成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳紹哲 Chen, Shao-Jer
論文名稱：	醫用超音波影像定量紋路分析與組織病理的對照研究 QUANTITATIVELY CHARACTERIZING THE TEXTURAL FEATURE OF CLINICAL ULTRASONIC IMAGES WITH HISTOPATHOLOGICAL CORRELATION
指導教授：	鄭國順 Cheng, Kuo-Sheng
學位類別：	博士 Doctor
系所名稱：	工學院 - 醫學工程研究所 Institute of Biomedical Engineering
論文出版年：	2008
畢業學年度：	96
語文別：	英文
論文頁數：	108
中文關鍵詞：	淋巴結、乳癌、紋路分析、組織特徵、病理組織、甲狀腺結節、超音波影像
外文關鍵詞：	Thyroid nodules, Breast neoplasm, Histopathological finding, Tissue characterization, Textural analysis, Ultrasonic image, Lymph nodes
相關次數：	點閱：83 下載：1
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本論文旨在發展超音波影像定量紋路分析及其與組織病理關聯性之方法，臨牀使用的超音波儀為ATL HDI 3000 and GE LOGIQ 700。影像擷取時的參數皆獲得控制，超音波影像紋路特徵將詳細地與其病理特徵比對，乳癌病理切片亦數位化以計算間質組織與細胞數量。根據統計特徵矩陣之非相似值，乳房stellate carcinoma呈現最低相似值，circumscribed carcinoma呈現最高相似值，混雜間質與細胞的乳房惡性組織之非相似值則分布其中。正規化的間質與細胞比例與非相值呈現高度的線性相關，由相互關係矩陣乳房stellate carcinoma呈現高能量、低亂度、低對比值、低變異及低總和平均之超音波影像。在甲狀腺結節的實驗中，相互關係矩陣的總和平均值可充分的反映超音波之回音變化，纖維組織呈現最低的回音及最低的總和平均，大濾泡呈現高回音及高總和平均差值，乳突細胞及濾泡細胞則呈現中度的回音，甲狀腺結節的回音法則是濾泡及乳突細胞混雜越多的濾泡組織，回音性越高，間質組織則呈現相反之現象。轉移的淋巴結比良性淋巴結呈現較高的亂度值，其原因是因為腫瘤細胞之異質化浸潤。結核淋巴炎之低回音的乾酪化壞死及其顯著的低總和平均有助於其與轉移的淋巴結之鑑別。由實驗結果發現病理的成分與特徵可由超音波影像評估，本成果可用於切片、開刀計劃、監視疾病病程及療效評估。

In this thesis, a quantitative characterization of the ultrasonic image texture and its correlation with the histopathological finding is developed for facilitating clinical diagnosis. The ultrasound imaging system in clinical use is ATL HDI 3000 and GE LOGIQ 700. The parameters used for image acquisition are kept in the same conditions during clinical examination. The sonographic textural features are closely correlated with their histopathological findings. The amount of fibrous stroma and the cellularity of the corresponding breast cancer images were also calculated and quantified by digitally processing the images. Based on the dissimilarity values from statistical feature matrix, the breast stellate carcinoma shows the least dissimilarity in ultrasound images. The breast circumscribed carcinoma exhibits the most dissimilarity, and the breast malignant tissue mixed with fibrous and cellular parts has the dissimilarity values in between. Both the normalized percentage of fibrosis area and cellular area have highly linear correlation with the textural feature of dissimilarity. From the coocurrence matrix, the stellate carcinoma also reveals the image of high energy, low variance, low entropy, or low sum average. In the study of thyroid nodules, the sum average value derived from co-occurrence matrix can well reflect echogenicity. Fibrosis shows lowest echogenicity and lowest sum average value. Enlarged follicles show highest echogenicity and different sum average value. Papillary or follicular tumors show the echogenicity in between. The rule of thumb for the echogenicity is that the more follicles mixed in, the higher echo of the follicular and papillary tumor, and vice versa for fibrosis mixed. There are significantly higher entropy values of the metastatic lymph nodes than of the benign lymph nodes due to more heterogeneous pattern of cancer cells infiltration. The characteristics of hypoechoic caseous necrosis and the significantly lower sum average value of TB lymphadenitis allow the differentiation between TB and metastases. From the experimental results, it is shown that the pathologic features and components could be predicted on ultrasonography. They can be applied to biopsy or surgery planning, disease progression monitoring and therapeutic effect evaluation. The proposed image analysis method may also be extended to similar characterization of histopathological tissue in other applications.

中文摘要		I
ABSTRACT		II
致 謝		IV
LIST OF TABLES	VII
LIST OF FIGURES	VIII
CHAPTER 1 INTRODUCTION	1
1.	Background and Motivation	1
2	Literature review	2
3	Problem statement	2
CHAPTER 2 ULTRASOUND IMAGE ANALYSIS	4
1.	Patients	4
2.	Instrument	5
3.	Ultrasound image analysis	6
3.1.	Statistical feature matrix (SFM)	6
3.2	Co-occurrence matrix	7
3.3	Laws’ Texture	9
3.4	Wavelet feature	9
3.5	Neighboring Gray Level Dependence Matrix	11
3.6	Gray Level Run-Length Matrix	13
3.7	Fourier feature based on local fourier coefficients	15
3.8	Stepwise logistic regression analysis for feature selection	16
3.9	Relief-F feature selection algorithm	18
3.10	Software Design	19
CHAPTER 3 HISTOPATHOLOGICAL IMAGE ANALYSIS	22
1	The HSI color space	22
2	The YIQ color space	22
3	Software Design	23
CHAPTER 4 EXPERIMENTAL RESULTS	27
1	Correlation between the ROIs area and histopatholgy area	27
2	Statistical feature matrix and histopathological correlation	34
3	Co-occurrence matrix and histopathological correlation	41
4	Stepwise logistic regression (SLR) analysis for feature selection	47
5	Quantitative Correlation between Sonographic Texture Feature and Histopathology for Breast Cancer	49
5.1	Linear regression: an example of statistical feature matrix	49
5.2	Feature selection using stepwise multiple linear regression	56
6	Textural differences between metastatic and benign lymph nodes with histopathologic correlation	58
7	Sonographic texture of the major histopathological components of thyroid nodules	61
CHAPTER 5	CORRELATION BETWEEN SONOGRAPHIC TEXTURE FEATURE AND HISTOPATHOLOGY	64
1	SFM for breast cancer with histopathological correlation.	64
2	Co-ocurrence matrix for breast cancer with histopathological correlation.	71
3	Stepwise logistic regression analysis for feature selection	79
4	Quantitative Correlation between Sonographic Texture Feature and Histopathology for Breast Cancer	81
4.1	Linear regression between SFM and histopathology for breast cancer	81
4.2	Feature selection using stepwise multiple linear regression	87
5	Textural differences between metastatic and benign lymph nodes with histopathologic correlation	89
6	Sonographic texture of the major histopathological components of thyroid nodules	93
CHAPTER 6 CONCLUSION	99
REFERENCES		101
                                    

1. J. C. Bamber, L. De Gonzalez, D. O. Cosgrove, et al, “Quantitative evaluation of real-time ultrasound features of the breast”. Ultrasound in Medicine & Biology. 14 Suppl 1:81-7, 1988.
2. D. R. Chen, R. F. Chang, Y. L. Huang, et al, “Computer-aided diagnosis applied to US of solid breast nodules by using neural networks”. Radiology 213: 407-412, 1999.
3. C. M. Wu, Y. C. Chen, K. S. Hsieh, “Texture features for classification of ultrasonic liver images”. IEEE Transactions on medical imaging 11:141-152, 1992.
4. Y. N. Sun, M. H. Horng, X. Z. Lin, “Ultrasonic image analysis for liver diagnosis”. IEEE Engineering in Medicine and Biology 15:93-101, 1996.
5. HDI 3000 Ultrasound system reference manual. ATL, 1995.
6. LOGIQ 700 Expert Series: Conformance Statement for DICOM V3.0. Direction 2243479-100, Revision 1. Technical Publications. GE Healthcare, Chalfant St. Giles, UK. Available at:http://www.gehealthcare.com/usen/interoperability/dicom/docs/logiq700_rev2.pd
7. C. M. Wu, T. C. Chen, “Statistical feature matrix for texture analysis”. CVGIP 54:407-419, 1992.
8. R. M. Haralick, K. Shanugam, I. Dinstein, “Texture features for image classification”. IEEE Trans. Syst. Man. Cybernet 3:610-621, 1973.
9. C. M. Wu, Y. C. Chen, K. S. Hsieh, “Texture features for classification of ultrasonic liver images”. IEEE Transactions on medical imaging 11:141-152, 1992.
10. M. Antonini, M. Barlaud, P. Mathieu and I. Daubechies, “Image coding using wavelet transform. IEEE tranactions of image processing”. 1(2):205-220, 1992.
11. C. Sun and W. G. Wee, “Neighboring gray level dependence matrix for texture classification”. Computer vision, grahics and image processing 23:341-352, 1982.
12. H. H. Loh, J. G. Leu, R. C. Luo, “The analysis of natural textures using run length features”. IEEE Transactions on industrial electronics 35(2):323-328, 1988.
13. F. Zhou, J. F. Feng, Q. Y. Shi, “Texture feature based on local Fourier transform”, Image Processing, 2001. Proceedings. 2001 International Conference. 2: 610 – 613, 2001.
14. SAS OnlineDoc version 7-1. SAS Institute Inc., 1999.
15. Y. H. Chou, C. M. Tiu, G. S. Hung, S. C. Wu, T. Y. Chang, H. K. Chiang, “Stepwise Logistic Regression Analysis of Tumor Contour Features for Breast Ultrasound Diagnosis,” Ultrasound in Medicine and Biology, vol. 27, no. 11, pp. 1493- 1498, 2001.
16. R. S. Marko, I. Kononenko, “Theoretical and Empirical Analysis of ReliefF and RReliefF”. Machine Learning Journal 53:23-69, 2003.
17. I. Kononenko, “Estimating attributes: Analysis and extensions of RELIEF”. Proceedings of the 1994 European Conference on Machine Learning:171-182, 1994.
18. R. C. Gonzales and R. E. Woods, Digital Image Processing. Reading, MA, Addison-Wesley, 1992.
19. J. D. Foley, A. V. Dam, S. K. Feiner, J. F. Hughes, Computer graphics: principles and practice. Addison-Weley, 1992.
20. A. T. Stavros, D. Thickman, C. L. Rapp, et al, Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. Radiology 196(1):123-134, 1995.
21. E. Ueno, “Breast ultrasound”. Gan to Kagaku Ryoho [Japanese Journal of Cancer & Chemotherapy] 23 Suppl 1:14-23, 1996.
22. A. J. Roy, C. H. Patrick, M. James, Pathology for Surgeons 2nd ed. Great Britain, Pa: Butterworth-Heinemann, 293-294, 1993.
23. G. Gozzi, C. Cressa, M. Bazzocchi, et al, “Causes of attenuation of the sound waves in neoplasms of the breast. Histologic and echographic correlation study”. Radiologia Medica 72(4): 195-8, 1996.
24. B. Andrea, P. Flavio, “An investigation of the textural characteristics associated with gray level co-occurrence matrix statistical parameters”. IEEE Trans. Geoscience and Remote Sensing 33:293-304, 1995.
25. T. Sergios and K. Konstantinos, Pattern Recognition. Academic Press, 2003.
26. P. Gong, J. D. Marceau, and P. J. Howarth, "A comparison of spatial feature extraction algorithms for land-use classification with SPOT HRV data," Remote Sensing Environ 40: 137-151, 1992.
27. T. K. Hirose, L. McNutt and J. S. Paterson, “A study of textural and tonal information for classifying sea ice SAR imagery,” Proc. IGARSS ’89, Vancouver, Canada, 747-750, 1989.
28. S. J. Chen, K. S. Cheng, Y. C. Dai, et al, “Quantitatively characterizing the texture feature of ultrasonic images for breast cancer with histopathological correlation”. Journal of ultrasound in medicine 24:651-661, 2005.
29. A. Ahuja, M. Ying, “An overview of neck node sonography”. Invest Radiol 37:333-342, 2002.
30. W. Isarangkul, “Dense fibrosis. Another diagnostic criterion for papillary thyroid carcinoma”. Arch Pathol Lab Med. 117(6):645-646, 1993.
31. T. Eriko, O.C. David, P.S. John, Diagnostic features on ultrasound. Ultrasound diagnosis of the breast disease. 1st ed. UK, Pa: Churchill Livingstone, 54-55, 1994.
32. S.J. Perry. Physical Principles of Medical Imaging. Ultrasound Imaging. 2nd ed. US, Pa: Aspen Publishers, Inc, 93-395, 1993.
33. B.S. Garra, B.H. Krasner, S.C. Horii, et al, “Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis”. Ultrasonic Imaging 15:267-285, 1993.
34. F.K. Zentrum FK, H.H. Medizinichen, “Texture analysis: a new method for evaluating ultrasound imaged lesions of the breast”. Bildgebung 61:284-290, 1994.
35. A. Jemal, T. Murray, A. Samuels , A. Ghafoor, E. Ward, M.J. Thun. “Cancer statistics, 2003”. CA Cancer J Clin 53: 25–26, 2003.
36. S. Huber, J. Danes, I. Zuna, J. Teubner, M. Medl, S. Delorme, “Relevance of sonographic B-mode criteria and computer-aided ultrasonic tissue characterization in differential/diagnosis of solid breast masses”. Ultrasound in Medicine & Biology 26: 1243-52, 2000.
37. S. Huber, M. Medl, M. Vesely, H. Czembirek, I. Zuna, S. Delorme, “Ultrasonographic tissue characterization in monitoring tumor response to neoadjuvant chemotherapy in locally advanced breast cancer (work in progress)”. Journal of Ultrasound in Medicine 19: 677-86, 2000.
38. B.D. Fornage, N. Sneige, B.S. Edeiken, “Interventional breast sonography”. European Journal of Radiology 42:17-31, 2002.
39. M.C. Frates, C.B. Benson, J.W. Charboneau, E.S. Cibas, O.H. Clark, B.G. Coleman, J.J. Cronan, P.M. Doubilet, D.B. Evans, J.R. Goellner, I.D. Hay, B.S. Hertzberg, C.M. Intenzo, R.B. Jeffrey, J.E. Langer, P.R. Larsen, S.J. Mandel, W.D. Middleton, C.C. Reading, S.I. Sherman, F.N. Tessler, “Management of Thyroid Nodules Detected at US: Society of Radiologists in Ultrasound Consensus Conference Statement”. Radiology 237:794-800, 2005.
40. D.S. Cooper, G.M. Doherty, B.R. Haugen, R.T. Kloos, S.L. Lee, S.J. Mandel, E.L. Mazzaferri, B. McIver, S.I. Sherman, R.M. Tuttle, “The American Thyroid Association Guidelines Taskforce. Management guidelines for patients with thyroid nodules and differentiated thyroid cancer”. Thyroid 16(2):109-42, 2006.
41. M.R. Carol, R.W. Stephanie, J.W. Charboneau, J.A. Johnson, Diagnostic ultrasound. Elsevier Mosby, Philadelphia, PA, 735-757, 2005.
42. T.C. Chang, C.T. Hong, S.L. Chang, H.C. Hsieh, K.Y. Liaw, S.W. How, “Correlation between sonography and pathology in thyroid diseases”. Journal of the Formosan Medical Association 89:777-83, 1990.
43. F.N. Tessler, M.E. Tublin, “Thyroid sonography: current applications and future directions”. AJR Am J Roentgenol 173:437-43, 1999.
44. C. Lu, T.C. Chang, Y.L. Hsiao, M.S. Kuo, “Ultrasonographic findings of papillary thyroid carcinoma and their relation to pathologic changes”. Journal of the Formosan Medical Association 93:933-938, 1994.
45. L.S. Chow, H. Gharib, J.R. Goellner, J.A. van Heerden, “Nondiagnostic thyroid fine-needle aspiration cytology: management dilemmas”. Thyroid 11:1147–1151, 2001.
46. H. Gharib, J.R. Goellner, A.R. Zinsmeister, C.S. Grant, J.A. Van Heerden, “Fine-needle aspiration biopsy of the thyroid. The problem of suspicious cytologic findings”. Ann Intern Med 101:25–28,1984.
47. Z.W. Baloch, S. Fleisher, V.A. LiVolsi, P.K. Gupta, “Diagnosis of “follicular neoplasm”: A gray zone in thyroid fine needle aspiration cytology”. Diagn Cytopathol 26:41–44, 2002.
48. G.M. Sclabas, G.A. Staerkel, S.E. Shapiro, B.D. Fornage, S.I. Sherman, R. Vassillopoulou-Sellin, J.E. Lu, D.B. Evans. “Fine-needle aspiration of the thyroid and correlation with histopathology in a contemporary series of 240 patients”. Am J Surg 186:702–709; discussion 709–710, 2003.
49. T.J. Jonas, “A surgeon looks at cervical lymph nodes”. Radiology 175: 607-610, 1990.
50. Y. Toriyabe, T. Nishimura, S. Kita, Y. Saito, N. Miyokawa, “Differentiation between benign and metastatic cervical lymph nodes with ultrasound”. Clin Radiol. 52(12):927-32, 1997.

校內：2009-01-22公開
校外：2010-01-22公開

簡易檢索 / 詳目顯示

相關論文