進階搜尋


下載電子全文  
系統識別號 U0026-2308201416363800
論文名稱(中文) 應用二維經驗模態分解之乳房攝影特徵分析
論文名稱(英文) Mammographic Feature Characterization Using Two-Dimensional Empirical Mode Decomposition
校院名稱 成功大學
系所名稱(中) 生物醫學工程學系
系所名稱(英) Department of BioMedical Engineering
學年度 102
學期 2
出版年 103
研究生(中文) 陳勁宇
研究生(英文) Chin-Yu Chen
電子信箱 chency@seed.net.tw
學號 p88941039
學位類別 博士
語文別 英文
論文頁數 65頁
口試委員 指導教授-鄭國順
共同指導教授-郭淑美
口試委員-姚維仁
口試委員-孫永年
召集委員-施東河
口試委員-林灶生
中文關鍵字 經驗模態分解  二維經驗模態分解  Radon轉換  數位乳房攝影 
英文關鍵字 empirical mode decomposition  two-dimensional empirical mode decomposition  Radon transform  digital mammography 
學科別分類
中文摘要 經驗模態分解 (empirical mode decomposition, EMD) 是一種自適性的疊代運算法,用來分解非線性或非靜態之變動訊號,以得到不同的頻率成分。雙維度經驗模態分解 (bi-dimensional empirical mode decomposition, BEMD) 則發展成為分解二維影像訊號的方法。但是在BEMD求取上下包絡線的近似運算過程中,傾向於在兩個主要維度的運算,導致像素之間在不同角度的變化關係,其考量有所限制或不足。我們因此提出一個不同於BEMD的二維運算方式來解決這個現象,成功發展出新的二維經驗模態分解 (2DEMD) 方式,並且用於分析乳房X光攝影的影像特徵,以及病變影像的強化。
本研究所提出的2DEMD運算方式,是結合二維影像投影及反投影重建技術,先使用Radon transform將二維的影像,經由投影在不同的角度上,降階為一維的線性訊號。接下來,我們可以使用傳統的一維經驗模態分解(1DEMD)運算,得到多個一維的內部模態函數(intrinsic mode function, IMF)。最後藉由inverse Radon transform反投影之影像重建技術,將不同角度的一維IMF重建為二維IMF影像,如此可完成2DEMD的運算。為了將這個技術應用於乳房X光攝影,我們收集了一些不同型態的數位乳房X光攝影影像,包括不同乳腺緻密度的正常乳房影像,以及各種常見的良惡性病變影像,以2DEMD加以分析,並判讀其影像特徵在各個不同IMF的分佈呈現方式。
正常的乳腺組織集中出現在中頻部分的內部模態函數,IMF4到IMF6之間。以細線條表現的棘狀邊緣 (spiculated margin) 及結構扭曲 (architectural distortion),則是集中呈現在較高頻的IMF2及IMF3。粗線條出現在接下來的IMF4。細微鈣化(microcalcifications)以及粗鈣化的邊緣,則是集中出現在最高頻的成分IMF1及IMF2,小粗鈣化接著出現在IMF3,大粗鈣再接下來出現在IMF4。不論是良性或惡性腫瘤本身,都集中出現在中低頻的成分IMF5及IMF6。
在本研究中,我們成功的整合影像投影及重建技術,提出一個新的二維經驗模態分解運算法,並且第一次應用新的2DEMD的技術,將乳房X光攝影的正常腺體結構及病變影像,加以歸類及分析,得到正常乳腺組織及常見的良惡性病變的IMF特徵,並成功應用於病變的影像強化,可用於增強病變影像的視覺感知,預期將有助於困難病變的影像診斷,並對後續乳房攝影的相關研究,提供基本的貢獻。
英文摘要 Empirical mode decomposition (EMD) is a self adaptive method that decomposes non-linear non-stationary signals into different frequency components. Bi-dimensional EMD (BEMD) is introduced to deal with the image data in a two-dimensional space. However, with BEMD, the counting of pixel relationship is constrained within two (x and y) or limited directions during the interpolation of upper and lower envelopes. Hence we propose a new two-dimensional method to solve the situation. The new 2DEMD algorithm has been successfully developed and applied in digital mammography to analyze image features, and for lesion enhancement.

The new 2DEMD we proposed in this paper combines the techniques of image projection / back-projection and conventional 1DEMD. Radon Transform is used to project the two-dimensional image into one-dimensional space in every angle. Subsequently, we apply the conventional EMD in one-dimensional space to get the intrinsic mode functions (IMFs). Then inverse Radon Transform is used to rebuild the two-dimensional IMFs to accomplish the 2DEMD calculations. In order to validate the utility of this method, normal mammography images with different densities and abnormal mammography with a variety of lesions were collected. These images were then interpreted and analyzed in terms of their IMF distribution.

Normal fibroglandular tissue is mainly seen in IMF4 to IMF6, the middle frequency components. The thin lines of spiculated margin and architectural distortion are mainly visible in high frequency components, namely IMF2 and IMF3. Thick lines are visible in subsequent IMF4. Microcalcifications and margins of coarse calcifications are mainly visible in IMF1 and IMF2, followed by small coarse calcifications in IMF3, and larger coarse calcifications in IMF4. Masses of either benign or malignant nature are mainly visible in IMF5 and IMF6.

Using a combination of Radon transform and empirical mode decomposition, we successfully establish a new 2DEMD technique to tackle the problematic pixel relationship in different angles. This novel 2DEMD technique allows us to characterize the IMF features of normal structures and lesions. Furthermore, these features can be used to enhance the mammographic lesions for better visual perception. This achievement will contribute to mammographic imaging diagnosis, and also provide the fundamental EMD concepts for future research in mammography.
論文目次 Abstract in Chinese (中文摘要) I
Abstract III
Acknowledgement (誌謝) V
Contents VI
List of Figures VIII
List of Tables X
-----------------------------------------------------------
1 Introduction
1.1 Breast density in mammography 1
1.1.1 Breast density classification 1
1.1.2 Breast density and cancer risk 3
1.1.3 Factors affect breast density 4
1.2 Cross-population breast cancer incidences 7
1.3 Measurement of breast density 9
1.3.1 Qualitative assessment of breast density 9
1.3.2 Quantitative measurement of breast density 11
1.4 Breast lesions in mammography 12
1.5 Empirical mode decomposition 14
1.5.1 The EMD algorithm 14
1.5.2 BEMD and 2DEMD 18
1.5.3 EMD and mammography 19
1.6 Radon transform 20
1.7 Objectives of the present study 24
2 Materials and Methods
2.1 Two dimensional empirical mode decomposition (2DEMD) 26
2.2 Image Preparation 28
2.3 Verification of 2DEMD 29
2.4 Image interpretation and feature characterization 30
2.5 Statistical analysis of the IMF features 31
3 Results and Discussion
3.1 2DEMD versus BEMD 32
3.2 IMF distribution for normal breast and lesion types 34
3.3 IMF presentation of normal mammography and lesion types 36
3.3.1 Normal mammography 36
3.3.2 Benign coarse calcifications 39
3.3.3 Microcalcifications 40
3.3.4 Benign circumscribed mass 42
3.3.5 Malignant speculated mass 43
3.3.6 Malignant mass with microcalcifications 45
3.3.7 Architectural distortion 47
3.4 IMF based lesion enhancement
3.4.1 Benign coarse calcifications 49
3.4.2 Microcalcifications 50
3.4.3 Benign circumscribed mass 51
3.4.4 Subtle malignant mass 52
3.4.5 Architectural distortion 53
4 Conclusions and future works 54
References 56
Appendix 59
參考文獻 1. American College of Radiology (ACR). Breast Imaging Reporting and Data System (BI-RADS) - Mammography, 4th ed. Reston, VA. American College of Radiology, 2003.
2. American College of Radiology (ACR). Breast Imaging Reporting and Data System (BI-RADS) - Mammography, 5th ed. Reston, VA. American College of Radiology, 2013.
3. Wolfe JN. Breast patterns as an index of risk of developing breast cancer. Am J Roentgenol 1976, 126:1130-1139.
4. Wolfe JN. Risk for breast cancer development determined by mammographic parenchymal pattern. Cancer 1976, 37:2486-2492.
5. Harvey JA, Bovbjerg VE. Quantitative assessment of mammographic breast density: relationship with breast cancer risk. Radiology 2004, 230(1): 29-41.
6. McCormack VA, dos Santos Silva I. Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis. Cancer Epidemiol Biomarkers Prev 2006, 15: 1159-1169.
7. Boyd NF, Guo H, Martin LJ, Sun L, Stone J, et al. Mammographic density and the risk and detection of breast cancer. N Engl J Med 2007, 356:227-236.
8. Maskarinec G, Pagano I, Lurie G, Kolonel LN. A longitudinal investigation of mammographic density: the multiethnic cohort. Cancer Epidemiol Biomarkers Prev. 2006; 15(4): 732-739.
9. Kelemen LE, Pankratz VS, Sellers TA, Brandt KR, Wang A, et al. Age-specific Trends in Mammographic Density. The Minnesota breast cancer family study. Am J Epidemiol. 2008; 167:1027-1036.
10. del Carmen MG, Halpern EF, Kopans DB, Moy B, Moore RH, et al. Mammographic breast density and race. Am J Roentgenol. 2007; 188:1147-1150.
11. Chen CY, Li YZ, Guo SM, Cheng KS. Mammography Density Analysis of Taiwanese Women. Asian Breast Disease Association (ABDA) Conference. 2013, Taipei, Taiwan.
12. Ooms EA, Zonderland HM, Eijkemans MJC, Kriege M, Mahdavian Delavary B, et al. Mammography: interobserver variability in breast density assessment. The Breast. 2007; 16:568-576.
13. Byng JW, Yaffe MJ, Jong RA, Shumak RS, Lockwood GA, et al. Analysis of mammographic density and breast cancer risk for digitized mammograms. RadioGraphics. 1998; 18(6): 1587-1598.
14. Oliver A, Freixenet J, Marti R, Pont J, Perez E, et al. A novel breast tissue density classification methodology. IEEE Transactions on Information Technology in Biomedicine. 2008; 12(1): 55-65.
15. Chen Z, Denton ERE, Zwiggelaar R. Topographic representation based breast density segmentation for mammographic risk assessment. IEEE ICIP 2012; 1993-1996.
16. Boehm HF, Schneider T, Buhmann-Kirchhoff SM, Schlossbauer T, Rjosk-Dendorfer D, et al. Automated classification of breast parenchymal density: topologic analysis of x-ray attenuation patterns depicted with digital mammography. Am J Roentgenol 2008; 191: W275-282.
17. Bhuiyan SMA, Adhami RR, Khan JF. Fast and adaptive bidimensional empirical mode decomposition using order-statistics filter based envelope estimation. The European Association for Signal Processing Journal on Advances in Signal Processing. 2008; 3:1-18.
18. Chen CY, Guo SM, Tsai JSH, Li YZ, Cheng KS. Effective breast density segmentation: empirical mode decomposition. (Submitted, 2013)
19. Yaffe MJ. Review mammographic density- measurement of mammographic density. Breast Cancer Research. 2008;10(3): 209-218.
20. van Engeland S, Snoeren PR, Huisman H, Boetes C, Karssemeijer N. Volumetric breast density estimation from full-field digital mammograms. IEEE Trans Med Imaging. 2006; 25:273-282.
21. Huang NE, Shen Z, Long SR, Wu MC, Shih HH, et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. in Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998: 903-995.
22. Linderhed A. 2D empirical mode decompositions in the spirit of image compression. in SPIE AeroSense 2002, Orlando, Florida, 2002: 1-8.
23. Nunes JC, Bouaoune Y, Deléchelle E, Niang O, Bunel P. Image analysis by bidimensional empirical mode decomposition. Image and vision computing. 2003; 21: 1019-1026.
24. Nunes JC, Guyot S, Deléchelle E. Texture analysis based on local analysis of the bidimensional empirical mode decomposition. Machine Vision and applications. 2005; 16: 177-188.
25. Bhuiyan SM, Attoh-Okine NO, Barner KE, Ayenu-Prah AY, Adhami RR. Bidimensional empirical mode decomposition using various interpolation techniques. Advances in Adaptive Data Analysis. 2009; 1: 309-338.
26. Niang O, Deléchelle E, Lemoine J. A spectral approach for sifting process in empirical mode decomposition. IEEE Transactions on Signal Processing. 2010; 58: 5612-5623.
27. Niang O, Thioune A, Delechelle E, Lemoine J. Spectral intrinsic decomposition method for adaptive signal representation. ISRN Signal Processing. 2012; Article ID 457152, 10 pages.
28. Niang O, Thioune A, Gueirea MCE, Deléchelle E, Lemoine J. Partial differential equation-based approach for empirical mode decomposition: application on image analysis. IEEE Transactions on Image Processing. 2012; 21: 3991-4001.
29. Chen CY, Guo SM, Chang WS, Tsai JSH, Cheng KS: An improved bidimensional empirical mode decomposition: A mean approach for fast decomposition. Signal Processing. 2014; 98: 344-358.
30. Sickles EA. Mammographic features of early breast cancer. Am J Roentgenol. 1984; 143: 461-464.
31. Tabar L, Fagerberg CJ, Gad A, Baldetorp L, Holmberg LH, et al. Reduction in mortality from breast cancer after mass screening with mammography: randomised trial from the breast cancer screening working group of the Swedish National Board of health and Welfare. The Lancet. 1985; 325: 829-832.
32. Wang J, Chang KJ, Chen CY, Chien KL, Tsai YS, et al.: Evaluation of the diagnostic performance of infrared imaging of the breast: a preliminary study. BioMedical Engineering OnLine. 2010; 9(3): 3-14.
33. Jai-Andaloussi S, Sekkaki A, Quellec G, Lamard M, et al. Mass segmentation in mammograms by using bidimensional empirical mode decompsition BEMD. 35th Annual Internaltional conference of the IEEE EMBS, Osaka, Japan. July, 2013: 5441-5444.
34. Sondele S, Saini I. Digital mammograms classification using artificial neural network based on bidimensional empirical mode decomposition features. Int J Elec Electr Eng Telecoms. 2013; 2(3): 44-48.
35. Toft P. The Radon Transform, theory and implementation. Ph.D. thesis, Department of Mathematical Modelling Section for Digital signal Processing, Technical University of Denmark, 1996.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2014-09-09起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2014-09-09起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw