臺灣博碩士論文加值系統

對於全球女性來說，乳癌已經成為最普遍的癌症之一，同時也是癌症致死的主要原因，早期偵測可以提供更好的治療並大幅降低死亡率。早期乳癌篩檢以乳房X光攝影為主要檢查工具，近年發展新型態的乳房斷層攝影是一項三維斷層技術，有助於解決二維乳房X光影像產生的組織重疊問題。因此我們提出一個電腦輔助診斷系統，應用在乳房X光影像以及乳房斷層攝影，並比較它們的效能。電腦輔助診斷系統由二元邏輯回歸分類器建立，從乳房X光影像的ROI或乳房斷層攝影的VOI提取紋理特徵，包含灰階共生矩陣、ranklet轉換、以及Gabor小波轉換。並評估不同特徵組合的效能。電腦輔助診斷系統經由42個良性和82個惡性的腫瘤的資料庫進行驗證。由Gabor小波轉換應用在乳房斷層攝影達成最佳的效能。準確率85.48% (106/124)，靈敏性86.59% (71/82)，特異性83.33% (35/42)，以及ROC曲線面積0.8712。總結來說，乳房斷層攝影搭配Gabor小波轉換特徵相較於乳房X光影像的分類效果更好。

Among female throughout the world, breast cancer has become one of the most common carcinomas and the leading cause of cancer-related death. Early detection can provide a better treatment and significantly reduce mortality. Currently, the most effective tool to diagnose breast cancer is mammography screening. Tomosynthesis as a three dimensional (3-D) tomographic technique can overcome the overlapping problem from superimposed tissues of two dimensional (2-D) mammography. Therefore, we proposed a computer-aided diagnosis (CADx) system implemented in tomosynthesis and also in mammography to compare their performance. The CADx system was built by binary logistic regression classifier. Texture features, including gray-level co-occurrence matrix (GLCM), ranklet, and Gabor, were extracted from user-specified regions of interest (ROIs) in mammograms or volumes of interest (VOIs) in tomosynthesis images. The performance of different combinations of features were evaluated. The CADx system was tested with a dataset of 42 benign and 82 malignant tumors. The best performance was achieved by applying Gabor feature in tomosynthesis with an accuracy of 85.48% (106/124), a sensitivity of 86.59% (71/82), a specificity of 83.33% (35/42), and an Az value of 0.8712. To summarize, tomosynthesis is more effective in classification of breast tumor with Gabor feature than mammography.

口試委員會審定書 i
致謝 ii
摘要 iii
Abstract iv
Table of Contents v
List of Figures vi
List of Tables vii
Chapter 1 Introduction 1
Chapter 2 Materials 3
2.1 Patients and Lesion Characters 3
2.2 Data Acquisition 3
Chapter 3 The Tumor Diagnosis Method 5
3.1 ROI or VOI Specification 7
3.2 Feature Extraction 8
3.2.1 GLCM Features 8
3.2.2 Ranklet Texture Features 10
3.2.3 Gabor Features 13
3.3 Classification 15
3.3.1 Feature Analysis 15
3.3.2 Tumor Classification 16
Chapter 4 Experiment Results and Discussion 17
4.1 Experiment Environment 17
4.2 Statistical Analysis Result 17
4.3 Result and Discussion 22
Chapter 5 Conclusion and Future Works 32
References 34

[1]Torre, L.A., et al., Global cancer statistics, 2012. CA: A Cancer Journal for Clinicians, 2015. 65(2): p. 87-108.
[2]Siegel, R.L., K.D. Miller, and A. Jemal, Cancer statistics, 2015. CA: A Cancer Journal for Clinicians, 2015. 65(1): p. 5-29.
[3]Narod, S.A., Tumour size predicts long-term survival among women with lymph node-positive breast cancer. Current Oncology, 2012. 19(5): p. 249-253.
[4]Saadatmand, S., et al., Influence of tumour stage at breast cancer detection on survival in modern times: population based study in 173 797 patients. BMJ, 2015. 351.
[5]Smith, R.A., et al., Cancer screening in the United States, 2015: A review of current American Cancer Society guidelines and current issues in cancer screening. CA: A Cancer Journal for Clinicians, 2015. 65(1): p. 30-54.
[6]Porter, P.L., Global trends in breast cancer incidence and mortality. Salud Pública de México, 2009. 51: p. s141-s146.
[7]Jalalian, A., et al., Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review. Clinical Imaging, 2013. 37(3): p. 420-426.
[8]Bochud, F.O., et al., Estimation of the noisy component of anatomical backgrounds. Medical Physics, 1999. 26(7): p. 1365-1370.
[9]Burgess, A.E., F.L. Jacobson, and P.F. Judy, Human observer detection experiments with mammograms and power-law noise. Medical Physics, 2001. 28(4): p. 419-437.
[10]Helvie, M.A., Digital Mammography Imaging: Breast Tomosynthesis and Advanced Applications. Radiologic clinics of North America, 2010. 48(5): p. 917-929.
[11]Niklason, L.T., et al., Digital tomosynthesis in breast imaging. Radiology, 1997. 205(2): p. 399-406.
[12]James, T.D., III and J.G. Devon, Digital x-ray tomosynthesis: current state of the art and clinical potential. Physics in Medicine & Biology, 2003. 48(19): p. R65.
[13]Andersson, I., et al., Breast tomosynthesis and digital mammography: a comparison of breast cancer visibility and BIRADS classification in a population of cancers with subtle mammographic findings. European Radiology, 2008. 18(12): p. 2817-2825.
[14]Gennaro, G., et al., Digital breast tomosynthesis versus digital mammography: a clinical performance study. European Radiology, 2010. 20(7): p. 1545-1553.
[15]Svahn, T.M., et al., Breast tomosynthesis and digital mammography: a comparison of diagnostic accuracy. The British Journal of Radiology, 2012. 85(1019): p. e1074-e1082.
[16]Doi, K., et al., Computer-aided diagnosis in radiology: potential and pitfalls. European Journal of Radiology, 1999. 31(2): p. 97-109.
[17]Giger, M.L., Computer-aided diagnosis of breast lesions in medical images. Computing in Science & Engineering, 2000. 2(5): p. 39-45.
[18]Giger, M.L., N. Karssemeijer, and S.G. Armato, Guest editorial computer-aided diagnosis in medical imaging. IEEE Transactions on Medical Imaging, 2001. 20(12): p. 1205-1208.
[19]Vyborny, C.J., M.L. Giger, and R.M. Nishikawa, COMPUTER-AIDED DETECTION AND DIAGNOSIS OF BREAST CANCER. Radiologic Clinics of North America, 2000. 38(4): p. 725-740.
[20]Tang, J., et al., Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances. IEEE Transactions on Information Technology in Biomedicine, 2009. 13(2): p. 236-251.
[21]Lei, J., et al., Diagnostic accuracy of digital breast tomosynthesis versus digital mammography for benign and malignant lesions in breasts: a meta-analysis. European Radiology, 2014. 24(3): p. 595-602.
[22]Caumo, F., et al., Incremental effect from integrating 3D-mammography (tomosynthesis) with 2D-mammography: Increased breast cancer detection evident for screening centres in a population-based trial. The Breast, 2014. 23(1): p. 76-80.
[23]Haas, B.M., et al., Comparison of Tomosynthesis Plus Digital Mammography and Digital Mammography Alone for Breast Cancer Screening. Radiology, 2013. 269(3): p. 694-700.
[24]Rose, S.L., et al., Implementation of Breast Tomosynthesis in a Routine Screening Practice: An Observational Study. American Journal of Roentgenology, 2013. 200(6): p. 1401-1408.
[25]Skaane, P., et al., Comparison of Digital Mammography Alone and Digital Mammography Plus Tomosynthesis in a Population-based Screening Program. Radiology, 2013. 267(1): p. 47-56.
[26]Skaane, P., et al., Prospective trial comparing full-field digital mammography (FFDM) versus combined FFDM and tomosynthesis in a population-based screening programme using independent double reading with arbitration. European Radiology, 2013. 23(8): p. 2061-2071.
[27]Rafferty, E.A., et al., Assessing Radiologist Performance Using Combined Digital Mammography and Breast Tomosynthesis Compared with Digital Mammography Alone: Results of a Multicenter, Multireader Trial. Radiology, 2013. 266(1): p. 104-113.
[28]Chan, H.-P., et al., Computer-aided Detection System for Breast Masses on Digital Tomosynthesis Mammograms: Preliminary Experience. Radiology, 2005. 237(3): p. 1075-1080.
[29]Reiser, I., et al., Computerized mass detection for digital breast tomosynthesis directly from the projection images. Medical Physics, 2006. 33(2): p. 482-491.
[30]Chan, H.-P., et al., Computer-aided detection of masses in digital tomosynthesis mammography: Comparison of three approaches. Medical Physics, 2008. 35(9): p. 4087-4095.
[31]Reiser, I., et al., Automated detection of microcalcification clusters for digital breast tomosynthesis using projection data only: A preliminary study. Medical Physics, 2008. 35(4): p. 1486-1493.
[32]Hardesty, L.A., S.M. Kreidler, and D.H. Glueck, Digital Breast Tomosynthesis Utilization in the United States: A Survey of Physician Members of the Society of Breast Imaging. Journal of the American College of Radiology, 2014. 11(6): p. 594-599.
[33]Ciatto, S., et al., Integration of 3D digital mammography with tomosynthesis for population breast-cancer screening (STORM): a prospective comparison study. The Lancet Oncology, 2013. 14(7): p. 583-589.
[34]Friedewald, S.M., et al., Breast cancer screening using tomosynthesis in combination with digital mammography. JAMA, 2014. 311(24): p. 2499-2507.
[35]Guyon, I. and A. Elisseeff, An Introduction to Feature Extraction, in Feature Extraction: Foundations and Applications, I. Guyon, et al., Editors. 2006, Springer Berlin Heidelberg: Berlin, Heidelberg. p. 1-25.
[36]Kamila, N.K., Handbook of Research on Emerging Perspectives in Intelligent Pattern Recognition, Analysis, and Image Processing. 2015: IGI Global.
[37]Bengio, Y., Representation Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013. 35(8): p. 1798-1828.
[38]Haralick, R.M., K. Shanmugam, and I. Dinstein, Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973. SMC-3(6): p. 610-621.
[39]Haralick, R.M., Statistical and structural approaches to texture. Proceedings of the IEEE, 1979. 67(5): p. 786-804.
[40]Masotti, M. and R. Campanini, Texture classification using invariant ranklet features. Pattern Recognition Letters, 2008. 29(14): p. 1980-1986.
[41]Daubechies, I., Ten lectures on wavelets. 1992: Society for Industrial and Applied Mathematics. 357.
[42]Smeraldi, F. Ranklets: orientation selective non-parametric features applied to face detection. in Pattern Recognition, 2002. Proceedings. 16th International Conference on. 2002.
[43]Smeraldi, F. and J. Bigun, Retinal vision applied to facial features detection and face authentication. Pattern Recogn. Lett., 2002. 23(4): p. 463-475.
[44]Gabor, D., Theory of communication. Part 1: The analysis of information. Electrical Engineers - Part III: Radio and Communication Engineering, Journal of the Institution of, 1946. 93(26): p. 429-441.
[45]Turner, M.R., Texture discrimination by Gabor functions. Biological Cybernetics, 1986. 55(2): p. 71-82.
[46]Sprinthall, R.C., Basic Statistical Analysis. 2012: Pearson Allyn & Bacon.
[47]Hosmer, D.W., S. Lemeshow, and R.X. Sturdivant, Applied Logistic Regression. 2013: Wiley.
[48]Kohavi, R., A study of cross-validation and bootstrap for accuracy estimation and model selection, in Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2. 1995, Morgan Kaufmann Publishers Inc.: Montreal, Quebec, Canada. p. 1137-1143.
[49]Zweig, M.H. and G. Campbell, Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clinical Chemistry, 1993. 39(4): p. 561-577.
[50]Metz, C.E., B.A. Herman, and C.A. Roe, Statistical Comparison of Two ROC-curve Estimates Obtained from Partially-paired Datasets. Medical Decision Making, 1998. 18(1): p. 110-121.
[51]Jain, A.K. and B. Chandrasekaran, 39 Dimensionality and sample size considerations in pattern recognition practice, in Handbook of Statistics. 1982, Elsevier. p. 835-855.
[52]Friedman, J.H., On Bias, Variance, 0/1—Loss, and the Curse-of-Dimensionality. Data Mining and Knowledge Discovery, 1997. 1(1): p. 55-77.
[53]Raudys, S.J. and A.K. Jain, Small sample size effects in statistical pattern recognition: recommendations for practitioners. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991. 13(3): p. 252-264.
[54]Rui, H., et al. Solving the small sample size problem of LDA. in Object recognition supported by user interaction for service robots. 2002.
[55]Majtner, T. and D. Svoboda. Extension of Tamura Texture Features for 3D Fluorescence Microscopy. in 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission. 2012.
[56]Zhao, G. and M. Pietikäinen, Dynamic Texture Recognition Using Volume Local Binary Patterns, in Dynamical Vision: ICCV 2005 and ECCV 2006 Workshops, WDV 2005 and WDV 2006, Beijing, China, October 21, 2005, Graz, Austria, May 13, 2006. Revised Papers, R. Vidal, A. Heyden, and Y. Ma, Editors. 2007, Springer Berlin Heidelberg: Berlin, Heidelberg. p. 165-177.
[57]Zhao, G. and M. Pietikainen, Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007. 29(6): p. 915-928.
[58]Cortes, C. and V. Vapnik, Support-vector networks. Machine Learning, 1995. 20(3): p. 273-297.
[59]Burges, C.J.C., A Tutorial on Support Vector Machines for Pattern Recognition. Data Min. Knowl. Discov., 1998. 2(2): p. 121-167.
[60]Haykin, S., Neural Networks: A Comprehensive Foundation (3rd Edition). 2007: Prentice-Hall, Inc.