臺灣博碩士論文加值系統

腫瘤生長與新血管增生之間的關係是幫助醫生診斷腫瘤發展結果一個重要的現象。與乳癌相關的血管新生作用近幾年已經被廣泛研究，也被證實與腫瘤的生長、惡化與轉移過程中扮演著重要的角色。以往的相關研究，只利用血管數的多寡來診斷腫瘤，而本篇論文將著重於血管相對於腫瘤的位置關係來診斷腫瘤，例如新血管是否位於腫瘤內。為了量化這些新提出的特徵，腫瘤區域首先必須切割出來，以利分析血管與腫瘤位置之關係。本篇論文提出電腦輔助診斷系統將使用乳房3-D 彩色都卜勒(Doppler)超音波成像技術，3-D 彩色都卜勒超音波的資料可被解碼成兩種連續的影像，分別是紀錄腫瘤結構的灰階影像與保存血管資訊的血管影像。灰階影像將利用模糊理論演算法及連結區塊標記法決定出腫瘤區域。決定腫瘤區域後，再利用血管影像計算出在相對應的區域中的血管點數。綜合以上的技術，本篇論文取出了如下的特徵：腫瘤體積，血管體積，血管與總體積的比例，腫瘤內部血管與腫瘤的比例，腫瘤外部血管與腫瘤的外部正常組織比例及腫瘤周圍血管與此範圍體積比例。最後，使用神經網路來結合以上的特徵運用在乳房腫瘤的診斷。本篇論文總共分析223個有乳房腫瘤的病例，其中包含115個良性腫瘤和108個惡性腫瘤。本篇論文所提出的系統正確率為85.20 %。

The correlation between tumor growth and angiogenesis is an important phenomenon that helps physicians to analyze the disease. Tumor angiogenesis has been widely studied in recent years and proved as a key role in tumor growth, invasion, and metastasis. In the past researches, only the vessel information is used to diagnose the tumor. However, the location of vessel related to the tumor, for example whether the vessel is inside the tumor or not, is proposed in this paper. In order to extract the new proposed features, the tumor regions should be segmented for capturing the information in and out tumor. This paper presents a computer-aided diagnostic (CAD) system that analyzes the relation between blood vessels and tumor using 3-D power Doppler ultrasound (US) for breast cancer. These 3-D power Doppler ultrasound datasets could be decoded into two kinds of sequential images, grey and vessel images. Grey images are applied by a fuzzy unit, a defuzzier unit, and connected component labeling techniques to determine tumor VOI (volume of interest). Vessel images are used to capture vessel blood voxels corresponding to the segmented tumor. This study of 3-D assessment of the correlation between blood vessels and tumor using the volumes of tumor and vessels, the ratio of vessel voxels and volume voxels, the ratio of vessel voxels inside tumor region, the ratio of vessel voxels outside tumor region, the ratio of vessel voxels around tumor region. Finally, these extracted features for all training datasets are put into the neural network and then the training process is computed. The trained neural network is then used for breast tumor diagnosis. For 223 solid breast rumors including 115 benign and 108 malignant cases, the accuracy of neural network using proposed features is 85.20 %.

摘　　要 i
ABSTRACT iii
TABLE OF CONTENT v
ACKNOWLEDGEMENTS vi
LIST OF FIGURES vii
LIST OF TABLES x


Chapter 1 Introduction 1
Chapter 2 Background and Related Preprocessing Techniques 4
2.1 3-D Ultrasound Datasets 4
2.2 Pre-processing 8
2.2.1 Histogram Equalization 8
2.2.2 Sigmoid Filter 9
2.2.3 Anisotropic Diffusion Filter 10
Chapter 3 The proposed CAD system 12
3.1 Tumor Extraction 13
3.1.1 Fuzzy Feature Parameters 14
3.1.2 Fuzzy Unit 17
3.1.3 Relaxation Techniques 19
3.2 3-D Connected Components 20
3.3 Shadow Reduction 22
3.4 Vessel Extraction 22
3.5 Features Extraction 23
Chapter 4 Experiments and Discussion 26
4.1 Experimental Results 26
4.2 ROC Curve 31
4.3 Neural Network 35
Chapter 5 Conclusion 40

[1] R.A. Smith, V. Cokkinides, and H.J. Eyre, "American Cancer Society Guidelines for the Early Detection of Cancer, 2005," CA Cancer J. Clin., vol. 55, no. 1, pp. 31-44, Jan. 2005.
[2] L. Carey, "Breast Cancer Facts & Figures 2005-2006.," The Journal of the American Medical Association, vol. 295 pp. 2492-2502, June 2006.
[3] A. Jemal et al., "Cancer statistics, 2005," CA Cancer J. Clin., vol. 55, no. 1, pp. 10-30, Jan. 2005.
[4] J. Folkman, "What is the evidence that tumors are angiogenesis dependent?," J. Natl. Cancer Inst., vol. 82 pp. 4-6, 1990.
[5] M.K. Gupta and R.Y. Qin, "Mechanism and its regulation of tumor-induced angiogenesis," World J. Gastroenterol., vol. 9, no. 6, pp. 1144-1155, June 2003.
[6] S. Montero, C. Guzman, H. Cortes-Funes, and R. Colomer, "Angiogenin expression and prognosis in primary breast carcinoma," Clin. Cancer Res., vol. 4, no. 9, pp. 2161-2168, Sept. 1998.
[7] D.Hanahan and J.Folkman, "Patterns and Emerging Mechanisms of the Angiogenic Switch during Tumorigenesis.," Cell, vol. 86, no. 3, pp. 353-364, Aug. 19960.
[8] 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.
[9] 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.
[10] L.W. Bassett, M. Ysrael, R.H. Gold, and C. Ysrael, "Usefulness of mammography and sonography in women less than 35 years of age," Radiology, vol. 180, no. 3, pp. 831-835, Sept. 1991.
[11] 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.
[12] 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.
[13] 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.
[14] 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.
[15] S.G. Orel and M.D. Schnall, "MR imaging of the breast for the detection, diagnosis, and staging of breast cancer," Radiology, vol. 220, no. 1, pp. 13-30, July 2001.
[16] S.G. Orel et al., "MR imaging-guided localization and biopsy of breast lesions: initial experience," Radiology, vol. 193, no. 1, pp. 97-102, Oct. 1994.
[17] S.W. Smith et al., "Feasibility study: real-time 3-D ultrasound imaging of the brain," Ultrasound Med. Biol., vol. 30, no. 10, pp. 1365-1371, Oct. 2004.
[18] G.M. Treece, A.H. Gee, R.W. Prager, C.J. Cash, and L.H. Berman, "High-definition freehand 3-D ultrasound," Ultrasound Med. Biol., vol. 29, no. 4, pp. 529-546, Apr. 2003.
[19] P.L. Carson et al., "The 3D and 2D color flow display of breast masses," Ultrasound Med. Biol., vol. 23, no. 6, pp. 837-849, 1997.
[20] 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.
[21] Cheng X.-Y., Ohya A., 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] Rosenfeld A and Pfaltz J.L., "Sequential Operations in digital Processing," JACM, vol. 13 pp. 471-494, 1966.
[23] A. Rosenfeld and A.C. Kak, Digital Picture Processing, 2 ed., New York: Academic Press, Inc., 1982.
[24] W.M. Chen, R.F. Chang, W.K. Moon, and D.R. Chen, "Breast cancer diagnosis using three-dimensional ultrasound and pixel relation analysis," Ultrasound Med. Biol., vol. 29, no. 7, pp. 1027-1035, July 2003.
[25] R.F. Chang, W.J. Wu, W.K. Moon, and D.R. Chen, "Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis," Ultrasound Med. Biol., vol. 29, no. 5, pp. 679-686, May 2003.
[26] W.J. Kuo, R.F. Chang, W.K. Moon, C.C. Lee, and D.R. Chen, "Computer-aided diagnosis of breast tumors with different US systems," Acad. Radiol., vol. 9, no. 7, pp. 793-799, July 2002.
[27] K. Drukker, M.L. Giger, C.J. Vyborny, and E.B. Mendelson, "Computerized detection and classification of cancer on breast ultrasound," Acad. Radiol., vol. 11, no. 5, pp. 526-535, May 2004.
[28] K. Drukker et al., "Computerized lesion detection on breast ultrasound," Med. Phys., vol. 29, no. 7, pp. 1438-1446, July 2002.
[29] K. Horsch, M.L. Giger, L.A. Venta, and C.J. Vyborny, "Computerized diagnosis of breast lesions on ultrasound," Med. Phys., vol. 29, no. 2, pp. 157-164, Feb. 2002.
[30] R.C. Gonzalez and R.E. Woods, Digital Image Processing, 2 ed. NJ: Prentice Hall, 1992.
[31] 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.
[32] 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.
[33] M.A. Quinones, C.M. Otto, M. Stoddard, A. Waggoner, and W.A. Zoghbi, "Recommendations for quantification of Doppler echocardiography: a report from the Doppler Quantification Task Force of the Nomenclature and Standards Committee of the American Society of Echocardiography," J. Am. Soc. Echocardiogr., vol. 15, no. 2, pp. 167-184, Feb. 2002.
[34] A. Fenster, D.B. Downey, and H.N. Cardinal, "Three-dimensional ultrasound imaging," Phys. Med. Biol., vol. 46, no. 5, pp. R67-R99, May 2001.
[35] Peter N.T.Wells, "Basic principles and Doppler physics," in Clinical applications of Doppler ultrasound, Kenneth J.W.Taylor, Peter N.Burns, and Peter N.T.Wells (eds.) 2 ed. New York: NY: Raven, 1995, pp. 1-17.
[36] Peter N.Burns, "Interpreting and analyzing the Doppler examination," in Clinical applications of Doppler ultrasound, Kenneth J.W.Taylor, Peter N.Burns, and Peter N.Burns (eds.) 2 ed. New York: NY: Raven, 1995, pp. 55-98.
[37] C. Martinoli et al., "Power Doppler sonography: clinical applications," Eur. J. Radiol., vol. 27 Suppl 2 pp. S133-S140, May 1998.
[38] JM Rubin, RO Bude, PL Carson, RL Bree, and RS Adler, "Power Doppler US: a potentially useful alternative to mean frequency- based color Doppler US," Radiology, vol. 190, no. 3, pp. 853-856, Mar. 1994.
[39] A. Kondo, K. Akakura, and H. Ito, "Assessment of renal function with color Doppler ultrasound in autosomal dominant polycystic kidney disease," Int. J. Urol., vol. 8, no. 3, pp. 95-98, Mar. 2001.
[40] C. Martinoli et al., "Power Doppler sonography: clinical applications," Eur. J. Radiol., vol. 27 Suppl 2 pp. S133-S140, May 1998.
[41] A. Krivanek and M. Sonka, "Ovarian ultrasound image analysis: follicle segmentation," Medical Imaging, IEEE Transactions on, vol. 17, no. 6, pp. 935-944, 1998.
[42] Y.P. Wang and T. Pavlidis, "Optimal correspondence of string subsequences," IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 11, pp. 1080-1087, 1990.
[43] 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.
[44] E.H. Mamdani, "Application of fuzzy logic to approximate reasoning using linguistic synthesis," IEEE Trans. Comp, vol. C-26 pp. 1182-1191, Dec. 1977.
[45] L.A. Zadeh, "Fuzzy algorithm," Info. Contr., vol. 12 pp. 94-102, 1968.
[46] R.N. Czerwinski, D.L. Jones, and W.D. O'Brien, "Line and boundary detection in speckle images," IEEE Trans. Image Process., vol. 7, no. 12, pp. 1700-1714, Dec. 1998.
[47] C.G. Boncelet, Jr., "Order statistic distributions with multiple windows," Information Theory, IEEE Transactions on, vol. 37, no. 2, pp. 436-442, 1991.
[48] A. Ronsenfeld, R.A. Hummel, and S.W. Zucker, "Scene labeling by relaxation operatioNn," IEEE Trans. Syst. ,Man. , and Cybern., vol. SMC-6 pp. 420-433, Jan. 19760.
[49] J.D. Foley, D.A. Vans, K. Feiner, and J.F. Hughes, "Computer graphics: principle and practice," pp. 610-724, 1990.
[50] R.N. Czerwinski, D.L. Jones, and W.D. O'Brien, "Line and boundary detection in speckle images," IEEE Trans. Image Process., vol. 7, no. 12, pp. 1700-1714, Dec. 1998.
[51] E.H. Mamdani, "Application of fuzzy logic to approximate reasoning using linguistic synthesis," IEEE Trans. Comp, vol. C-26 pp. 1182-1191, Dec. 1977.
[52] C.H. Wu, M.M. Hsu, Y.L. Chang, and F.J. Hsieh, "Vascular pathology of malignant cervical lymphadenopathy: qualitative and quantitative assessment with power Doppler ultrasound," Cancer, vol. 83, no. 6, pp. 1189-1196, Sept. 1998.
[53] M.H. Wu, S.J. Tsai, H.A. Pan, K.Y. Hsiao, and F.M. Chang, "Three-dimensional power Doppler imaging of ovarian stromal blood flow in women with endometriosis undergoing in vitro fertilization," Ultrasound Obstet. Gynecol., vol. 21, no. 5, pp. 480-485, May 2003.
[54] C.H. Wu, M.M. Hsu, Y.L. Chang, and F.J. Hsieh, "Vascular pathology of malignant cervical lymphadenopathy: qualitative and quantitative assessment with power Doppler ultrasound," Cancer, vol. 83, no. 6, pp. 1189-1196, Sept. 1998.
[55] M.K. Markey, G.D. Tourassi, M. Margolis, and D.M. Delong, "Impact of missing data in evaluating artificial neural networks trained on complete data," Comput. Biol. Med., May 2005.
[56] D. Delen, G. Walker, and A. Kadam, "Predicting breast cancer survivability: a comparison of three data mining methods," Artif. Intell. Med., vol. 34, no. 2, pp. 113-127, June 2005.
[57] B.K. Szabo, P. Aspelin, and M.K. Wiberg, "Neural network approach to the segmentation and classification of dynamic magnetic resonance images of the breast: comparison with empiric and quantitative kinetic parameters," Acad. Radiol., vol. 11, no. 12, pp. 1344-1354, Dec. 2004.
[58] A.Lendasse, V.Wertz, and M.Verleysen, "Model selection with cross-validations and bootstraps - Application to time series prediction with RBFN models," ArtificialNeural Networks and Neural Information Processing - ICANN/ICONIP 2003, O.Kaynak, E.Alpaydin, E.Oja, L.Xu eds, Springer-Verlag, Lecture Notes inComputer Science, vol. 2714 pp. 573-580, 2003.
[59] S. Haykin, Neural Networks: A Comprehensive Foundation, 2 ed. NJ: Prentice-Hall, 1999.