Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/91832
DC FieldValueLanguage
dc.contributor鄧洪聲zh_TW
dc.contributorHon-Son Donen_US
dc.contributor.authorYi-Wei Huangen_US
dc.contributor.author黃翊瑋zh_TW
dc.contributor.other通訊工程研究所zh_TW
dc.date2015zh_TW
dc.date.accessioned2015-12-11T07:30:49Z-
dc.identifier.citation[1] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm foroptimal margin classifiers,” in Proc. 5th Annu. Workshop Comput. Learn. Theory, 1992, pp. 144-152. [2] V. N. Vapnik, The Nature of Statistical Learning Theory, 2nd ed. New York: Springer Verlag, 2001. [3] H. Ren, Q. Du, C. I. Chang, J. O. Jensen, “Comparison between Constrained Energy Minimization based Approaches for Hyperspectral Imagery” IEEE conf. Advances in Techniques for Analysis of Remotely Sensed Data, Oct, 2003 [4] C. I. Chang, Hyperspectral Imaging: Techniques for Spectral Detection and Classification, Kluwer, 2003. [5] C. I. Chang, Hyperspectral Data Processing: Signal Processing Algorithm Design and Analysis Wiley, 2013. [6] C. K. Kuhl, R. K. Schmutzler, C. C. Leutner, A. Kempe, E. Wardelmann, A. Hocke, M. Maringa, U. Pfeifer, D. Krebs and H. H. Schild, 'Breast MR Imaging Screening in 192 Women Proved or Suspected to Be Carriers of a Breast Cancer Susceptibility Gene: Preliminary Results I' Radiology 2000; 215:267-279. [7] C. M. Wang, S. C. Yang, P. C. Chung, Y. N. Chung, C. C. Chen, C. W. Yang, and C. H. Wen, “Orthogonal Subspace Projection-Base Approach to Classification of MR Image Sequences” Computerized Medical Imaging and Graphics, December, 2001, vo1. 25, no. 6, pp. 465-476. [8] J. G. Sled, A. P. Zijdenbos, and A. C. Evans, “A Nonparametric Method for Automatic Correction of Intensity Nonuniformity in MRI Data” IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 17, NO. 1, FEBRUARY 1998 [9] N. Otsu, “A threshold selection method from gray-level histogram”, IEEE Transactions on Systems Man Cybernet, SMC-8 pp. 62-66, 1978. [10] D. D. Stark, and W. G. Bradley., Magnetic Resonance Imaging, vol. 1, 3rd, Mosby Inc.,1999. fuzzy [11] G. A. Wright, “Magnetic resonance image,” IEEE Signal Processing Mag., pp. 56–66, Jan. 1997. [12] G. Sebastiani and P. Barone, “Mathematical principles of basic magnetic resonance image in medicine,” Signal Process, vol. 25, pp. 227–250, 1991. [13] A. H. Andersen, Z. Zhang, M. J. Avison, D. M. Gash, “Automated segmentation of multispectral brain MR images,” J. Neurosci Methods 2002; 122:13-23. [14] L. P. Clarke, R. P. Velthuizen, M. A. Camacho, et al. MRI segmentation: methods and applications. Magn. Reson. Imaging 1995; 13: 343-368. [15] H. S. Zadeh, D. J. Peck, J. P. Windham, and T. Mikkelsen, “Brain tumor segmentation and characterization by pattern analysis of multispectral NMR images,” NMR Biomed 1998; 11: 201-208. [16] F. B. Mohamed, S. Vinitski, S. H. Faro, C. F. Gonzalez, J. Mack, T. Iwanaga. “Optimization of tissue segmentation of brain MR images based on multispectral 3D feature maps,” Magn. Reson. Imaging 1999; 17: 403-409. [17] J. W. Chai, H. M. Chen, C. C. C. Chen, Y. C. Ouyang, S. K. Lee and C. I. Chang “Quantitative analysis of brain magnetic resonance images using support vector machine in conjunction with independent component analysis,” J. Magnetic Resonance Imaging, vol. 32, pp. 24-34, 2010. [DOI 10.1002/jmri.22210]. [18] C. C. Chang and C. J. Lin, LIBSVM: A Library for Support Vector Machines, 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm [19] H. L. Xiong, M. N. S. Swamy, and M. O. Ahmad, “Optimizing the kernel in the empirical feature space,” IEEE Trans. Neural Networks 16 , 460–474, Feb. 2005. [20] B. Chen, H. Liu, and Z. Bao,“Optimizing the data-dependent kernel under a unified kernel optimization framework,” Pattern Recognition, vol. 41, pp. 2107-2119, 2007. [21] E. M. Purcell, H. C. Torry, and R. V. Pound, “Resonance absorption by nuclear magnetic moments in solid,” Phys. Rev. 46, 37-38 , 1946. [22] N. Otsu, “A threshold selection method from gray-level histogram”, IEEE Transactions on Systems Man Cybernet, SMC-8 pp. 62-66, 1978.zh_TW
dc.identifier.urihttp://hdl.handle.net/11455/91832-
dc.description.abstract本文的目標是藉由使用磁共振成像技術來設計了一套自動的方式,它可以計算乳房密度並且計算乳房容積。由於對某些高風險人群對來說,乳房X光檢查在高乳腺密度案例上,其用途有限,所以我們的目的是利用磁共振影像來測量乳腺密度,進而提升罹患乳腺癌風險評估的準確性。為求可以準確測量乳腺密度,我們結合支援向量機和約束能量最小化法來測量乳腺密度。約束能量最小化法(CEM),它可以成功地顯示高對比度圖像的分類結果,藉由我們增強的圖像,再使用閥值技術將乳房MRI中乳腺區域劃分出來。而支援向量機則可以在乳房MRI中乳腺區域乳腺較為稀疏區域作出分類,我們運用OTSU方法並調整其運算出來的閥值,進而將其閥值作為支援向量機的訓練點並做分類。結合這兩種方法,我們可以針對MR影像不同的乳腺分布情形進行運算,進而準確計算其乳腺密度。在測量乳腺密度的方法上,C均數演算法(Fuzzy C-Means,FCM)是一種廣為人知且頻繁運用的方法,我們會將模糊C均數演算法(FuzzyC-Means,FCM)和新的方法分別運算且進行比較,藉以證明新的方法可以測量出更為準確的乳腺密度。另外,我們也針對我們的實驗結果畫出統計性分析圖表盒鬚圖(Box Plot),盒鬚圖(Box Plot)是一種用於顯示一組數據分散情況資料的統計圖,可以用來表示一組數據的最大值、最小值、中位數、下四分位數及上四分位數,藉以幫助醫生可以分析乳腺密度資訊。zh_TW
dc.description.abstractThe object of this thesis is to develop a set of automatic way by using MRI technique which can calculate breast density, breast volume and tumor detection automatically. The effect of using mammography is limited for the group who have high risk on breast cancer. Differences in breast tissue composition are important determinants in assessing risk, identifying disease in images. Our goal is to develop an algorithm for tissue classification that separates breast tissue into two constituents of fat and glandular tissue therefore can calculate the breast density precisely. We use multispectral MRI technique to calculate breast density hence can help doctor to make an accurate diagnosis. In order to calculate the breast density precisely, we use Support Vector Machine (SVM) and Constrained Energy Minimum (CEM) to calculate breast density. The breast MR images were enhanced by using CEM method. The enhanced images are then applied OTSU method to adjust a threshold to segment the glandular region. Besides, SVM can have great performance while the region of glandular is scattered on the image. Combining these two methods, we can classify glandular as well as fat tissues. The proposed method was also compare by fuzzy c-means method. From the experiment result it shows that the proposed method performs better than the FCM on breast density calculation. In addition, we also use box plot to display the experiment results.en_US
dc.description.tableofcontents誌謝 i 摘要 ii Abstract iii Content iv List of Figure vi List of Table ix CHAPTER 1 Introduction 1 CHAPTER2 Background 4 2.1 Magnetic resonance imaging 4 2.2 Multi-spectral image processing technology 5 2.3 Band expansion process 6 2.4 Constrained energy minimization approach 6 2.5 Support Vector Machine 9 2.5.1. Non-Linearly SVM 9 2.5.2. Non-Linearly SVM 11 2.6 Dynamic threshold selection method ( Otsu method ) 13 2.7 Experimental materials 15 CHAPTER3 Methods 16 3.1. Experimental material 16 3.2. Pre-processing 17 3.3. Use ICEM and SVM to detect glandular on MR images 23 3.3.1. Band expansion process 25 3.3.2. Find the slice with the highest breast density 26 3.3.3. Use iterative constrained energy minimization approach 27 3.3.4. Use support vector machine approach 28 3.3.5. Calculate breast volume 29 3.3.6. Calculate breast density 32 3.4 Use CEM to detect tumor on MR images 32 CHAPTER 4 Experiment Results 33 4.1 Introduction 33 4.2 Result of classification 33 4.2 The bar chart and box plot of result 41 CHAPTER 5 Conclusion 65 Reference 67zh_TW
dc.language.isoen_USzh_TW
dc.rights不同意授權瀏覽/列印電子全文服務zh_TW
dc.subjectMRIen_US
dc.subjectBreast densityen_US
dc.subjectCEM(Constrained Energy Minimization)en_US
dc.subjectSVM(Support Vector Machine)en_US
dc.subjectOTSUen_US
dc.subjectFuzzy C-Means(FCM)en_US
dc.subjectMRIzh_TW
dc.subject乳腺密度zh_TW
dc.subject約束能量最小化 (Constrained Energy Minimization, CEMzh_TW
dc.subject支援向量機(Support Vector Machine, SVM)zh_TW
dc.subjectOTSUzh_TW
dc.subject模糊C均數(Fuzzy C-Means)zh_TW
dc.title乳房MR影像組織分類改善之量化分析zh_TW
dc.titleOn the Classification of Breast MR Imaging: A Quantitative Analysisen_US
dc.typeThesis and Dissertationen_US
dc.date.paperformatopenaccess2018-08-26zh_TW
dc.date.openaccess10000-01-01-
Appears in Collections:通訊工程研究所
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.