臺灣博碩士論文加值系統

乳癌是女性最常發生的癌症之一。及早發現癌症可以得到較適當的治療。目前，由於超音波的便利性及對人體較無傷害，所以超音波檢測對於乳癌的篩檢和診斷是一種有效且常用的方法。在本篇論文中，我們提出一個全自動的篩檢系統，分別對於全乳房超音波影像的三個垂直面檢測是否有腫瘤存在。首先，由於連續超音波影像之間的差異性很不明顯，所以我們會先將數張的超音波影像疊合在一起後再做處理以節省檢測時間。超音波影像通常本身有強烈的雜訊，因此前處理部份使用非等向性擴散模糊的方式來去除班點雜訊，並用S型濾鏡來強化對比提升邊界資訊。接著，全乳房超音波影像的三個垂直面會分別套用模糊理論來篩檢是否有腫瘤存在。在用模糊理論做篩檢後，只有標示為腫瘤的區塊會再經由一些事先定義的腫瘤條件來去掉不符合腫瘤特徵的區塊。最後我們會將三個垂直面各自篩檢出的可疑區塊互相做比對來得到最後的檢測結果。在測試的18個病例中，幾乎所有腫瘤或水泡都能被正確找到，而平均每個病例約會產生兩個誤判。依實驗結果，我們可以驗證這個系統的準確性。

Breast cancer is the most frequently diagnosed cancer in women. The early detection of the cancer provides a better chance of proper treatment. Ultrasound (US) is the efficient method used for breast cancer detection and diagnose presently because of its convenience and non-invasive. In this paper, whole breast ultrasound is adopted to detect the breast tumor. We propose a full automatic screening system to detect the possible tumors in three orthogonal views of the whole breast ultrasound. First, due to the differences between the successive US images are almost unobvious; we will overlap several US images together for reducing the detection time. Because the US image always has strong speckle noise, some preprocessing techniques, such as anisotropic diffusion filter and sigmoid filter, are used to reduce speckle noise and enhance the object boundary. Then, fuzzy techniques are applied to detect tumors in three orthogonal views independently. After the tumor detection by using fuzzy techniques, only the regions classified as tumors are considered to be applied the pre-defined criteria evaluation. The regions passed by the criteria evaluation are the suspicious tumor regions. Finally, we compare the relative relationships of suspicious regions in each view to each other for obtaining the detection results. By examining the US test database consisted of 18 cases, almost all the tumors or cysts could successfully be detected when an average of two false positive for each case is produced. The free-response operative characteristics (FROC) curve is also used to evaluate performance. The experimental results show that the proposal system gives quite satisfactory detection performance.

摘 要 i
ABSTRACT ii
ACKNOWLEDGEMENTS iv
LIST OF FIGURE vi
LIST OF TABLES viii

Chapter 1 Introduction 1
Chapter 2 Whole Breast Ultrasound and Related Pre-processing Techniques 4
2.1 Whole Breast Ultrasound 4
2.2 Related Pre-processing Techniques 7
2.2.1 Anisotropic Diffusion Filtering 7
2.2.2 Sigmoid Filtering 8
Chapter 3 Fuzzy Tumor Detection for Whole Breast Ultrasound Image 10
3.1 Tumor Detection Using Fuzzy Technique 11
3.1.1 Feature Extraction and Membership Function Generation 11
3.1.2 Fuzzification by Fuzzy Reasoning 15
3.1.3 Defuzzification by Relaxation Method 16
3.2 Tumor Criteria 17
3.2.1 Area Size Criterion 18
3.2.2 Width-height Ratio Criterion 18
3.3 Region Comparison between Three Orthogonal Views 19
Chapter 4 Experiments and Results 22
4.1 Experimental Results 22
4.2 Discussion 36
Chapter 5 Conclusion 38

[1] American Cancer Society, "Cancer Facts and Figures 2006," 2006.
[2] B. Cox, "Variation in the effectiveness of breast screening by year of follow-up," J Natl Cancer Inst Monogr, no. 22, pp. 69-72, 1997.
[3] P. Pisani, D.M. Parkin, and J. Ferlay, "Estimates of the worldwide mortality from eighteen major cancers in 1985. Implications for prevention and projections of future burden," Int. J. Cancer, vol. 55, no. 6, pp. 891-903, Dec. 1993.
[4] T.E. Wilson, M.A. Helvie, and D.A. August, "Breast cancer in the elderly patient: early detection with mammography," Radiology, vol. 190, no. 1, pp. 203-207, Jan. 1994.
[5] M.A. Roubidoux, M.A. Helvie, N.E. Lai, and C. Paramagul, "Bilateral breast cancer: early detection with mammography," Radiology, vol. 196, no. 2, pp. 427-431, Aug. 1995.
[6] E.A. Sickles, R.A. Filly, and P.W. Callen, "Benign breast lesions: ultrasound detection and diagnosis," Radiology, vol. 151, no. 2, pp. 467-470, May 1984.
[7] T.M. Kolb, J. Lichy, and J.H. Newhouse, "Comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: an analysis of 27,825 patient evaluations," Radiology, vol. 225, no. 1, pp. 165-175, Oct. 2002.
[8] N.F. Boyd et al., "Heritability of mammographic density, a risk factor for breast cancer," N. Engl. J. Med., vol. 347, no. 12, pp. 886-894, Sept. 2002.
[9] P. Crystal, S.D. Strano, S. Shcharynski, and M.J. Koretz, "Using sonography to screen women with mammographically dense breasts," AJR Am. J. Roentgenol., vol. 181, no. 1, pp. 177-182, July 2003.
[10] K. Flobbe et al., "The role of ultrasonography as an adjunct to mammography in the detection of breast cancer. a systematic review," Eur. J. Cancer, vol. 38, no. 8, pp. 1044-1050, May 2002.
[11] K.J. Taylor et al., "Ultrasound as a complement to mammography and breast examination to characterize breast masses," Ultrasound Med. Biol., vol. 28, no. 1, pp. 19-26, Jan. 2002.
[12] W.K. Moon, D.Y. Noh, and J.G. Im, "Multifocal, multicentric, and contralateral breast cancers: bilateral whole-breast US in the preoperative evaluation of patients," Radiology, vol. 224, no. 2, pp. 569-576, Aug. 2002.
[13] Chang-Chien KC, Chang RF, Chen DR, Takada E, and Moon WK, "Free-hand Whole Breast Ultrasound Computer-aided Screening," in Engineering Technology and Applications on Chinese and Western Medicine, Taichung, Taiwan, 2004, pp. 105.
[14] Chang-Chien KC, Chang RF, Chen DR, Takada E, and Moon WK, "Computer-aided Detection Using Free-Hand Ultrasound for Whole Breast Screening," in Computer Vision, Graphics and Image Processing, Hualien, Taiwan, 2004, pp. B3-1.
[15] A. Rakotomamonjy, P. Deforge, and P. Marche, "Wavelet-based speckle noise reduction in ultrasound B-scan images," Ultrason. Imaging, vol. 22, no. 2, pp. 73-94, Apr. 2000.
[16] E. Marom, S. Kresic-Juric, and L. Bergstein, "Speckle noise in bar-code scanning systems--power spectral density and SNR," Appl. Opt., vol. 42, no. 2, pp. 161-174, Jan. 2003.
[17] P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 7, pp. 629-639, July 1990.
[18] J.M. Thijssen, B.J. Oosterveld, and R.F. Wagner, "Gray level transforms and lesion detectability in echographic images," Ultrason. Imaging, vol. 10, no. 3, pp. 171-195, July 1988.
[19] F.K.H. Quek and C. Kirbas, "Vessel extraction in medical images by wave-propagation and traceback," IEEE Trans. Med. Imaging, vol. 20, no. 2, pp. 117-131, 2001.
[20] L.A.Zadeh, "Fuzzy algorithms," Info. Control, vol. 12 pp. 94-102, 1968.
[21] X.Y. Cheng, A.Ohya., M. Natori, and M. Nakajima, "Boundary extraction method for three dimensional ultrasonic echo imaging using fuzzy reasoning and relaxation techniques," in Nuclear Science Symposium and Medical Imaging Conference, 1993., 1993 IEEE Conference Record., 1993, pp. 1610-1614.
[22] X.Y. Cheng et al., "Breast tumor diagnosis system using three dimensional ultrasonic echography," in Engineering in Medicine and Biology society, 1997.Proceedings of the 19th Annual International Conference of the IEEE, 1997, pp. 517-520.
[23] R.A.Hummel and S.W.Zucker, "On the foundation of relaxation labeling processes," IEEE Trans. PAMI, vol. 5, no. 3, pp. 259-288, 1983.
[24] A.Ronsenfeld, R.A.Hummel, and S.W.Zucker, "Scene labeling by relaxation operations," IEEE Trans. Syst. , Man. , and Cybern., vol. SMC-6, pp. 420-433, June 1976.
[25] S.W.Zucker, R.A.Hummel, and A.Ronsenfeld, "An application of relaxation labeling to line and curve enhancement," IEEE Trans. Computer, vol. C-26, pp. 394-403, Apr. 1977.
[26] K.Z. Abd-Elmoniem, A.B.M. Youssef, and Y.M. Kadah, "Real-time speckle reduction and coherence enhancement in ultrasound imaging via nonlinear anisotropic diffusion," IEEE Trans. Biomedical Engineering, vol. 49, no. 9, pp. 997-1014, Sept. 2002.
[27] K. Horsch, M.L. Giger, C.J. Vyborny, and L.A. Venta, "Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography," Acad. Radiol., vol. 11, no. 3, pp. 272-280, Mar. 2004.
[28] M.L. Giger et al., "Computerized analysis of lesions in US images of the breast," Acad. Radiol., vol. 6, no. 11, pp. 665-674, Nov. 1999.
[29] H. Tang, T. Zhuang, and E.X. Wu, "Realizations of fast 2-D/3-D image filtering and enhancement," IEEE Trans. Med. Imaging, vol. 20, no. 2, pp. 132-140, Feb. 2001.
[30] R.C. Gonzalez and R.E. Woods, Digital Image Processing , Second ed. Reading, MA: Addison-Wesley, 1992.
[31] R.N. Czerwinski, D.L. Jones, and W.D. O'Brien, Jr., "Detection of lines and boundaries in speckle images-application to medical ultrasound," IEEE Trans. Med. Imag., vol. 18, no. 2, pp. 126-136, Feb. 1999.
[32] R.N. Czerwinski, D.L. Jones, and W.D. O'Brien, Jr., "Line and boundary detection in speckle images," IEEE Trans. Image Process, vol. 7, no. 12, pp. 1700-1714, Dec. 1998.
[33] S. Yu and L. Guan, "A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films," IEEE Trans. Med. Imaging, vol. 19, no. 2, pp. 115-126, Feb. 2000.