臺灣博碩士論文加值系統

乳癌為全世界女性之重要疾病與死因，所以對於乳癌診斷與治療的研究是必須的，近年來，磁振造影影像(Magnetic Resonance Imaging, MRI)逐漸取代傳統X光攝影及超音波檢測作為檢查乳癌的工具，磁振造影影像不但沒有放射線的問題，而且對於影像解析度及對比度上較為優異，但在乳房磁振造影檢查時，需注射顯影劑，顯影劑本身具有毒性，有些患者會對顯影劑過敏，因此，本論文提出利用近期發展的體素內不同調水分子運動(Intra-voxel incoherent motion, IVIM)擴散加權影像(Diffusion weight imaging, DWI)分析乳房組織。在這項研究中，許多算法將被使用。非監督式-自動目標生成過程（ATGP）、光譜角匹配法（SAM）與核限制能量最小化法(K-CEM)應用在偵測病灶範圍，對此範圍做定量分析。本研究主要運用決策樹(Decision tree)的方式，應用在整張影像上，針對IVIM各參數分別去分類，主要目的是為了針對較明顯的可疑病變區域，利用直方圖分析(histogram analysis)進而找出較佳的參數當作主要依據，如此一來，能提升偵測病灶位置的準確性，並從實驗結果中觀察是否有擴散的趨勢。此外，直方圖分析還被應用在各參數上區分各種病灶的類型。

Breast cancer is an important cause of death and disease for women in the world. It is required for the diagnosis and treatment of breast cancer research. In recent years, MRI is gradually replacing the traditional X-ray photography and ultrasound to detect breast cancer as an inspection tool. MRI is not only no radiation problem but also more excellent on the image resolution and contrast. However, when MRI use on breast examination, it must be injected the contrast agent. The contrast agent is toxicity, so some patients may have an allergy to contrast agents. Therefore, thesis presents breast tissue analysis of IVIM-MRI in recent evolvement. In this research, many algorithms will be used. Automatic target generation process (ATGP) and spectral angle mapper (SAM) with kernel-constrained energy minimization (K-CEM) applied to detect lesions range for quantitative analysis. The research use the decision tree to apply on the entire image for IVIM parameters to classify respectively. The main purpose of the suspicious lesion using histogram analysis identify preferred parameters as the main basis. As a result, not only can improve the detection accuracy of lesion location, but also observe whether there are trends in the spread of experimental results. In addition, the histogram analysis has also been applied to distinguish various types of lesions.

中文摘要 ii
Abstract iii
CHAPTER 1 Introduction 1
CHAPTER 2 Background 4
2.1 Magnetic Resonance Imaging (MRI) 4
2.2 Diffusion-Weighted Imaging (DWI) 4
2.2.1 Apparent Diffusion Coefficient (ADC) 5
2.3 Intra-Voxel Incoherent Motion (IVIM) 6
2.4 Band expansion process (BEP) 8
2.5 Automatic Target Generation Process (ATGP) 8
2.6 Spectral Angle Mapper (SAM) 9
2.7 Constrained Energy Minimization Approach 10
2.8 Kernel-Based Constrained Energy Minimization Approach 12
2.9 Decision Tree 15
CHAPTER 3 Breast tissue classification based on IVIM-MRI Method 16
3.1 Experimental Material 16
3.2 Pre-processing 18
3.2.1 Breast Region Segmentation 18
3.3 Lesion Region Detection 19
3.4 Quantitative Analysis 20
3.5 Define Breast Tissue Classification by Decision Tree 22
3.6 Histogram Analysis 24
CHAPTER 4 Experimental Results and Discussion 25
4.1 Real case of experiments 25
4.1.1 Mass 25
4.1.2 Non-mass 45
4.1.3 Normal Tissue 54
4.1.4 Cyst 59
4.2 Comparison of Tumor and Cyst 75
CHAPTER 5 Conclusion 77
Reference 78

[1]S. Buseman, J. Mouchawar, N. Calonge, and T.Byers, “Mammography screening matters foryoung women with breast carcinoma,” Cancer, vol.97, no. 2, pp. 352-358, 2003.
[2]G. M. Kacl, P. Liu, J. F. Debatin, E. Garzoli, R. F. Caduff, G. P. Krestin. Detection of breast cancer with conventional mammography and contrast-enhanced MR imaging. Eur Radiol. 1998; 8:194–200.
[3]BI-RADS Breast Imaging Reporting and Data System – Magnetic Resonance Imaging, First Edition, American College of Radiology, 2003.
[4]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.
[5]S. C. Partridge, W. B. Demartini, B.F. Kurland, P. R. Eby, S. W. White, C. D. Lehman, “Differential diagnosis of mam-mographically and clinically occult breast lesions on diffusion-weighted MRI,” JMRI, 31(3):562–70, 2010.
[6]R. H. Ei Khouli, M. A. Jacobs, S. D. Mezban, P. Huang, I. R. Kamel, K. J. Macura, D. A. Bluemke, “Diffusion-weighted imaging improves the diagnostic accuracy of conventional 3.0-T breast MR imaging,” Radiology, 256(1): 64–73, 2010.
[7]E. Rubesova, A. S. Grell, V. D. Maertelaer, T. Metens, S. L. Chao, M. Lemort, “Quantitative diffusion imaging in breast cancer: a clinical prospective study,” JMRI, 24(2): 319–24, 2006.
[8]C. Marini, C. Iacconi, M. Giannelli, A. Cilotti, M. Moretti, C. Bartolozzi, “Quantitative diffusion-weighted MR imaging in the differential diagnosis of breast lesion,” Eur Radiol, 17(10): 2646–55, 2007.
[9]Le Bihan D, Turner R, MacFall JR. Effects of intravoxel incoherent motions (IVIM)in steady-state free precession (SSFP) imaging: application to molecular diffu-sion imaging. Magn Reson Med Off J Soc Magn Reson Med Soc Magn Reson Med1989; 10(3):324–37.
[10]Le Bihan D, Breton E, Lallemand D, et al. Separation of diffusion and per-fusion in intravoxel incoherent motion MR imaging. Radiology 1988; 168(2):497–505.
[11]Y. Freund, L. Mason “The Alternating Decision Tree Learning Algorithm,” ICML ''99 Proceedings of the Sixteenth International Conference on Machine Learning: 124-133.
[12]Y. C. Ouyang, H. M. Chen, J. W. Chai, C. C. C. Chen, S. K. Poon, C. W. Yang, S. K. Lee and C.-I Chang, “Band expansion-based over-complete independent component analysis for magnetic resonance image analysis,” IEEE Trans. Biomedical Engineering, vol. 55, no. 6, pp. 1666-1677, June 2008.
[13]P. C. Lauterbur, “Image formation by induced local interactions: examples employing nuclear magnetic resonance,” Nature 242, 190-191 (1973).
[14]R. Woodhams, S. Ramadan, P. Stanwell, et al. Diffusion-weighted imaging of the breast: principles and clinical applications. RadioGraphics 2011; 31(4):1059–1084.
[15]E. M. Charles-Edwards, N. M. deSouza. Diffusion-weighted magnetic resonance imaging and its application to cancer. Cancer Imaging 2006; 6:135–143.
[16]R. N. Sener. Diffusion MRI: apparent diffusion coefficient (ADC) values in the normal brain and a classification of brain disorders based on ADC values. Comput Med Imaging Graph. 2001; 25 (4): 299-326.
[17]M. Mascalchi, M. Filippi, Floris R et-al. Diffusion-weighted MR of the brain: methodology and clinical application. Radiol Med. 2005; 109 (3): 155-97.
[18]S. Rana, S. Albayram, Lin DD et-al. Diffusion-weighted imaging and apparent diffusion coefficient maps in a case of intracerebral abscess with ventricular extension. AJNR Am J Neuroradiol. 2002; 23 (1): 109-12.
[19]R. M. El Kady, A.K. Choudhary, R. Tappouni. Accuracy of apparent diffusion coefficient value measurement on PACS workstation: A comparative analysis. AJR Am J Roentgenol. 2011; 196 (3): W280-4.
[20]R. Woodhams, S. Ramadan, P. Stanwell, et al. Diffusion-weighted imaging of the breast: principles and clinical applications. RadioGraphics 2011; 31(4):1059–1084.
[21]H. Ren and C.-I Chang, “Automatic spectral target recognition in hyperspectral imagery,” IEEE Trans. Aerosp. Electron. Syst., vol. 39, pp. 1232–1249, Oct. 2003.
[22]Boardman, 1992, SIPS User’s Guide Spectral Image Processing System, Version 1.2, Center for the Study of Earth from Space, Boulder.
[23]F. A. Kruse, A. B. Lefkoff, J. W. Boardman, K. B. Heiedbrecht, A. T. Shapiro, P. J. Barloon, A. F. H. Goetz, “The Spectral Image Processing System (SIPS) - Software for Integrated Analysis of AVIRIS Data,” Summaries of the 4th Annual JPL Airborne Geoscience Workshop, JPL Pub-92-14, AVIRISWorkshop. Jet Propulsion Laboratory, Pasadena, CA, pp. 23-25, 1992.
[24]J. C. Harsanyi, “Detection and classification of subpixel spectral signatures in hyperspectral image sequences,” Ph.D. dissertation, Dept, Elect. Eng., Univ. Maryland Baltimore County, Baltimore, MD, 1993.
[25]J. C. Harsanyi, W. Farrand, and C.-I. Chang, “Detection of subpixel spectral signatures in hyperspectral image sequences,” in Proc. American Society of Photogrammetry & Remote Sensing Annu. Meeting, Reno, pp. 236-247, 1994.
[26]R. S. Resmini, M. E. Kappus, W. S. Aldrich, J. C. Harsanyi, and M. Anderson, “Mineral mapping with Hyperspectral Digital Imagery Collection Experiment (HYDICE) sensor data at Cuprite, Nevada, U.S.A.,” lnt. J. Remote Sensing, vol. 18, no. 17, pp. 1553-1570, 1997.
[27]J. C. Shafer, R. Agrawal, M. Mehta: SPRINT: A Scalable Parallel Classifier for Data Mining. VLDB 1996, p. 544-555.
[28]M. Mehta, R. Agrawal, J. Rissanen.: SLIQ: A fast scalable classifier for data mining. In Proc. 1996 Intl. Conf. on Extending Database Technology (EDBT’96), Avignon, France, March 1996.
[29]S. M. Weiss, C. A. Kulikowski.: Computer System that Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert System. Morgan Kaufman, 1991.
[30]J. Han, M. Kamber.: Data Mining: Concepts and Techniques. Simon Fraser University, 2001.
[31]J. Patel, E. E. Sigmund, H. Rusinek, M. Oei, J. S. Babb, B. Taouli, “Diagnosis of Cirrhosis With Intravoxel Incoherent Motion Diffusion MRI and Dynamic Contrast-Enhanced MRI Alone and in Combination: Preliminary Experience,” JOURNAL OF MAGNETIC RESONANCE IMAGING, 31:589–600, 2010.