalez and R.E. Woods ” Digital image processing 2ed”, Addison Wesley, 2002. 24.連國珍,”空間領域影像處理”,數位影像處理,儒林書局,2004年9月 25.李嘉紘,郭智誠 ,”利用KMCC 和區域成長法之彩色影像切割技術-以葉片影像為例”,第四屆離島資訊技術與應用研討會論文集,2005年5月 26.黃育仁,”醫學影像內組織電腦輔助量測” http://140.128.102.71/research/mi/04/index.htm 27. N. Otsu, “A threshold selection method from gray level histogram”, IEEE Transaction on Systems, Man and Cybernetics,Vol. 8, pp. 62-66, 1978. 28.黃育仁, ”主動式輪廓超音波腫瘤影像切割”http://140.128.102.71/research/mi/02/index.htm 29. S. VAN ENGELAND, & N. KARSSEMEIJER. “ A regional registration method to _nd corresponding mass lesions in temporal mammogram pairs”, Med Phys ,32(8):2629.2638. 2005 30. S. Timp and N. Karssemeijer,“A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography” ,Med. Phys., vol. 31, pp. 958–971, 2004 31.吳文成,”碎形幾何與碎形理論”,http://www.atlas-zone.com/complex/fractals/index.html 32.C. Fortin, R. Kumaresan, W. Ohley,”Fractal dimension in the analysis of medical images”, IEEE ENGINEERING IN MEDICINE AND BIOLOGY ,June 1992 33.吳俊穎,”診斷性證據文獻數據分析”, 『臨床治療指引參考證據的評估─統計數據分析』研習會, 2004年10月 34.賴宣宇,”電腦輔助診斷系統於乳房腫瘤X光與超音波影像之整合應用”,中原大學醫學工程學系碩士學位論文,2005年7月 35.宇傳華,徐勇勇,“非參數法估計ROC曲線下面積”,中國衛生統計1999年第16卷第4期,http:// big5.51daifu.com/documents/2007/0305/7300183BF348B7E7H119851.shtml 36. Alberta Program for the Early Detection of Breast Cancer http://www.cancerboard.ab.ca/screentest/ 37. Cascio, D.; Fauci, F.; Magro, R.; Raso, G.; Bellotti, R.; De Carlo, F., “Mammogram Segmentation by Contour Searching and Mass Lesions Classification With Neural Network”, IEEE Transactions on Nuclear Science, Volume 53, Issue 5, Part 1, Oct. 2006 38.F´ABIO J. AYRES AND RANGARAJ M. RANGAYYAN,“Characterization of Architectural Distortion in Mammograms”,EMBS 2003 Student Paper Finalists 39. Hidefumi Kobatake,” Member, IEEE, and Yukiyasu Yoshinaga,“Detection of Spicules on Mammogram Based on Skeleton Analvsis”, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. IS, NO. 3, JUNE 1996 40. Huai Li,, K. J. Ray Liu, and Shih-Chung B. Lo,“Fractal Modeling and Segmentation for the Enhancement of Microcalcifications in Digital Mammograms”, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 16, NO. 6, DECEMBER 1997 41. ROELOFS, T., S. VAN WOUDENBERG, J. HENDRIKS, & N. KARSSEMEIJER.,“Optimized soft-copy display of digitized mammograms” In Proc. SPIE, Image Perception and Performance, volume 5043, pages 10.19. 2003. 42. N. Karssemeijer and G. M. Brake, “Detection of stellate distortions in mammograms” ,IEEE Transactions on Medical Imaging,vol. 15, no. 5, 1996 43.T. Pavlidis and Y.T. Liow, “Integrating Region Growing and Edge-Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, no. 3, pp. 225-233, Mar. 1990. 44.J. S. Lee, “Digital image enhancement and noise filtering by use of local statistics” , IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 2,pp. 165-168, 1980. 45.Iftekharuddin KM, Jia W, and Marsh R. ,“Fractal analysis of tumorin brain MR images.” Machine Vision and Applications, 13:352–362,2003. 46. B. D. Thackray and A. C. Nelson, “Semi-automatic segmentation of vascular network images using a rotating structuring element (ROSE) with mathematical morphology and dual feature thresholding” ,IEEE Trans.Med. Imaging, vol. 12, pp. 385–392, Sept. 1993. 47. KANG Wei, WANG Guangzhi, DING Hui,”Segmentation of the Breast Region in Mammograms Using Watershed Transformation”,Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27 th Annual Conference ,Shanghai, China, September 1-4, 2005 48.Weidong Xu, Shunren Xia, Min Xiao, and Huilong Duan,”A Model-based Algorithm for Mass Segmentation in Mammograms”,Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27 th Annual Conference ,Shanghai, China, September 1-4, 2005 49. I. Christoyianni, E. Dermatas, G. Kokkinakis, “Fast detection of masses in computer-aided mammography”, IEEE Signal Processing Magazine, pp. 54-64. January 2000. 50.R. Bird, T. Wallace, and B. Yankaskas,“Analysis of cancer missed at screening mammography”, Radiology, vol. 184, pp. 613–617, 1992 51. The Dutch Cancer Society,”Analysis of Temporal Mammogram Pairs to Detect and Characterise Mass Lesions”, Gra_media, RUG, Groningen ,June 2006
摘要: 乳癌是是我國婦女癌症死亡主因的第四位,乳癌診斷程序中,乳房X光攝影(Mammography)為臨床上醫生診斷乳癌(Breast cancer)的利器,在診斷乳房攝影腫瘤的影像時,可利用輪廓特徵來決定為良性或惡性腫瘤,良性腫瘤通常都會呈現圓滑的輪廓特徵,而惡性腫瘤則呈現星狀或不規則不平滑輪廓特徵,這種星狀或不規則不平滑特徵組織,稱為星狀物腫瘤(Spiculation),指的是腫瘤周圍的乳腺組織,因星狀物往外侵犯的關係造成的變形,星狀物的存在是惡性腫瘤判斷的依據。我們的研究目的是在乳房的X光影像中選取腫瘤懷疑的區域(ROI),分成三步驟,影像前處理、輪廓分割、特徵選取,找出具有星狀物輪廓的腫瘤,我們的方法首先強化腫瘤組織,接著有效分割出腫瘤的輪廓,最後利用規則式的碎形維度計算其輪廓特徵值,接著排序分出腫瘤輪廓類別,實驗結果證明我們的方法可有效偵測出星狀物腫瘤輪廓及其特徵。
Breast cancer is the fourth leading cause of cancer death for Taiwanese women. X-ray mammography is currently the most effective method for an early diagnosis of the breast cancer. The existence of spicules is one of most important visual signs for breast cancer diagnosis. Spiculation is a stellate distortion caused by the intrusion of breast cancer into surrounding tissue. In general, malignant tumors appear with rough and complex boundaries or contours, whereas benign masses present smooth, round, or oval contours. In this paper, we present a technique to detect the contours of spiculated lesions from the regions of interest (ROI) in a mammographic image. The method consists of tree steps: enhancement, contour segmentation, and feature selection. In this study, our method is able to enhance the signals from masses and extract the useful contour feature from the segmented regions. The ruler method of fractal dimension computed for each case was used to form a contour feature. These feature measures can be input to a classifier based on sorting. The experimental results show that our scheme can provide useful contour extraction for spiculation structures in mammographic images.
URI: http://hdl.handle.net/11455/19431
其他識別: U0005-1207200711074200
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1207200711074200
Appears in Collections:資訊科學與工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.