臺灣博碩士論文加值系統

輪廓資訊乃是許多超音波臨床研究的基石。其不但可以藉以描述解剖結構的型態特色而闡明病灶，且能在許多超音波影像的量化分析上扮演舉足輕重的角色。舉例而言，欲衡量心臟的功能，量化心臟內外表面的跳動形變乃是必要的。而若要使得量化分析的結論具有說服力，則輪廓資訊需是可靠且有效率的取得，如此一來，健全的超音波影像分割技巧，乃是必要的。
本文將超音波影像分割之課題分成兩個子議題，也就是二維影像以及二為影像序列的分割。針對此兩議題，我們分別提出ACCOMP以及C2RC-MAP兩演算法，來解決此兩子議題。此兩提出演算法的特色，在於其皆是以區域單元為基礎。所謂區域單元，乃是經由兩次分水嶺演算法所得到的水漥，而其在兩個演算法的功用，乃是取代像素而為基本搜尋的單位。利用區域單元為基本單位的益處有三。其一，相較於直接使用像素為搜尋單位，使用區域單元乃是較為有效率的。其緣由乃在於對於每個影像上，產生出來的區域單元之個數是遠比象素的數量來得小，因此，從效率分析的角度而言，乃是較為有效率的。其二，區域單元不僅可以提供區域的資訊，亦能提供邊界資訊。此兩種具體的線索，乃是像素所不能提供的。其三，由於區域單元乃是由一群具有相似灰階值強度的像素所組成，在統計的觀點而言，其對於雜訊的強健度乃是較單一之像素來的好。由是觀之，我們認為，利用區域單元為基本搜尋單位乃是較像素來得有效且更為有效率的。
ACCOMP演算法乃是由兩階段所組成。第一個階段的目的，乃是欲將影像或者感興趣的影像區塊加以分割成顯著區域；而第二階段的目的，乃是希望能將顯著區域中所保有的邊界訊息加以組織，而成有意義的輪廓。著眼於邊界資訊，對於目標物的內部複雜材質表現之問題，我們得以有效的避免。此二維影像分割演算法以測試了三百張乳房腫瘤超音波影像，並將演算法所得到的結果與手繪的輪過相比較。測試的結果證實，演算法產生的輪廓與手繪的差異比手繪與手繪間的差異來得小，且演算法的穩定性也是相當可靠的。
為了確保所得到的輪廓與肉眼測知的結果相近，以及序列上的連續性，我們提出了C2RC-MAP演算法，以克服序列影像的分割問題。該演算法的特色，乃是在於其在每張序列影像上，予以兩區域的競爭，也就是目標物區域與背景區域間的競爭。此兩區域競爭其所包夾的區域單元，以求所得到的兩區域分隔界線是較為明顯且仍舊保有序列上的連續性。我們將C2RC-MAP演算法測試了十組乳房腫瘤序列，其中，有三組是空間序列，而其餘七組是連續受壓序列。連續受壓序列包含兩個惡性以及五個良性腫瘤病例，而空間序列則是兩組惡性及一組良性病例。同樣地，演算法所得到的結果與手繪的輪過相比較。測試的結果證實，演算法產生的輪廓與手繪的差異比手繪與手繪間的差異來得小，且演算法的穩定性也是相當可靠的。除此之外，我們也將C2RC-MAP演算法的結果與Chan and Vese 的level set method演算法相比較，而發現，C2RC-MAP的結果是較為穩定與優良的。

Boundary information of the object of interest in sonography is the fundamental basis for many clinical studies. It can help to manifest the abnormality of anatomy by characterizing the morphological features and plays the essential role in numerous quantitative ultrasound image analyses. For instance, the evaluation of functional properties of heart demands the quantification of the deformation of epi- and endo-cardiac surfaces. To draw a convincing conclusion for the quantitative analysis, the boundary information should be reliable and efficiently generated― which means robust image segmentation techniques are necessary.
This study addresses the challenging segmentation problem of ultrasound images into two parts: 2D and 2D series. Theses two parts are attacked by the two proposed algorithms, i.e. ACCOMP and C2RC-MAP algorithms, respectively. The unique feature of the proposed algorithms is the concept of cell-based. The cell is the catchment basin tessellated by two-pass watershed transformation and is served as the basic operational unit in the two proposed algorithms. Taking the cell tessellation as the basis can be beneficial in three main points. First, comparing to directly finding solutions on pixels, searching on cells is more efficient. It is because the search space spanned by cells is dramatically smaller than the space of pixels. Therefore redundant computation could be saved. Second, the concrete region and edge information can be obtained in the cell tessellation. The concrete information in regions and edges could be valuable clues to assist the segmentation task. Third, as the cell is the group of pixels with homogeneous intensity, it might be more robust to noise in statistics— which could potentially improve the task of image process in ultrasound images. With these three advantages, cell-based image segmentation approaches might be more efficacious and efficient than pixel-based approaches.
The ACCOMP algorithm is a two-phase data-driven approach, which is constituted by the partition and the edge grouping phases. The partition phase is purposed to tessellate the image or ROI with prominent components and is carries out by the cell competition algorithm. For the second phase, it is realized by the cell-based graph-traversing algorithm. Focusing on the edge information, the complicated echogenicity problem can be bypassed. The ACCOMP algorithm is validated on 300 breast sonograms, including 165 carcinomas and 135 benign cysts. The results show that more than 70% of the derived boundaries fall within the span of the manually outlines under 95% confident interval. The robustness of reproducibility is confirmed by the Friedman test, the p-values of which is 0.54. It has also suggested that the lesions sizes derived by the ACCOMP algorithm are highly correlated with the lesions defined by the average manually delineated boundaries.
To ensure the delineated boundaries of a series of 2D images closely following the visually perceivable edges with high boundary coherence between consecutive slices, the C2RC-MAP algorithm is proposed. It deforms the region boundary in a cell-by-cell fashion through a cell-based two-region competition process. The cell-based deformation is guided by a cell-based MAP framework with a posterior function characterizing the distribution of the cell means in each region, the salience and shape complexity of the region boundary and the boundary coherence of the consecutive slices. The C2RC-MAP algorithm has been validated using 10 series of breast sonograms, including 7 compression series and 3 freehand series. The compression series contains 2 carcinoma and 5 fibroadenoma cases and the freehand series 2 carcinoma and 1 fibroadenoma cases. The results show that more than 70% of the derived boundaries fall within the span of the manually delineated boundaries. The robustness of the proposed algorithm to the variation of ROI is confirmed by the Friedman tests, the p-values of which are 0.517 and 0.352 for the compression and freehand series groups, respectively. The Pearson’s correlations between the lesion sizes derived by the proposed algorithm and those defined by the average manually delineated boundaries are all higher than 0.990. The overlapping and difference ratios between the derived boundaries and the average manually delineated boundaries are mostly higher than 0.90 and lower than 0.13, respectively. For both series groups, all assessments conclude that the boundaries derived by the proposed algorithm be comparable to those delineated manually. Moreover, it is shown that the proposed algorithm is superior to the Chan and Vese level set method based on the paired-sample t-tests on the performance indices at 5% significance level.

CHAPTER 1 6
CHAPTER 2 13
2.1 CELL COMPETITION ALGORITHM 19
Cell Generation Stage 21
Cell Competition Mechanism 25
2.2 CELL-BASED GRAPH-SEARCHING ALGORITHM 36
Establishment of the C-Graph 40
Relief of Cell-Edges 44
Edges Grouping by Constrained Depth First Search Scheme 46
Contour Selection under Five Criteria 51
Heuristic Guess of the Initial Cell-edge 52
CHAPTER 3 58
3.1 CELL-BASED MAP SCHEME 61
3.2 REGION APPEARANCE PROBABILITY MODEL 65
3.3 CONTOUR MODEL 65
3.4 LABELING PRIOR 69
3.5 EM ALGORITHM 72
CHAPTER 4 74
4.1 ACCOMP ALGORITHM 76
4.2 C2RC-MAP ALGORITHM 81
CHAPTER 5 104
REFERENCE 110

[1]X. Papademetris, A. J. Sinusas, D. P. Dione, and J. S. Duncan, “Estimation of 3D left ventricular deformation from echocardiography,” Medical Image Analysis, 5(1): pp. 17-28, 2001.
[2]X. Papademetris, A. J. Sinusas, D. P. Dione, T. Constable, and J. S. Duncan, “Estimation of 3-D left ventricular deformation from medical images using biomechanical Models,” IEEE Trans. Med. Imag., 21(7): pp. 786-800, 2002.
[3]G. Jacob, J. A. Noble, M. Mulet-Parada, and A. Blake, “Evaluating a robust contour tracker on echocardiographic sequences,” Medical Image Analysis, 3(1): pp. 63-75, 1999.
[4]G. Jacob, J. A. Noble, A. D. Kelion, and A. P. Banning, “Quantitative regional analysis of myocardial wall motion,” Ultrasound Med. Biol., 27(6): pp. 773-784, 2001.
[5]G. Jacob, J. A. Noble, C. Behrenbruch, A. D. Kelion, and A. P. Banning, “A shape-space-based approach to tracking myocardial borders and quantifying regional left-ventricular function applied in echocardiography,” IEEE Trans. Med. Imag., 21(3): pp. 226-238, March 2002.
[6]A. Stavros, D. Thickman, C. Rapp, M. Dennis, S. Parker, and G. Sisney, “Solid breast nodules: use of sonography to distinguish between benign and malignant lesions,” Radiology, 196: pp. 123-134, 1995.
[7]P. Skaane and K. Engedal, “Analysis of sonographic features in the differentiation of fibroadenoma and invasive ductal carcinoma,” American Journal of Roentgenology, 170: pp. 109-114, 1998.
[8]Y. H. Chou, C. M. Tiu, G. S. Hung, S. C. Wu, T. Y. Chang and H. K. Chiang, “Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis,” Ultrasound Med. Biol., 27(11): pp. 1493-1498, 2001.
[9]C. M. Chen, Y. H. Chou, K. C. Han, G. S. Hung, C. M. Tiu, H. J. Chiou and S. Y. Chiou, “Computer-aided diagnosis of breast lesions on sonogram using nearly setting-independent features and artificial neural networks,” Radiology, 226(2): pp. 504-514, 2003.
[10]W. K. Moon, R. F. Chang, C. J. Chen, D. R. Chen, and W. L. Chen, “Solid breast masses: classification with computer-aided analysis of continuous US images obtained with probe compression,” Radiology, 236: pp. 458-464, 2005.
[11]S. E. Nissen, J. C. Gurley, C. L. Grines, D. C. Booth, R. McClure, M. Berk, C. Fischer, and A. N. DeMaria, “Intravascular ultrasound assessment of lumen size and wall morphology in normal subjects and patients with coronary artery disease," Circulation, 84(3): pp. 1087-1099, 1991.
[12]S. E. Nissen and P. Yock, “Intravascular ultrasound: novel pathophysiological insights and current clinical application,” Circulation, 103(4): pp. 604-616, 2001.
[13]P. R. Liebson and L. W. Klein, “Intravascular ultrasound in coronary atherosclerosis: A new approach to clinical assessment,” American Heart Journal, 123: pp. 1643-1660, 1991.
[14]G. R. Lockwood, L. K. Ryan, A. I. Gottlieb, E. Lonn, J. W. Hunt, P. Liu, and F. S. Foster, “In vitro high resolution intravascular imaging in muscular and elastic arteries,” J. Am. Coll. Cardiol., 20: pp. 203-214, 1992.
[15]D. Y. Lee, N. Eigler, H. Luo, T. Nishioka, S. Tabak, J. S. Forrester, and R. J. Siegel, “Effects of intracoronary ultrasound imaging on clinical decision making,” American Heart Journal, 129(6): pp. 1084-93, 1995.
[16]F. Shao, K. V. Ling, W. S. Ng, and R. Y. Wu, “Prostate boundary detection from ultrasonographic images,” J. Ultrasound Med., 22(6): pp. 605-623, June 2003.
[17]J. Bakker, M. Olree, R. Kaatee, E. E. de Lange, and R. J. A. Beek, “Renal volume measurements: Accuracy and repeatability of US compared with that of MR imaging,” Radiology, 211: pp. 623-628, 1999.
[18]M. Martin-Fernandez and C. Alberola-Lopez, “An approach for contour detection of human kidneys for ultrasound images using Markov random fields and active contours,” Medical Image Analysis, 9(1): pp. 1-23, 2005.
[19]J. A. Noble and D. Boukerroui, “Ultrasound image segmentation: A survey,” IEEE Trans. Med. Imag., 25(8): pp. 987-1010, Aug. 2006.
[20]D. Shen, Y. Zhan and C. Davatzikos, “Segmentation of prostate boundaries from ultrasound images using statistical shape model,” IEEE Trans. Med. Imag., 22(4): pp. 539-551, April 2003.
[21]L. Gong, S. D. Pathak, D. R. Haynor, P. S. Cho, and Y. Kim, “Parametric shape modeling using deformable superellipses for prostate segmentation,” IEEE Trans. Med. Imag., 23(3): pp. 340-349, March 2004.
[22]E. Brusseau, C. L. de Korte, F. Mastik, J. Schaar, and A. F. W. van der Steen, “Fully automatic luminal contour segmentation in intracoronary ultrasound imaging: A statistical approach,” IEEE Trans. Med. Imag., 23(6): pp. 554-566, May 2004.
[23]M. Song, R. M. Haralick, F. H. Sheehan, and R. K. Johnson, “Integrated surface model optimization for freehand three-dimensional echocardiography,” IEEE Trans. Med. Imag., 21(9): pp. 1077-1090, September 2002.
[24]J. Xie, Y. Jiang, and H. Tsui, “Segmentation of kidney from ultrasound images based on texture and shape priors,” IEEE Trans. Med. Imag., 24(1): pp. 45-57, January 2005.
[25]S. C. Mitchell, J. G. Bosch, B. P. F. Lelieveldt, R. J. van der Geest, J. H. C. Reiber, and M. Sonka, “3-D active appearance models: Segmentation of cardiac MR and ultrasound images,” IEEE Trans. Med. Imag., 21(9): pp. 1167-1178, September 2002.
[26]J. G. Bosch, S. C. Mitchell, B. P. F. Lelieveldt, F. Nijland, O. Kamp, M. Sonka and J. H. C. Reiber, “Automatic segmentation of echocardiographic sequences by active appearance motion models,” IEEE Trans. Med. Imag., 21(11): pp. 1374-1383, November 2002.
[27]C. M. Chen, Y. H. Chou, C. S. K. Chen, J. Z. Cheng, Y. F. Ou, F. C. Yeh, and K. W. Chen, “Cell-competition algorithm: a new segmentation algorithm for multiple objects with irregular boundaries in ultrasound images,” Ultrasound Med. Biol., 31(12): pp. 1647-1664, 2005.
[28]V. Chalana, D. T. Linker, D. R. Haynor, and Y. Kim, “A multiple active contour model for cardiac boundary detection on echocardiographic sequences,” IEEE Trans. Med. Imag., 15(3): pp. 290-298, June 1996.
[29]I. Mikic, S. Krucinski, and J. D. Thomas, “Segmentation and tracking echocardiographic sequences: Active contours guided by optical flow estimates,” IEEE Trans. Med. Imag., 17(2): pp. 274-284, Apr. 1998.
[30]C. Corsi, G. Saracino, A. Sarti, and C Lamberti, “Left ventricular volume estimation for real-time three-dimensional echocardiography,” IEEE Trans. Med. Imag., 21(9): 1202–1208, 2002.
[31]X. J. Ye, A. J. Noble, and D Atkinson, “3-D freehand echocardiography for automatic left ventricle reconstruction and analysis based on multiple acoustic windows,” IEEE Trans. Med. Imag., 21(9): 1051–1058, 2002.
[32]A. Krivanek and M Sonka, “Ovarian ultrasound image analysis: Follicle segmentation,” IEEE Trans. Med. Imag., 17(6): 935–944, 1998.
[33]K. Drukker, M. L. Giger, et. al., ”Computerized lesion detection on breast ultrasound,” Medical Physics, 29(7): 1438–1446, 2002.
[34]B. Cigale and D. Zazula, “Segmentation of ovarian ultrasound images using cellular neural networks,” Int. J. Pattern Recogn., 18(4): 563–581, 2004.
[35]N. Archip, et. al., “Ultrasound image segmentation using spectral clustering,” Ultrasound Med. Biol., 31(11): 1485–1497, 2005.
[36]S. Joo, et. al., “Computer-aided diagnosis of solid breast nodules: Use of an artificial neural network based on multiple sonographic features,” IEEE Trans. Med. Imag., 23(10): 1292–1300, 2004.
[37]J. Shi and J. Malik, “Normalized cut and image segmentation”, IEEE TPAMI, 22(8): 888-905, 2000.
[38]Z. Tu and S. C. Zhu, “Parsing images into regions, curves, and curve grouping”, Int’l J. of Computer Vision, 69(2): 223-249, 2006.
[39]J. M. Gauch, “Image segmentation and analysis via multiscale gradient watershed hierarchies,” IEEE Trans Image Processing, 8(1): 69-79, 1999.
[40]L. Vincent and P. Soille, “Watershed in digital spaces: an efficient algorithm based on immersion simulations,” IEEE Trans PAMI, 13(6): 583-597, 1991.
[41]S. Wang, T. Kubota, J. M. Siskind, and J. Wang, “Salient closed boundary extraction with ratio contour,” IEEE TPMI, 27(4): 546–561, 2005.
[42]W. Köhler, “Gestalt psychology,” Psychological Research, 31(1): 18-30, 1967.
[43]Y. Zhan and D. Shen, “Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method,” IEEE Trans. Med. Imag., 25(3): 256-273, 2006.
[44]S. C. Zhu and A. Yuille, “Region competition: Unifying snakes, region growing, and bayes /MDL for multiband image segmentation,” IEEE Trans. Pattern Anal. Machine Intell., 18(9):884–900, 1996.
[45]T. Leung and J. Malik, “Contour continuity in region based on image segmentation”, Proc. ECCV 1999, 1: 544-559.
[46]A. Desolneux, L. Moisan, and J. M. Morel, “A grouping principle and four application,” IEEE Trans. Pattern Anal. Machine Intell., 25(4): 508-513.
[47]B. Fischer, J. M. Buhmann, “Path-based clustering for grouping of smooth curves and texture segmentation,” IEEE Trans. Pattern Anal. Machine Intell., 25(4): 513-518.
[48]S. Mahamud, L. R. Williams, K. K. Thornber, and K. Xu, “Segmentation of multiple salient closed contours from real images,” IEEE Trans. Pattern Anal. Machine Intell., 25(4): 433-444.
[49]G. I. Sanchez-Ortiz, G. J. T. Wright, N. Clarke, J. Declerck, A. P. Banning, and J. A. Noble, “Automated 3-D echocardiography analysis compared with manual delineations and SPECT MUGA,” IEEE Trans. Med. Imag., 21(9): pp. 1069-1076,Sept. 2002.
[50]I. Dydenko, F. Jamal, O. Bernard, J. D’hooge, I. E. Magnin, and D. Friboulet, “A level set framework with a shape and motion prior for segmentation and region tracking in echocardiography”, Medical Image Analysis, 10: pp. 162-177, 2006.
[51]C. Hass, H. Ermert, S. Holt, P. Grewe, A. Machraoui, and J. Barmeyer, “Segmentation of 3D intravascular ultrasonic images based on a random field model,” Ultrasound Med. Biol., 26(2): 297-306, 2000.
[52]A. P. Dempster, N. M. Laird, and D.B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” Journal of the Royal Statistical Society, 39: 1-38, 1977.
[53]J. Z. Cheng, C. M. Chen, Y. H. Chou, C. S. K. Chen, C. M. Tiu, and K. W. Chen. “Cell-based two-region competition algorithm with a MAP framework for boundary delineation of a series of 2D ultrasound images,” To appear in Ultrasound Med. Biol., 2007.
[54]J. E. Cates, R. T. Whitaker, and G. M. Jones, “Case study: an evaluation of user-assisted hierarchical watershed segmentation,” Medical Image Analysis, 9: 566-578, 2005.
[55]C. M. Chen, H. H. S. Lu, and K. C. Han, “A textural approach based on Gabor functions for texture edge detection in ultrasound images,” Ultrasound Med. Biol., 27(4): 515-534, 2007.
[56]W. W. Daniel, “Applied nonparametric statistics,” Boston, MA: Houghton Mifflin, 1978.
[57]T. F. Chan, and L. A. Vese, “Active contours without edges,” IEEE Trans Image Processing, 10(2): 266-277, 2001.
[58]R. F. Chang, W. J. Wu, W. K. Moon, and D. R. Chen, “Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors,” Breast Cancer Research and Treatment, 89: 179-185, 2005.
[59]K. S. Shreedhara and M. A. Kumar, “3D reconstruction of solid breast nodule in ultra sonographic image,” Proceedings of the International Conference on Cognition and Recognition, 759-767, 2005.
[60]F. Mao, J. Gill, D. Downey, and A. Aaron Fenstera, “Segmentation of carotid artery in ultrasound images: Method development and evaluation technique,” Medical Physics, 27(8): 1961-1970, 2000.