請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58929完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張瑞峰 | |
| dc.contributor.author | Min-Chun Yang | en |
| dc.contributor.author | 楊閔淳 | zh_TW |
| dc.date.accessioned | 2021-06-16T08:39:20Z | - |
| dc.date.available | 2018-11-05 | |
| dc.date.copyright | 2013-11-05 | |
| dc.date.issued | 2013 | |
| dc.date.submitted | 2013-10-07 | |
| dc.identifier.citation | [1] H. D. Cheng, et al., 'Approaches for automated detection and classification of masses in mammograms,' Pattern Recognition, vol. 39, pp. 646-668, Apr 2006.
[2] P. M. Shankar, et al., 'Application of the compound probability density function for characterization of breast masses in ultrasound B scans,' Physics in Medicine and Biology, vol. 50, pp. 2241-2248, May 21 2005. [3] K. J. W. Taylor, et al., 'Ultrasound as a complement to mammography and breast examination to characterize breast masses,' Ultrasound in Medicine and Biology, vol. 28, pp. 19-26, Jan 2002. [4] H. Zhi, et al., 'Comparison of ultrasound elastography, mammography, and sonography in the diagnosis of solid breast lesions,' J Ultrasound Med, vol. 26, pp. 807-15, Jun 2007. [5] B. Sahiner, et al., 'Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy,' Radiology, vol. 242, pp. 716-24, Mar 2007. [6] C. M. Chen, et al., 'Breast lesions on sonograms: Computer-aided diagnosis with nearly setting-independent features and artificial neural networks,' Radiology, vol. 226, pp. 504-514, Feb 2003. [7] K. Drukker, et al., 'Computerized lesion detection on breast ultrasound,' Med Phys, vol. 29, pp. 1438-46, Jul 2002. [8] M. André, et al., 'Improving the Accuracy of Diagnostic Breast Ultrasound,' in Acoustical Imaging. vol. 26, R. Maev, Ed., ed: Springer US, 2002, pp. 453-460. [9] W. A. Berg, et al., 'Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer,' JAMA, vol. 299, pp. 2151-63, May 14 2008. [10] Y. Ikedo, et al., 'Development of a fully automatic scheme for detection of masses in whole breast ultrasound images,' Med Phys, vol. 34, pp. 4378-88, Nov 2007. [11] R. F. Chang, et al., 'Rapid image stitching and computer-aided detection for multipass automated breast ultrasound,' Med Phys, vol. 37, pp. 2063-73, May 2010. [12] M. N. Alekhin and B. A. Sidorenko, '[Potential and perspectives of the use of portable ultrasound diagnostic systems in cardiology.],' Kardiologiia, vol. 44, pp. 88-91, 2004. [13] X. G. Xu, et al., 'Design and test of a PC-based portable three-dimensional ultrasound software system Ultra3D,' Comput Biol Med, vol. 38, pp. 244-51, Feb 2008. [14] R. F. Chang, et al., 'Support vector machines for diagnosis of breast tumors on US images,' Acad Radiol, vol. 10, pp. 189-97, Feb 2003. [15] W. Bader, et al., 'Does texture analysis improve breast ultrasound precision?,' Ultrasound in Obstetrics & Gynecology, vol. 15, pp. 311-316, Apr 2000. [16] M. Masotti, 'A ranklet-based image representation for mass classification in digital mammograms,' Med Phys, vol. 33, pp. 3951-61, Oct 2006. [17] E. Angelini, et al., 'A ranklet-based CAD for digital mammography,' Digital Mamography, Proceedings, vol. 4046, pp. 340-346, 2006. [18] F. Smeraldi, 'Ranklets: orientation selective non-parametric features applied to face detection,' 16th International Conference on Pattern Recognition, Vol Iii, Proceedings, pp. 379-382, 2002. [19] F. Smeraldi, et al., 'Tracking points on deformable objects with ranklets,' 2005 International Conference on Image Processing (ICIP), Vols 1-5, pp. 3749-3752, 2005. [20] M. Masotti and R. Campanini, 'Texture classification using invariant ranklet features,' Pattern Recognition Letters, vol. 29, pp. 1980-1986, Oct 15 2008. [21] F. Bianconi, et al., 'Robust color texture features based on ranklets and discrete Fourier transform,' Journal of Electronic Imaging, vol. 18, Oct-Dec 2009. [22] Y. L. Huang, et al., 'Computer-aided diagnosis applied to 3-D US of solid breast nodules by using principal component analysis and image retrieval,' 2005 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vols 1-7, pp. 1802-1805, 2005. [23] Y. L. Huang, et al., 'Breast cancer diagnosis using image retrieval for different ultrasonic systems,' Icip: 2004 International Conference on Image Processing, Vols 1- 5, pp. 2957-2960, 2004. [24] M. Costantini, et al., 'Characterization of solid breast masses - Use of the sonographic breast imaging reporting and data system lexicon,' Journal of Ultrasound in Medicine, vol. 25, pp. 649-659, May 2006. [25] J. Sijbers, et al., 'Parameter estimation from magnitude MR images,' International Journal of Imaging Systems and Technology, vol. 10, pp. 109-114, 1999. [26] R. F. Chang, et al., 'Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis,' Ultrasound in Medicine and Biology, vol. 29, pp. 679-86, May 2003. [27] H. Salazar, et al., 'Role of embolic protection devices in acute myocardial infarction. Is their routine use of clinical benefit at six months?,' Journal of the American College of Cardiology, vol. 51, pp. A208-A208, Mar 11 2008. [28] P. DeJean, et al., 'An intraoperative 3D ultrasound system for tumor margin determination in breast cancer surgery,' Med Phys, vol. 37, pp. 564-70, Feb 2010. [29] G. Cevenini, et al., 'A naive Bayes classifier for planning transfusion requirements in heart surgery,' J Eval Clin Pract, Aug 23 2011. [30] M. Yousef, et al., 'Combining multi-species genomic data for microRNA identification using a Naive Bayes classifier,' Bioinformatics, vol. 22, pp. 1325-34, Jun 1 2006. [31] A. Rosenfeld and J. L. Pfaltz, 'Sequential Operations in Digital Picture Processing,' J. ACM, vol. 13, pp. 471-494, 1966. [32] D. P. Chakraborty, 'Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data,' Med Phys, vol. 16, pp. 561-8, Jul-Aug 1989. [33] K. Drukker, et al., 'Computerized analysis of shadowing on breast ultrasound for improved lesion detection,' Med Phys, vol. 30, pp. 1833-42, Jul 2003. [34] K. Drukker, et al., 'Robustness of computerized lesion detection and classification scheme across different breast US platforms,' Radiology, vol. 237, pp. 834-40, Dec 2005. [35] W. K. Moon, et al., 'Computer-aided tumor detection based on multi-scale blob detection algorithm in automated breast ultrasound images,' IEEE Trans Med Imaging, vol. 32, pp. 1191-200, Jul 2013. [36] D. Kotsianos-Hermle, et al., 'Analysis of 107 breast lesions with automated 3D ultrasound and comparison with mammography and manual ultrasound,' Eur J Radiol, May 9 2008. [37] J. A. Shipley, et al., 'Automated quantitative volumetric breast ultrasound data-acquisition system,' Ultrasound in Medicine and Biology, vol. 31, pp. 905-17, Jul 2005. [38] W. A. Berg, et al., 'Diagnostic accuracy of mammography, clinical examination, US, and MR imaging in preoperative assessment of breast cancer,' Radiology, vol. 233, pp. 830-49, Dec 2004. [39] R. F. Chang, et al., 'Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors,' Breast Cancer Res Treat, vol. 89, pp. 179-85, Jan 2005. [40] Q. Guo, et al., 'Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms,' Int J Comput Assist Radiol Surg, vol. 4, pp. 11-25, Jan 2009. [41] M. M. Dundar, et al., 'Computerized Classification of Intraductal Breast Lesions Using Histopathological Images,' Ieee Transactions on Biomedical Engineering, vol. 58, pp. 1977-1984, Jul 2011. [42] F. Lefebvre, et al., 'Computerized ultrasound B-scan characterization of breast nodules,' Ultrasound in Medicine and Biology, vol. 26, pp. 1421-8, Nov 2000. [43] 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. [44] L. Shen, et al., 'Application of shape analysis to mammographic calcifications,' IEEE Trans Med Imaging, vol. 13, pp. 263-74, 1994. [45] A. Madabhushi and D. N. Metaxas, 'Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions,' IEEE Trans Med Imaging, vol. 22, pp. 155-169, Feb 2003. [46] K. G. Kim, et al., 'Computerized scheme for assessing ultrasonographic features of breast masses,' Academic Radiology, vol. 12, pp. 58-66, Jan 2005. [47] J. Z. Cheng, et al., 'Computer-aided US Diagnosis of Breast Lesions by Using Cell-based Contour Grouping,' Radiology, vol. 255, pp. 746-754, Jun 2010. [48] V. Goldberg, et al., 'Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence,' Med Phys, vol. 19, pp. 1475-81, Nov-Dec 1992. [49] Y. Zheng, et al., 'Reduction of breast biopsies with a modified self-organizing map,' IEEE Trans Neural Netw, vol. 8, pp. 1386-96, 1997. [50] B. S. Garra, et al., 'Improving the Distinction between Benign and Malignant Breast-Lesions - the Value of Sonographic Texture Analysis,' Ultrasonic Imaging, vol. 15, pp. 267-285, Oct 1993. [51] K. Horsch, et al., 'Computerized diagnosis of breast lesions on ultrasound,' Med Phys, vol. 29, pp. 157-64, Feb 2002. [52] A. Takemura, et al., 'Discrimination of Breast Tumors in Ultrasonic Images Using an Ensemble Classifier Based on the AdaBoost Algorithm With Feature Selection,' Ieee Transactions on Medical Imaging, vol. 29, pp. 598-609, Mar 2010. [53] R. Lagalla and M. Midiri, 'Image quality control in breast ultrasound,' European Journal of Radiology, vol. 27 Suppl 2, pp. S229-33, May 1998. [54] M. Masotti, et al., 'Computer-aided mass detection in mammography: False positive reduction via gray-scale invariant ranklet texture features,' Med Phys, vol. 36, pp. 311-316, Feb 2009. [55] K. S. Sim, et al., 'A contrast stretching bilateral closing top-hat Otsu threshold technique for crack detection in images,' Scanning, vol. 35, pp. 75-87, Mar-Apr 2013. [56] R. A. Smith, et al., 'Mammography Screening for Breast Cancer,' New England Journal of Medicine, vol. 367, Nov 22 2012. [57] P. B. Krishnaiah, et al., 'Screening Mammography for Reducing Breast Cancer Mortality,' American Family Physician, vol. 85, pp. 176-+, Jan 15 2012. [58] L. L. Humphrey, et al., 'Breast cancer screening: a summary of the evidence for the U.S. Preventive Services Task Force,' Ann Intern Med, vol. 137, pp. 347-60, Sep 3 2002. [59] J. A. Harvey and V. E. Bovbjerg, 'Quantitative assessment of mammographic breast density: relationship with breast cancer risk,' Radiology, vol. 230, pp. 29-41, Jan 2004. [60] T. M. Kolb, et al., 'Comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: An analysis of 27,825 patient evaluations,' Radiology, vol. 225, pp. 165-175, Oct 2002. [61] 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. 1081-7, Jul 5 2000. [62] E. D. Pisano, et al., 'Diagnostic performance of digital versus film mammography for breast-cancer screening,' N Engl J Med, vol. 353, pp. 1773-83, Oct 27 2005. [63] W. Buchberger, et al., 'Clinically and mammographically occult breast lesions: detection and classification with high-resolution sonography,' Semin Ultrasound CT MR, vol. 21, pp. 325-36, Aug 2000. [64] P. Crystal, et al., 'Using sonography to screen women with mammographically dense breasts,' AJR Am J Roentgenol, vol. 181, pp. 177-82, Jul 2003. [65] P. B. Gordon and S. L. Goldenberg, 'Malignant breast masses detected only by ultrasound. A retrospective review,' Cancer, vol. 76, pp. 626-30, Aug 15 1995. [66] S. S. Kaplan, 'Clinical utility of bilateral whole-breast US in the evaluation of women with dense breast tissue,' Radiology, vol. 221, pp. 641-9, Dec 2001. [67] T. M. Kolb, et al., 'Comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: an analysis of 27,825 patient evaluations,' Radiology, vol. 225, pp. 165-75, Oct 2002. [68] Y. Kim, et al., Programmable ultrasound imaging using multimedia technologies: a next-generation ultrasound machine vol. 1, 1997. [69] P. Domingos and M. Pazzani, 'On the optimality of the simple Bayesian classifier under zero-one loss,' Machine Learning, vol. 29, pp. 103-130, Nov-Dec 1997. [70] V. Mesev, 'Morphological image analysis: principles and applications,' Environment and Planning B-Planning & Design, vol. 28, pp. 800-801, Sep 2001. [71] K. Horsch, et al., 'Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography,' Academic Radiology, vol. 11, pp. 272-280, Mar 2004. [72] M. L. Giger, et al., 'Computerized analysis of lesions in US images of the breast,' Academic Radiology, vol. 6, pp. 665-674, Nov 1999. [73] R. G. Keys, 'Cubic Convolution Interpolation for Digital Image-Processing,' Ieee Transactions on Acoustics Speech and Signal Processing, vol. 29, pp. 1153-1160, 1981. [74] A. K. Cherri and M. A. Karim, 'Optical symbolic substitution: edge detection using Prewitt, Sobel, and Roberts operators,' Appl Opt, vol. 28, pp. 4644-8, Nov 1 1989. [75] F. J. Lagerwaard, et al., 'Use of maximum intensity projections (MIP) for target volume generation in 4DCT scans for lung cancer,' International Journal of Radiation Oncology Biology Physics, vol. 63, pp. 253-260, Sep 1 2005. [76] C. Beigelman-Aubry, et al., 'Multi-detector row CT and postprocessing techniques in the assessment of diffuse lung disease,' Radiographics, vol. 25, pp. 1639-52, Nov-Dec 2005. [77] N. Otsu, 'Threshold Selection Method from Gray-Level Histograms,' Ieee Transactions on Systems Man and Cybernetics, vol. 9, pp. 62-66, 1979. [78] P. S. Liao, et al., 'A fast algorithm for multilevel thresholding,' Journal of Information Science and Engineering, vol. 17, pp. 713-727, Sep 2001. [79] D. A. Clausi, 'K-means Iterative Fisher (KIF) unsupervised clustering algorithm applied to image texture segmentation,' Pattern Recognition, vol. 35, pp. 1959-1972, Sep 2002. [80] G. F. Tzortzis and A. C. Likas, 'The Global Kernel k-Means Algorithm for Clustering in Feature Space,' Ieee Transactions on Neural Networks, vol. 20, pp. 1181-1194, Jul 2009. [81] M. N. Ahmed, et al., 'A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data,' Ieee Transactions on Medical Imaging, vol. 21, pp. 193-199, Mar 2002. [82] R. Nock and F. Nielsen, 'On weighting clustering,' Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 28, pp. 1223-1235, Aug 2006. [83] A. Rakotomamonjy, et al., 'Wavelet-based speckle noise reduction in ultrasound B-scan images,' Ultrason Imaging, vol. 22, pp. 73-94, Apr 2000. [84] R. C. Gonzalez, et al., Digital image processing, third ed. Upper Saddle River, New Jersey: Pearson Prentice Hall, 2008. [85] R. N. Czerwinski, et al., 'Detection of lines and boundaries in speckle images--application to medical ultrasound,' IEEE Trans Med Imaging, vol. 18, pp. 126-36, Feb 1999. [86] R. F. Wagner, et al., 'Fundamental Correlation Lengths of Coherent Speckle in Medical Ultrasonic Images,' Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control, vol. 35, pp. 34-44, Jan 1988. [87] R. M. Haralick, 'Digital Step Edges from Zero Crossing of 2nd Directional-Derivatives,' Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 6, pp. 58-68, 1984. [88] B. Andre, et al., 'An image retrieval approach to setup difficulty levels in training systems for endomicroscopy diagnosis,' Med Image Comput Comput Assist Interv, vol. 13, pp. 480-7, 2010. [89] J. A. Sethian, 'A fast marching level set method for monotonically advancing fronts,' Proc Natl Acad Sci U S A, vol. 93, pp. 1591-5, Feb 20 1996. [90] E. C. Morgan, et al., 'Probability distributions for offshore wind speeds,' Energy Conversion and Management, vol. 52, pp. 15-26, Jan 2011. [91] J. Sijbers, et al., 'Estimation of the noise in magnitude MR images,' Magnetic Resonance Imaging, vol. 16, pp. 87-90, Jan 1998. [92] E. Bribiesca, 'An easy measure of compactness for 2D and 3D shapes,' Pattern Recognition, vol. 41, pp. 543-554, Feb 2008. [93] J. Praagman, 'Classification and Regression Trees - Breiman,L, Friedman,Jh, Olshen,Ra, Stone,Cj,' European Journal of Operational Research, vol. 19, pp. 144-144, 1985. [94] S. Yu and L. Guan, 'A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films,' IEEE Trans Med Imaging, vol. 19, pp. 115-26, Feb 2000. [95] S. Theodoridis and K. Koutroumbas, Pattern Recognition, fourth ed. San Diego, CA: Academic Press, 2009. [96] J. M. Chang, et al., 'Radiologists' performance in the detection of benign and malignant masses with 3D automated breast ultrasound (ABUS),' Eur J Radiol, vol. 78, pp. 99-103, Apr 2011. [97] W. K. Moon, et al., 'Computer-Aided Diagnosis for the Classification of Breast Masses in Automated Whole Breast Ultrasound Images,' Ultrasound in Medicine and Biology, vol. 37, pp. 539-548, Apr 2011. [98] A. T. Stavros, et al., 'Solid breast nodules: use of sonography to distinguish between benign and malignant lesions,' Radiology, vol. 196, pp. 123-34, Jul 1995. [99] P. Crystal, et al., 'Using sonography to screen women with mammographically dense breasts,' American Journal of Roentgenology, vol. 181, pp. 177-182, Jul 2003. [100] D. R. Chen, et al., 'Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks,' Ultrasound in Medicine and Biology, vol. 28, pp. 1301-10, Oct 2002. [101] Y. L. Huang and D. R. Chen, 'Support vector machines in sonography: application to decision making in the diagnosis of breast cancer,' Clin Imaging, vol. 29, pp. 179-84, May-Jun 2005. [102] N. Piliouras, et al., 'Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound,' Comput Med Imaging Graph, vol. 28, pp. 247-55, Jul 2004. [103] Y. L. Huang, et al., 'Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines,' Neural Computing & Applications, vol. 15, pp. 164-169, Apr 2006. [104] A. V. Alvarenga, et al., 'Complexity curve and grey level co-occurrence matrix in the texture evaluation of breast tumor on ultrasound images,' Med Phys, vol. 34, pp. 379-87, Feb 2007. [105] N. N. Tsiaparas, et al., 'Comparison of Multiresolution Features for Texture Classification of Carotid Atherosclerosis From B-Mode Ultrasound,' Ieee Transactions on Information Technology in Biomedicine, vol. 15, pp. 130-137, Jan 2011. [106] C.-C. Chang and C.-J. Lin, 'LIBSVM: A library for support vector machines,' ACM Trans. Intell. Syst. Technol., vol. 2, pp. 1-27, 2011. [107] W. Gomez-Flores, et al., 'Analysis of Co-occurrence Texture Statistics as a Function of Gray-Level Quantization for Classifying Breast Ultrasound,' IEEE Trans Med Imaging, Jun 28 2012. [108] D. A. Clausi, 'An analysis of co-occurrence texture statistics as a function of grey level quantization,' Canadian Journal of Remote Sensing, vol. 28, pp. 45-62, Feb 2002. [109] T. Ojala, et al., 'Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,' Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 971-987, Jul 2002. [110] M. M. S. Matsumoto, et al., 'Local binary pattern texture-based classification of solid masses in ultrasound breast images,' pp. 83201H-83201H, 2012. [111] F. Smeraldi and J. Bigun, 'Retinal vision applied to facial features detection and face authentication,' Pattern Recognition Letters, vol. 23, pp. 463-475, Feb 2002. [112] E. L. Lehmann and H. J. M. D'Abrera, Nonparametrics : statistical methods based on ranks, Rev. 1st ed. New York: Springer, 2006. [113] R. M. Haralick, et al., 'Textural Features for Image Classification,' Ieee Transactions on Systems Man and Cybernetics, vol. Smc3, pp. 610-621, 1973. [114] L. K. Soh and C. Tsatsoulis, 'Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices,' Ieee Transactions on Geoscience and Remote Sensing, vol. 37, pp. 780-795, Mar 1999. [115] S. G. Mallat, 'A Theory for Multiresolution Signal Decomposition - the Wavelet Representation,' Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 11, pp. 674-693, Jul 1989. [116] G. E. Mailloux, et al., 'Local Histogram Information-Content of Ultrasound B-Mode Echographic Texture,' Ultrasound in Medicine and Biology, vol. 11, pp. 743-750, 1985. [117] M. M. Mokji and S. A. R. A. Bakar, 'Gray Level Co-Occurrence Matrix Computation Based On Haar Wavelet,' presented at the Proceedings of the Computer Graphics, Imaging and Visualisation, 2007. [118] N. Linder, et al., 'Identification of tumor epithelium and stroma in tissue microarrays using texture analysis,' Diagnostic Pathology, vol. 7, Mar 2 2012. [119] J. Benson, 'Is screening mammography safe for high-risk patients?,' Lancet Oncol, vol. 7, pp. 360-2, May 2006. [120] K. I. Kim, et al., 'Support vector machines for texture classification,' Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 1542-1550, Nov 2002. [121] X. J. Peng and D. Xu, 'Bi-density twin support vector machines for pattern recognition,' Neurocomputing, vol. 99, pp. 134-143, Jan 1 2013. [122] K. Hammouche, et al., 'A multilevel automatic thresholding method based on a genetic algorithm for a fast image segmentation,' Computer Vision and Image Understanding, vol. 109, pp. 163-175, Feb 2008. [123] J. Shawe-Taylor and N. Cristianini, Kernel methods for pattern analysis. Cambridge, UK ; New York: Cambridge University Press, 2004. [124] E. Alpaydin, Introduction to machine learning. Cambridge: Mass: MIT Press, 2004. [125] G. W. Heiman, Basic statistics for the behavioral sciences, 6th ed. Belmont, CA: Wadsworth Cengage Learning, 2011. [126] B. Efron and R. Tibshirani, 'Improvements on cross-validation: The .632+ bootstrap method,' Journal of the American Statistical Association, vol. 92, pp. 548-560, Jun 1997. [127] R. Xu, et al., 'Target detection with improved image texture feature coding method and support vector machine,' International Journal of Intelligent Technology, vol. 1, pp. 47-56, 2006. [128] C. H. Brase and C. P. Brase, Understanding basic statistics, 5th ed. Belmont, CA: Brooks/Cole, Cengage Learning, 2010. [129] J. A. Hanley and B. J. Mcneil, 'A Method of Comparing the Areas under Receiver Operating Characteristic Curves Derived from the Same Cases,' Radiology, vol. 148, pp. 839-843, 1983. [130] Y. H. Guo, et al., 'Breast ultrasound image enhancement using fuzzy logic,' Ultrasound in Medicine and Biology, vol. 32, pp. 237-247, Feb 2006. [131] G. R. Foxall and I. Szmigin, 'Adaption-innovation and domain-specific innovativeness,' Psychological Reports, vol. 84, pp. 1029-1030, Jun 1999. [132] H. Daume and D. Marcu, 'Domain adaptation for statistical classifiers,' Journal of Artificial Intelligence Research, vol. 26, pp. 101-126, 2006. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58929 | - |
| dc.description.abstract | 根據美國癌症協會的最新研究報告，乳癌是女性癌症死亡的第二大主因。因乳癌的切確形成原因還未能完整的了解，但我們能夠從早期的乳癌偵測與診斷有效用並有效率的增加臨床治療成功率同時降低不必要的腫瘤穿刺。超音波成影技術是目前其中一種廣泛使用來偵測與分類乳房腫瘤的非侵入式治療法。目前，有許多的研究學者致力於開發電腦輔助系統(如 CADx 和 CADe)來協助醫生解釋超音波影像如腫瘤偵測與診斷等的輔助工具。相對於使用傳統笨重且龐大的超音波掃描機器來做超音波影像的篩檢，可攜式的超音波設備更能提高病人的檢查比率。在本研究中，我們使用可攜式超音波機器Terason t3000 (Terason Ultrasound, Burlington, MA, USA) 並使用手持探頭擷取來源超音波影像以做進一步的分析。為了有效率的處理巨量資料的議題以利發展實用的全乳房腫瘤偵測臨床應用軟體，我們提出了快速簡易貝氏分類法來處理像素的分類問題與二階段的腫瘤篩選機制來挑出真正可疑的腫瘤同時壓低系統的偽陽性。我們所提出的系統能達到 93.94% 的偵測準確率及每百張超音波影像4.22個偽陽性誤判腫瘤，此系統能夠很有效的幫助醫生重新檢視系統所偵測出的少許可疑的腫瘤以利快速的完成第二次乳房檢查的進行。同時為了減少腫瘤的穿刺，許多的研究人員亦致力於使用以GLCM為基礎的紋理特徵開發電腦輔助診斷以協助腫瘤的診斷。但是，這些紋理特徵的研究分析並沒有考量到超音波機器上的參數設定會影響資料的取樣而造成跨機器平台診斷效能的變異。因此，我們的研究專注於使用超音波影像不受到亮度影響的轉換方法以開發一個可靠的電腦輔助診斷的系統。當我們從轉換後的超音波影像中擷取多解析度的特徵後，診斷的效能在此不受到亮度影像的特徵下比目前在發展中的紋理分析的結果都還要更好。我們做了一些實驗並進行接收者操作特徵分析 (ROC)，我們得到三台機器診斷的效能在接收者操作特徵分析下的面積(AUC)分別是0.918 (95% 信賴區間為 0.848 到 0.961), 0.943 (95% 信賴區間為 0.906 到 0.968) 以及 0.934 (95% 信賴區間為 0.883 到 0.961)。實驗的結果顯示使用數值排序法來進行紋理分析較不易受到跨機器平台的影響並且適合用來設計與開發一個可靠的臨床腫瘤診斷的應用軟體。 | zh_TW |
| dc.description.abstract | Breast cancer is the second leading cause of death for female as latest reported from the American Cancer Society (ACS). Since the exact causes of the disease remain unknown, early detection and diagnosis can effectively and efficiently increase successful clinical treatment while reducing unnecessary biopsies of breast masses. Ultrasound imaging is one of widely used non-invasive modality to detect and classify abnormalities of breast lesions. Recently, many researchers are dedicated to develop computer-aided systems (i.e., CADx and CADe) for breast cancer detection and diagnosis to aid radiologists in interpreting breast ultrasound (BUS) images. Compared to traditional heavy and large ultrasonic machines for screening BUS images, portable PC-based breast ultrasound (BUS) imaging systems can be adopted to improve the patient throughput. Herein, we use PC-based ultrasound machine Terason t3000 (Terason Ultrasound, Burlington, MA, USA) with free-hand probe to acquire the source BUS images for later analysis. To effectively address the big data issue while developing clinical applications for whole breast lesion detection, the proposed pixel classification based on naïve Bayes classifier is used to categorize the normal or lesion objects and two-phase lesion selection scheme is adopted to pick out all the suspected lesions with a lower false-positive rate. The proposed system present 93.94% with 4.22 false-positive per hundred slices and is effective for the radiologists to perform the second examination by merely reviewing the detected lesion objects of the proposed system. In order to reduce the biopsies of the breast masses, many researches devote to develop computer-aided diagnostic system using GLCM-based textural features for tumor diagnosis. Nonetheless, these texture analyses did not consider varied parameter setting of different ultrasonic devices might result in large variation of diagnostic performances across the sonographic platforms. Therefore, we aim at developing a robust computer-aided diagnostic system for BUS images based on the invariant gray-scale transform (i.e., ranklet transform). While multi-resolution features are extracted from the ranklet transformed BUS images for texture analysis, the diagnostic performances with the invariant texture features outperform those with state-of-art texture analyses. We conducted experiments in terms of receiver operating characteristic (ROC) analysis, the AUC values derived from the area under the curve for the three databases are 0.918 (95% confidence interval [CI], 0.848 to 0.961), 0.943 (95% CI, 0.906 to 0.968) and 0.934 (95% CI, 0.883 to 0.961), respectively. The experiments reveal the texture analyses using ranklet transform are less sensitive to different ultrasonic devices and properly adopted for designing a robust system for tumor diagnosis. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T08:39:20Z (GMT). No. of bitstreams: 1 ntu-102-D96922009-1.pdf: 2601913 bytes, checksum: c69b06974fb6f048c9b4bbbf387a75c4 (MD5) Previous issue date: 2013 | en |
| dc.description.tableofcontents | Contents
口試委員審定書 i Acknowledgments ii 摘要 iii Abstract v Contents viii List of Figures xi List of Tables xv Chapter 1 Introduction - 1 - 1.1 Research motivation - 1 - 1.2 Issue Description - 3 - 1.2.1 Whole Breast Lesion Detection Using Naive Bayes Classifier for Portable Ultrasound - 4 - 1.2.2. Robust Texture Analyses using Gray Scale Invariant Feature Representation for Breast Lesions Diagnosis - 5 - 1.3 Organization - 6 - Chapter 2 A Literature Review of Computer-aided Lesion Detection and Diagnosis for Breast Ultrasound - 8 - 2.1 A Literature Review of Computer-aided Lesion Detection for Breast Ultrasound - 9 - 2.2 A Literature Review of Computer-aided Lesion Diagnosis Using Texture Patterns for Breast Ultrasound - 11 - Chapter 3 Whole Breast Lesion Detection Using Naive Bayes Classifier for Portable Ultrasound - 14 - 3.1 Introduction - 14 - 3.2 Materials and Methods - 17 - 3.2.1 Patients and Lesion Characteristics - 17 - 3.2.2 Image Data Acquisition - 18 - 3.2.3 Whole Breast Lesion Detection Based on Naive Bayes Classifier - 19 - 3.2.4 Spatio-Temporal Resolution Down-sampling - 20 - 3.2.5 Tissue Feature Extraction - 24 - 3.2.6 Distribution Model Estimation for Feature Parameters and Pixels Reasoning by Naive Bayes Classification - 27 - 3.2.7 Suspected Lesions Extraction - 31 - 3.2.8 False Positive Rate Reduction via Two-phase Lesion Selection Criteria - 33 - 3.2.9 Separation of Classification of Holistic and Partial Lesions for Improving Detection Sensitivity - 37 - 3.3 Results - 38 - 3.3.1 Performance Quantitative Evaluation - 38 - 3.3.2 Discussion - 46 - Chapter 4 Robust Texture Analyses using Gray-Scale Invariant Feature Representation for Breast Lesions Diagnosis - 50 - 4.1 Introduction - 50 - 4.2 Materials - 53 - 4.3 Methods - 56 - 4.3.1 Robust Gray-Scale Invariant Ranklet Transform - 57 - 4.3.2 Multi-Resolution Gray-scale Invariant GLCM Texture Extraction - 60 - 4.3.3 Detailed Implementation of the texture analyses - 62 - 4.3.4 Texture Analysis for Breast Ultrasound Diagnosis using Support Vector Machine (SVM) - 66 - 4.3.5 Statistical Analysis - 67 - 4.4 Experiments - 69 - 4.4.1 Stability of the Texture Analysis via Ranklet Transform - 72 - 4.4.2 Robustness of the Texture Analysis via Ranklet Transform - 75 - 4.4.3 Statistical Analysis for the proposed texture analyses - 80 - 4.5 Discussion and Conclusion - 86 - Chapter 5 Conclusion and Future Works - 89 - References - 91 - Publications - 101 - List of Figures Fig. 2 1 The framework of a proposed computer-aided system - 9 - Fig. 3 1 The proposed clock-based storing mechanism. - 19 - Fig. 3 2 The framework of the proposed automatic lesion detection mechanism (a) An input image sequence I. (b) Perform spatio-temporal resolution down-sampling for resolution reduction to obtain a synthesized image S from the image sequence I. (c) Calculate mean and stick features via average filter and stick operator from the synthesized image S to derive the mean image Sn and stick image Sk, respectively. (d) Pixel-wise tissue classification using naïve Bayes classifier to produce a binary image C. Note that the tumor tissue is highlighted with black pixels. (e) Extract the morphological features from suspected regions and perform two-phase lesion selection criterion for false-positive rate reduction. - 20 - Fig. 3 3 The framework for determining a compact image from a serial of degraded 2-D images using edge-preserved minimum-intensity projection algorithm. (a) The spatial resolution down-sampling from the high-resolution images. (b) The edge maps for the degraded image. Note that the edge pixels are expressed as white pixels. (c) The compact image is obtained from the edge-preserved minimum-intensity projection of the consecutive degraded 2-D images and corresponding edge maps. - 23 - Fig. 3 4 The diagram for synthesizing an edge-preserved compact image using a series of degraded 2-D BUS images and corresponding edge maps. - 23 - Fig.3 5 The compact image obtained from different projection algorithms. (a) The compact image with the edge-preserved minimum-intensity projection. (i.e., edge-preserved mIP). (b) The compact image with the minimum intensity projection (i.e., mIP). (c) The difference image between image processed by edge-preserved mIP (a) and that processed by conventional mIP (b). Note that gray values in difference image are scaled for clear visualization. - 24 - Fig. 3 6 The sticks with size 5×5 mask and 8 templates of possible stick orientations. - 26 - Fig. 3 7 (a) An example compact image (b) The derived feature image calculated from the intensity local mean with 5×5 mask (c) The derived feature image calculated from the intensity local stick with 5×5 mask - 27 - Fig. 3 8 Statistical histograms and estimated Rayleigh distribution for feature parameters of both tissues. (a) The calculated statistical histograms of the feature parameters. (b) The estimated Rayleigh distribution for stick feature parameter of both tissues. - 29 - Fig. 3 9 (a) A compact BUS image (b) The classification result based on naive Bayes classifier. (c) The decision regions of the proposed feature parameters. The feature values of the inference pixels lay in the black decision region would be classified as the lesion tissues. - 31 - Fig. 3 10 A serial of 2-D compact BUS image slices with a suspected lesion, the lesion region with the dotted circle in image slice (i) is connected to the fat tissue and the lesion with solid circle is shown in image slice (iv). Note that the lesion is a 3-D connected component from image slice (i) to image slice (vi). - 33 - Fig. 3 11 Four connective compact image slices with first-phase lesion selection results. The 2-D lesions satisfy the first-phase selection criteria are highlighted with dotted circles. - 36 - Fig. 3 12 (a) A serial of 2-D compact image slices with suspected lesions satisfy the first-phase selection criteria. (b) The final determined result of a 2-D compact image slice with a real lesion after assessing by the region continuity criteria is shown for visualization. Note that the determined lesion is highlighted with dotted circle. - 36 - Fig. 3 13 The FROC curve of the two-phase lesion selection criteria. (a) First-phase: the sensitivity rate for non-split method is 96.97% (32/33) at 58.77 FPs per hundred slices (THnon-split = 0.93) and is 96.97% (32/33) at 39.67 FPs per hundred slices for split method (THsplit_inside = THsplit_outside = 0.94). (b) Second-phase: the sensitivity rate for non-split method is 93.94% (31/33) at 10.15 FPs per hundred slices (THnon-split = 0.1) and is 93.94% (31/33) at 4.22 FPs per hundred slices (THsplit_inside = 0.11, THsplit_outside = 0.08) for split method. - 41 - Fig. 3 14 A series of 2-D compact image slices and corresponding determined lesions. Note that the real lesion is highlighted with solid circle, and the false positive lesion is indicated by the dotted circle. (a) A true-positive case of a 1.0 cm invasive ductal carcinoma in right breast. (i) 10 o’clock region. (ii) 11 o’clock region. (b) A true-positive case of a 0.67 cm fibrocystic disease in left breast. (i) 1 o’clock region. (ii) 2 o’clock region. - 44 - Fig. 3 15 Two true-positive malignant cases with shadowing. Note that the detected real lesion is highlighted with solid circle and the shadow is indicated by the dotted circle. (a) A true-positive case of a 2.8 cm invasive ductal carcinoma. (b) A true-positive case of a 2.2 cm invasive ductal carcinoma. - 45 - Fig. 3 16 A false-negative case of 0.52 cm fibroadenoma in right breast and the real lesion is indicated by the dotted circle. (a) 10 o’clock. (b) 11 o’clock. - 46 - Fig. 4 1 The framework of the proposed multi-resolution texture analysis via ranklet transform. (a) Database (b) A BUS image I is decomposed into multiple ranklet images (i.e., R2H, R2V, R2D…) using ranklet transform (c) Multi-resolution (R2, R4 …) texture features are extracted from the ranklets to form the compact texture representation for each BUS image (d) SVM classifier is adopted to classify each BUS image from the database into a benign tumor or a malignant one. - 57 - Fig. 4 2 (a) The diagram for determining the ranklet coefficient of an arbitrary point p and resolution r in a moving square crop (b) The geometrical representation of the three orientations horizontal (H), vertical (V) and diagonal (D) directions of the square crop with subset Art(p) and Brt(p) (t = {H, V, D}) - 60 - Fig. 4 3 The ranklets (R8) and wavelets (W-1) with corresponding three orientations horizontal (H), vertical (V) and diagonal (D) are derived from an input BUS image I, I filtered by histogram equalization and gamma correction, respectively. Note that the coefficients of the wavelet and ranklet images are scaled for clear visualization. - 65 - Fig. 4 4 The diagnostic performance (AUC) comparison of origin, wavelets and ranklets using different number of scales for training the SVM classifiers of each database. The selected parameter C for linear SVMs of the three databases are (a) {2, 2, 32} (b) {16, 16, 8} (c) {8, 8, 8}, respectively. Note that the parameter set for the three methods is expressed as {origin, wavelets, ranklets}. - 71 - Fig. 4 5 Average AUC values calculated from 500 bootstrap samples of each database for the three texture analyses (a) origin (b) wavelets (c) ranklets. - 74 - Fig. 4 6 The computation time (μs/rp) of the ranklet transform with specific resolution r = {2, 4, 8, 16, 32, 64} - 84 - List of Tables Table 3 1 The sensitivity rates of different sizes of benign, malignant lesions and whole dataset. - 43 - Table 3 2 Three different FPs measurements under two detection sensitivity rates of the proposed split method - 43 - Table 4 1 Tumor histological distributions of the collected databases - 55 - Table 4 2 ROC texture analyses (Mean ± Standard Deviation) for Origin (Ori.), Wavelets (Wave.) and Ranklets (Rank.) with default texture descriptor calculated from 500 independent bootstrap samples - 75 - Table 4 3 Diagnostic performance evaluation (AUC values and 95% CI are listed) of cross-platform training/testing combination between each collected database - 79 - Table 4 4 Mean (Means) and standard deviation (SDs) for intensity mean and standard deviation of tumors for each database - 80 - Table 4 5 The p-value of the z-test on the AUC value while applying cross-platform training/testing or LOO-CV scheme between Ranklets and Wavelets, Ranklets and Origin - 82 - Table 4 6 The p-value of the Welch’s t-test on the distribution of the AUC values between Ranklets and Wavelets, Ranklets and Origin - 82 - Table 4 7 Texture features extracted from ranklet GLCMs - 83 - Table 4 8 The description of the symbols used in this work - 84 - | |
| dc.language.iso | en | |
| dc.subject | 乳癌 | zh_TW |
| dc.subject | 可攜式超音波 | zh_TW |
| dc.subject | 簡易貝式分類器 | zh_TW |
| dc.subject | 腫瘤偵測 | zh_TW |
| dc.subject | 可靠式電腦輔助診斷 | zh_TW |
| dc.subject | robust computer-aided diagnosis | en |
| dc.subject | portable ultrasound | en |
| dc.subject | Breast cancer | en |
| dc.subject | naive Bayes classifier | en |
| dc.subject | lesion detection | en |
| dc.title | 超音波電腦輔助腫瘤偵測與可靠性診斷 | zh_TW |
| dc.title | Computer-aided Lesion Detection and Robust Diagnosis for Breast Ultrasound | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 102-1 | |
| dc.description.degree | 博士 | |
| dc.contributor.oralexamcommittee | 曾宇鳳,廖弘源,張簡光哲,薛智文 | |
| dc.subject.keyword | 乳癌,可攜式超音波,簡易貝式分類器,腫瘤偵測,可靠式電腦輔助診斷, | zh_TW |
| dc.subject.keyword | Breast cancer,portable ultrasound,naive Bayes classifier,lesion detection,robust computer-aided diagnosis, | en |
| dc.relation.page | 102 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2013-10-09 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-102-1.pdf 未授權公開取用 | 2.54 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。