臺灣博碩士論文加值系統

根據衛生署資料統計，乳癌是台灣女性主要死因之一，偵測與預測乳房惡性腫瘤是值得重視的議題。近年來大多使用非侵入式的超音波影像對病人做檢查，尤其在三維全乳房超音波攝影(Whole Breast Ultrasound Imaging)問世之後，它提供了完整的三維乳房解剖構造，有助於醫生為病人診斷。根據研究顯示，乳房密度越高的女性，越容易罹患乳癌。乳房密度計算是預測乳癌的主要指標之一，但由於乳房超音波的雜訊高，三維資料量大，用人工計算乳房密度更顯得吃力，因此本研究將對乳房組織依其音波回音性的高低進行分割。
為了解決超音波影像中模糊的邊界、雜訊高以及灰階質不同質性(intensities in-homogeneity)等問題，本實驗利用改進的等位函數法(Level Set Method)演算法，依照不同組織的音波回音性進行分割。另外，某些區域的乳房組織會被乳頭陰影遮蔽，影響分割的結果。所以本實驗目的除了圈出乳腺組織外，再針對被陰影遮蔽的部分，對Region Based的Variational Level Set Model加入概率的概念做改進，使其能夠反應區域內部灰階值的統計性質，從而取得更準確的分割結果。假設在影像中，局部區域的灰階值呈高斯分佈(Gaussian Distributions)，我們提出改進的基於概率的Level Set Method，此種LSM的能量包含三個變數函數：灰階值平均(mean)，偏移場(bias field)和變異數(variance)。通過能量極小化，使輪廓達到最佳分割。能量極小化是通過交錯更新Level Set Function和求得灰階值、偏移場和變異數的最佳值。模型本身具有計算偏移場(Bias field)的函數，分割的同時可以完成影像校正(Bias Correction)。本論文通過對區域變異數的全域化，進一步改進模型，並通過實驗說明全域變異數和區域變異數的差別。其中全域變異數模型的速度大幅改進。
本實驗採用由台北榮民總醫院提供的U-system全乳房超音波影像，選出正常乳房組織、乳房組織較少和有異常區塊的影像做分割。本實驗的模型，可描繪乳腺組織模糊的邊界，並找出部分被陰影遮蔽較暗的乳腺組織，且對整張影像做偏移場校正。

According to the statistic from Department of Health, breast cancer is one of the leading causes of cancer death among Taiwanese women. Medical research has shown that women with higher breast density have higher incidence of breast cancer. Therefore, estimation of breast density is worth paying more attention. Ultrasound imaging is one of the most important imaging modalities to diagnose breast cancer. Three-dimensional (3D) whole breast ultrasound imaging has been intensively studied, as it provides completed 3D anatomy of breast, which is helpful for diagnosis. However, it is difficult to manually segment the image for the calculation of the breast density, especially for a tremendous amount of data. Therefore, this thesis proposed a model to segment breast parenchyma on whole breast ultrasound images.
Blurry object boundaries and inhomogeneity of image intensities on ultrasound images have been a great challenge for automatic image segmentation. In addition, some parts of breast tissues are covered by shadow of nipple, which causes considerable error in the segmentation. To overcome these difficulties, we use a Variational Level Set Method for image segmentation.
In our work, the level set method is formulated in a probabilistic model, which is able to take into account the statistical property of the intensities in each region to be segmented. In our improved model, the local image intensities are described by Gaussian distributions, which are used to define the energy functional in a level set formulation. The energy minimization is achieved by level set evolution and estimation of mean, bias field and variances in an iterative process. The bias field and variances of intensities are taken into account in our method for segmentation and bias correction. Furthermore, by globalizing the variance parameter, our model computationally more efficient.
This thesis uses U-system whole breast ultrasound images, and these images include the cases with normal parenchyma、less parenchyma and abnormal region. Our model can depict the blurred boundaries of parenchyma 、find parts of parenchyma which is in shadowed area and correct bias field on entire image.

誌 謝.............................................................................................................................. 1
中文摘要........................................................................................................................ 2
Abstract .......................................................................................................................... 4
圖目錄............................................................................................................................ 7
表目錄............................................................................................................................ 8
第一章 緒論............................................................................................................ 9
1.1 研究背景.......................................................................................................... 9
1.2 研究動機........................................................................................................ 10
1.2.1 全乳房超音波攝影（whole breast ultrasound imaging） ................ 10
1.2.2 乳房密度(breast density)計算 ............................................................ 12
1.3 文獻回顧....................................................................................................... 13
1.4 研究目的....................................................................................................... 14
1.5 研究架構........................................................................................................ 16
第二章 基礎理論.................................................................................................. 17
2.1 一般曲線運動(General Curve Evolution) .................................................... 17
2.1.1 動態輪廓線(Dynamic Curves) .......................................................... 19
2.1.2 幾何式主動輪廓(Geometric Curve Evolution) ................................ 19
2.2 等位函數法(Level Set Method) ................................................................... 20
2.2.1 由輪廓運動方式推導......................................................................... 22
2.2.2 定義能量並且求Gradient flow ......................................................... 23
2.2.3 等位函數法的標準流程.................................................................... 25
第三章 研究材料及方法...................................................................................... 27
3.1 Piecewise Constant Model ............................................................................. 27
3.2 灰階不同質性影像模型............................................................................... 29
3.3 同時分割和偏移場估計之等位函數法....................................................... 29
3.3.1 同時分割和偏移場估計之等位函數法-基本概念 ........................... 30
3.3.2 同時分割和偏移場估計之等位函數法-能量和演化方程式 ........... 32
3.4 同時分割和偏移場估計之基於概率等位函數法-能量定義 ...................... 37
3.4.1 同時分割和偏移場估計之基於概率等位函數法-演化方程式 ....... 40
3.5 基於概率模型中變異數函式特殊情形....................................................... 45
3.5.1 全域性變異數和演化方程式............................................................ 45
3.5.2 固定常數變異數................................................................................ 48
3.5.3 變異數均相等.................................................................................... 49
3.6 實驗流程....................................................................................................... 49
第四章 研究成果與討論...................................................................................... 51
4.1 模型之間的差別........................................................................................... 51
7
4.2 二維全乳房超音波影像實驗整體問題討論............................................... 52
4.3 三維全乳房超音波影像結果與討論........................................................... 61
第五章 未來展望.................................................................................................. 74
Reference ..................................................................................................................... 76

[1]行政院衛生署。民國97年死因統計結果分析.
[2]P. Pisani, et al., "Estimates of the worldwide mortality from eighteen major cancers in 1985. Implications for prevention and projections of future burden," Int J Cancer, vol. 55, pp. 891-903, Dec 2 1993.
[3]ACS, "Breast cancer facts and figures 2005-2006," American Cancer Society, 2007.
[4]Y. Zheng, et al., "Reduction of breast biopsies with a modified self-organizing map," IEEE Trans Neural Netw, vol. 8, pp. 1386-96, 1997.
[5]L. W. Bassett, et al., "Usefulness of mammography and sonography in women less than 35 years of age," Radiology, vol. 180, pp. 831-5, Sep 1991.
[6]A. T. Stavros, et al., "Solid Breast Nodules - Use of Sonography to Distinguish Benign and Malignant Lesions," Radiology, vol. 196, pp. 123-134, Jul 1995.
[7]P. Skaane and K. Engedal, "Analysis of sonographic features in the differentiation of fibroadenoma and invasive ductal carcinoma," American Journal of Roentgenology, vol. 170, pp. 109-114, Jan 1998.
[8]N. F. Boyd, et al., "Heritability of Mammographic Density, a Risk Factor for Breast Cancer," N Engl J Med, vol. 347, pp. 886-894, September 19 2002.
[9]V. A. McCormack and I. dos Santos Silva, "Breast Density and Parenchymal Patterns as Markers of Breast Cancer Risk: A Meta-analysis," Cancer Epidemiology Biomarkers & Prevention, vol. 15, pp. 1159-1169, June 2006.
[10] N. F. Boyd, et al., "Mammographic breast density as an intermediate phenotype for breast cancer," The Lancet Oncology, vol. 6, pp. 798-808, 2005.
[11] N. F. Boyd, et al., "Mammographic density and the risk and detection of breast cancer," N Engl J Med, vol. 356, pp. 227-36, Jan 18 2007.
[12] K. Kerlikowske, et al., "Variability and accuracy in mammographic interpretation using the American College of Radiology Breast Imaging Reporting and Data System," J. Natl. Cancer Inst., vol. 90, pp. 1801-1809, December 2, 1998 1998.
[13] N. F. Boyd, et al., "The association of breast mitogens with mammographic densities," Br J Cancer, vol. 87, pp. 876-82, Oct 7 2002.
[14] J. Brisson, et al., "Tamoxifen and Mammographic Breast Densities," Cancer Epidemiology Biomarkers & Prevention, vol. 9, pp. 911-915, September 2000.
[15] J. Cuzick, et al., "Tamoxifen and Breast Density in Women at Increased Risk of Breast Cancer," J. Natl. Cancer Inst., vol. 96, pp. 621-628, April 21 2004.
[16] G. A. Greendale, et al., "The Association of Endogenous Sex Steroids and Sex Steroid Binding Proteins with Mammographic Density: Results from the Postmenopausal Estrogen/Progestin Interventions Mammographic Density Study," Am. J. Epidemiol., vol. 162, pp. 826-834, November 1 2005.
[17] G. A. Greendale, et al., "Postmenopausal Hormone Therapy and Change in Mammographic Density," J. Natl. Cancer Inst., vol. 95, pp. 30-37, January 1 2003.
[18] J. J. Heine and P. Malhotra, "Mammographic Tissue, Breast Cancer Risk, Serial Image Analysis, and Digital Mammography: Part 2. Serial Breast Tissue Chage and Related Temporal Influences," Academic Radiology, vol. 9, pp. 317-335, 2002.
[19] H. Li, et al., "Fractal Analysis of Mammographic Parenchymal Patterns in Breast Cancer Risk Assessment," Academic Radiology, vol. 14, pp. 513-521, (2007).
[20] M. T. Mandelson, et al., "Breast Density as a Predictor of Mammographic Detection: Comparison of Interval- and Screen-Detected Cancers," J. Natl. Cancer Inst., vol. 92, pp. 1081-1087, July 5 2000.
[21] G. Ursin, et al., "Mammographic Density and Breast Cancer in Three Ethnic Groups," Cancer Epidemiology Biomarkers & Prevention, vol. 12, pp. 332-338, April 2003.
[22] J.-H. Chen, et al., "Breast density analysis for whole breast ultrasound images," Medical Physics, vol. 36, pp. 4933-4943, 2009.
[23] M. J. Gooding, et al., "Automatic mammary duct detection in 3D ultrasound," presented at the MICCAI 2005, 2005.
[24] Y. Ikedo, et al., "Automated analysis of breast parenchymal patterns in whole breast ultrasound images: preliminary experience," International Journal of Computer Assisted Radiology and Surgery, vol. 4, pp. 299-306, 2009.
[25] R. M. Haralick, et al., "Textural Features for Image Classification," IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics vol. 3, pp. 610-621, 1973.
[26]Stanley Osher, Ronald P. Fedkiw, Level set methods and dynamic implicit surfaces, pp23-142
[27]T. Chan and L. Vese, Active contours without edges. IEEE Trans. Imag. Proc.,10(2):266–277, February 2001.
[28]C. Li, Research on Level Set Methods, http://www.engr.uconn.edu/~cmli/research/
[29] Lewis, E., Fox, N.: Correction of differential intensity inhomogeneity in longitudinal MR
[30] Dawant, B., Zijdenbos, A., Margolin, R.: Correction of intensity variations in MR images for computer-aided tissues classification. IEEE Trans. Med. Imag. 12(4), 770–781 (1993)
[31] Meyer, C., Bland, P., Pipe, J.: Retrospective correction of intensity inhomogeneities in MRI. IEEE Trans. Med. Imag. 14(1), 36 (1995)
[32] Sled, J., Zijdenbos, A., Evans, A.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans. Med. Imaging 17(1), 87–97 (1998)
[33] C. Li, C. Kao, J. C. Gore, and Z. Ding, "Implicit Active Contours Driven by Local Binary Fitting Energy", in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Washington, DC, USA, 2007, pp. 1–7.
[34] C. Li, R. Huang, Z. Ding, C. Gatenby, D. N. Metaxas, and J. C. Gore, "A Variational Level Set Approach to Segmentation and Bias Correction of Images with Intensity Inhomogeneity", MICCAI vol.LNCS 5242, pp 1083-1091,2008.
[35]Paragios and Deriche, Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation, International Journal of Computer Vision , 46(3), pp 223-247, (2002).
[36] Daniel Cremers, A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape, International Journal of Computer Vision , 72(2), pp 195-215, (2007)