進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0109201713390500
論文名稱(中文) 應用於肌腱醫學影像的分割、追蹤與評估
論文名稱(英文) Segmentation, Tracking, and Evaluation in Tendon Medical Images
校院名稱 成功大學
系所名稱(中) 資訊工程學系
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 105
學期 2
出版年 106
研究生(中文) 莊柏逸
研究生(英文) Bo-I Chuang
學號 P78971359
學位類別 博士
語文別 英文
論文頁數 93頁
口試委員 指導教授-孫永年
口試委員-洪昌鈺
口試委員-江清芬
口試委員-莊仁輝
口試委員-楊岱樺
口試委員-王士豪
口試委員-王明習
口試委員-李同益
中文關鍵字 肌腱  超音波影像  顯微影像  分割  追蹤  主動形狀模型  光流向演算法  區塊匹配法 
英文關鍵字 Tendon  Ultrasound  Microscopy  Segmentation  Tracking  Active Shape Model  Optical Flow  Block Matching 
學科別分類
中文摘要 近年來,肌腱病變成為常見的臨床議題。超音波影像及H&E染色顯微影像常用來診斷肌腱病變的嚴重程度。然而由於超音波成像的斑點雜訊,使得傳統的影像處理方法無法穩定的分割及追蹤超音波影像中的肌腱。此外,肌腱運動過程的出平面問題,使得肌腱追蹤更為困難。而在顯微影像部份,在大多數研究中皆透過人工判定來評估肌腱病變嚴重程度,對於客觀的量化分析較為缺乏。
針對上述問題,在本論文中,我們分別在超音波及顯微影像中,提出了三個分割及追蹤的方法。在橫切超音波影像中,我們提出了用以分割肌腱及滑液腔內壁的ATASM。我們設計了適應性權重方法針對ASM能量函式中各能量項在不同位置的重要性給予不同權重值。並對ATASM分割出的區域以小波轉換及共生紋理特徵區分正常與病變影像。在縱切超音波影像中,我們提出了結合光流法及區塊匹配法的OFTB-MKBM。在此方法中,我們對每個相鄰時間點的影像以光流法計算並累計肌腱移動量。再利用累計的移動量選擇合適時間間隔,以多區塊匹配法計算更正確的移動量,最後透過光流法的結果內插時間間隔內的運動量。而在顯微影像中,我們分別對巨觀及微觀影像設計自動化分割方法。在微觀顯微影像中,我們先使用以抽樣為主的閥值法分割細胞核,再依分割出的細胞核數量決定是否要用Laplacian閥值法進一步修正分割結果。在巨觀影像中,我們首先以顏色資訊將血管及鈣化區域分割出,再使用顏色飽和度資訊區分正常與不正常組織。最後再比較微觀與巨觀影像的結果,探討兩者的相關性。在實驗部份,相較於傳統主動輪廓模型(active contour model)及主動形狀模型(active shape model)的結果,我們的ATASM分割出的輪廓與專家圈選的更為接近。並且在42組病人與正常人的影像中,我們的方法能區分出其肌腱病變與否。在OFTB-MKBM方法中,我們使用大體進行驗證,絕對平均誤差在0.05公釐以內。我們也將OFTB-MKBM方法用於假體及病人影像中,並與光流向演算法(optical flow)及多核心區塊匹配法(multi-kernel block matching)比較,並得到更準確的追蹤結果。在顯微影像部份,我們使用專家判斷的結果驗證微觀影像分割方法,並得到90.85%的敏感度性,優於使用最大亂度閥值法(maximum entropy thresholding)及水平集分割法(level set)的分割結果。我們也驗證微觀與巨觀影像的分割結果,從實驗結果顯示兩分割結果有很好的相關性。
英文摘要 Tendinopathy is a common clinical issue in recent years. Ultrasound and H&E stained tendon microscopy images are commonly used for the clinical diagnosis of tendinopathy severity. Due to property variations of ultrasound images, traditional methods cannot effectively segment the finger joint’s tendon structure. Moreover, speckle noise and out-of-plane issues make the tendon tracking process difficult. In microscopy, as most of the reported tendon tissue evaluations are manual, objective quantitative analyses remain scant.
In this thesis, we developed three tracking and segmentation methods for ultrasound and microscopy images. In axial view ultrasound images, an adaptive texture-based active shape model (ATASM) method is proposed for segmenting the tendon and synovial sheath. Adapted weights are applied in the segmentation process to adjust the contribution of energy terms depending on image characteristics at different positions. The pathology is then determined according to the wavelet and co-occurrence texture features of the segmented tendon area., In order to automatically track the tendon motion, we developed a new method called optical-flow-trend-based multi-kernel block matching (OFTB-MKBM) that combines the advantages of optical flow and multi-kernel block matching in the sagittal view ultrasound images. For every pair of adjacent image frames, the optical flow is computed and used to estimate the accumulated displacement. The proposed method selects the frame interval adaptively based on this displacement. Multi-kernel block matching is then computed on the two selected frames. To reduce the tracking errors, the detailed displacements of the frames in between are interpolated based on the optical flow results. In microscopy, we develop two automatic systems for tendon nuclei segmentation from micro- and macro-view images. In micro-view microscopy, the proposed sampling-based thresholding segments the nuclei by feature sampling from a small number of selected nuclei. For complex images with more nuclei, the Laplacian-based thresholding is proposed to segment the nuclei based on the nuclei boundary information. The system selects the thresholding result depending on the number of segmented nuclei. The segmented nuclei are then classified as normal or abnormal based on their characteristics. In macro-view microscopy, we first segment the vessel and calcified regions according to the color information. The remaining regions are then classified into normal or abnormal tissues based on their saturation values. In the experiments, the results of proposed ATASM had fewer errors, with respect to the ground truth, than the traditional active contour model (ACM) and active shape model (ASM). The segmentation results were all acceptable in data of both clear and fuzzy boundary cases in 74 images. And the symptom classifications of 42 cases were also a good reference for diagnosis according to the expert clinicians’ opinions. The mean absolute error of OFTB-MKBM evaluated by using cadaver data was less than 0.05 mm. The proposed OFTB-MKBM also tracked the motion of phantom and tendons in vivo, and achieved the better tracking results than optical flow and multi-kernel block matching. The average sensitivity of micro-view segmentation method in the microscopy achieved 90.85% with respect to expert judgments. The results are better than the ones using maximum entropy threshold and level set segmentation structure. The experiment also showed that the proposed micro- and macro-view classifications have good correlation with each other.
論文目次 CHAPTER 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Outlines 9
CHAPTER 2 Tendon Segmentation in Ultrasound Images 11
2.1 ATASM Overview 11
2.2 Shape Model Construction 13
2.3 Texture Profile Construction 13
2.4 Energy Function Setup 15
2.5 Weight of Energy Term Computation 16
2.6 Shape Model Locating 17
2.7 GA-Based Energy Optimization 17
2.8 ATASM for Tendon Segmentation 18
2.9 ATASM for Synovial Sheath Segmentation 21
2.10 Synovial Sheath Segmentation Post-processing 22
CHAPTER 3 TENDON TRACKING IN ULTRASOUND IMAGES 23
3.1 Optical flow method 23
3.2 Multi-kernel block matching 24
3.3 Optical-flow-trend-based multi-kernel block matching 24
CHAPTER 4 TENDON CLASSIFICATION IN MICROSCOPY 31
4.1 Micro-view Segmentation & Classification 31
4.2 Macro-view segmentation 36
4.3 Correspondence between micro- and macro-view images 38
CHAPTER 5 EXPERIMENT RESULTS AND DISCUSSION 41
5.1 Results of axial view ultrasound segmentation 41
5.2 Results of sagittal view ultrasound tracking 54
5.3 Results of micro- and macro-view microscopy image 70
CHAPTER 6 CONCLUSION 81
REFERENCE 84
參考文獻 [1]. Ryzewicz M, Wolf JM. Trigger digits: principles, management, and complications. J Hand Surg Am. 2006;31(1):135-146.
[2]. Lorthioir J. Surgical treatment of trigger-finger by a subcutaneous method. J Bone Joint Surg Am. 1958;40-A(4):793-5.
[3]. Jou IM, Chern TC. Sonographically assisted percutaneous release of the a1 pulley: a new surgical technique for treating trigger digit. The Journal of Hand Surgery: British & European Volume 31.2 (2006): 191-199.
[4]. Klauser AS, Faschingbauer R, Jaschke WR. Is sonoelastography of value in assessing tendons? Seminars in musculoskeletal radiology. Vol. 14. No. 03. © Thieme Medical Publishers, 2010.
[5]. Sahu Ramji Lal, Gupta P. Experience of percutaneous trigger finger release under local anesthesia in the Medical College of Mullana, Ambala, Haryana. Annals of medical and health sciences research 4.5 (2014): 806-809.
[6]. Gabor, Dennis. "Theory of communication. Part 1: The analysis of information." Electrical Engineers-Part III: Radio and Communication Engineering, Journal of the Institution of 93.26 (1946): 429-441.
[7]. Hamameh G, Gustavsson T. Combining snakes and active shape models for segmenting the human left ventricle in echocardiographic images. In: Computers in Cardiology 2000. IEEE; 2000:115-118.
[8]. He P, Zheng J. Segmentation of tibia bone in ultrasound images using active shape models. In: 2001 Proceedings of the 23rd Annual EMBS International Conference. Vol 3. IEEE; 2001:2712-2715.
[9]. Shen D, Zhan Y, Davatzikos C. Segmentation of Prostate Boundaries From Ultrasound Images Using Statistical Shape Model. IEEE Trans Med Imaging. 2003;22(4):539-551.
[10]. Medina R, Bravo A, Windyga P, Toro J, Yan P, Onik G. A 2-d active appearance model for prostate segmentation in ultrasound images. In: Engineering in Medicine and Biology 27th Annual Conference. Vol 4. ; 2005:3363-3366.
[11]. Cosío FA. Automatic initialization of an active shape model of the prostate. Med Image Anal. 2008;12:469-483.
[12]. Tsai PY, Chen HC, Huang HH, et al. A new automatic algorithm to extract craniofacial measurements from fetal three-dimensional volumes. Ultrasound Obstet Gynecol. 2012;39(6):642-647.
[13]. Chen HC, Tsai PY, Huang HH, et al. Registration-based segmentation from three-dimensional ultrasound image for quantitative measurement of fetal craniofacial structure. Ultrasound Med Biol. 2012;38(5):811-823.
[14]. Santhiyakumari, N., et al. "Detection of the intima and media layer thickness of ultrasound common carotid artery image using efficient active contour segmentation technique." Medical & biological engineering & computing 49.11 (2011): 1299-1310.
[15]. Gong, Xue-Hao, et al. "Segmentation of Uterus Using Laparoscopic Ultrasound by an Image-Based Active Contour Approach for Guiding Gynecological Diagnosis and Surgery." PloS one 10.10 (2015): e0141046.
[16]. Liao, Xiangyun, et al. "Multi-scale and shape constrained localized region-based active contour segmentation of uterine fibroid ultrasound images in HIFU therapy." PloS one 9.7 (2014): e103334.
[17]. Kim ND, Booth L, Amin V, Lim J, Udpa S. Ultrasonic image processing for tendon injury evaluation. In: Time-Frequency and Time-Scale Analysis, 1998. Proceedings of the IEEE-SP International Symposium on. IEEE; 1998:241-244.
[18]. Huang Q, Dony RD. Neural network texture segmentation in equine leg ultrasound images. In: Electrical and Computer Engineering, 2004. Canadian Conference on. Vol 3. IEEE; 2004:1269-1272.
[19]. Christodoulou CI, Pattichis CS, Pantziaris M, Nicolaides A. Texture-Based Classification of Atherosclerotic Carotid Plaques. IEEE Trans Med Imaging. 2003;22(7):902-912.
[20]. Huang YL, Wang KL, Chen DR. Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines. Neural Comput Appl. 2006;15:164-169.
[21]. Zhu C, Gu GC, Liu HB, Shen J, Yu H. Segmentation of Ultrasound Image Based on Texture Feature and Graph Cut. In: Computer Science and Software Engineering, 2008 International Conference on. IEEE; 2008:795-798.
[22]. Iakovidis DK, Keramidas EG, Maroulis D. Fusion of fuzzy statistical distributions for classification of thyroid ultrasound patterns. Artif Intell Med. 2010;50(1):33-41.
[23]. Padmanabhan, K., D. Nedumaran, and S. Ananthi. "Gabor spectra for Doppler echocardiography." Medical and Biological Engineering and Computing 36.3 (1998): 270-275.
[24]. Puri, M., et al. "Texture analysis of foot sole soft tissue images in diabetic neuropathy using wavelet transform." Medical and Biological Engineering and Computing 43.6 (2005): 756-763.
[25]. Zahnd G, et al. Evaluation of a Kalman-based block matching method to assess the bi-dimensional motion of the carotid artery wall in B-mode ultrasound sequences. Medical image analysis 17.5 (2013): 573-585.
[26]. Lai TY, et al. Application of a novel Kalman filter based block matching method to ultrasound images for hand tendon displacement estimation. Medical physics 43.1 (2016): 148-158.
[27]. Ayvali E, Desai JP. Optical Flow-Based Tracking of Needles and Needle-Tip Localization Using Circular Hough Transform in Ultrasound Images. Annals of biomedical engineering 43.8 (2015): 1828-1840.
[28]. Tenbrinck D, et al. Histogram-based optical flow for motion estimation in ultrasound imaging. Journal of mathematical imaging and vision 47.1-2 (2013): 138-150.
[29]. Barbosa D, et al. Fast tracking of the left ventricle using global anatomical affine optical flow and local recursive block matching. Proceedings of the MICCAI Challenge on Endocardial Three-dimensional Ultrasound Segmentation-CETUS (2014): 17-24.
[30]. Korstanje JWH, et al. Development and validation of ultrasound speckle tracking to quantify tendon displacement. Journal of biomechanics 43.7 (2010): 1373-1379.
[31]. Matsuzawa R, et al. Monitoring of lesion induced by high-intensity focused ultrasound using correlation method based on block matching. Japanese Journal of Applied Physics 51.7S (2012): 07GF26.
[32]. Siddig AMA, Yousif RK, Alanwer M. Motion estimation in ultrasound image using dynamic multi-shape search. Computing, Electrical and Electronics Engineering (ICCEEE), 2013 International Conference on. IEEE, 2013.
[33]. Li J, et al. Estimation and visualization of longitudinal muscle motion using ultrasonography: a feasibility study. Ultrasonics 54.3 (2014): 779-788.
[34]. Karamanidis K, et al. Use of a Lucas–Kanade-Based Template Tracking Algorithm to Examine In Vivo Tendon Excursion during Voluntary Contraction Using Ultrasonography. Ultrasound in medicine & biology 42.7 (2016): 1689-1700.
[35]. Alvarez L, Weickert J, Sánchez J. Reliable estimation of dense optical flow fields with large displacements. International Journal of Computer Vision 39.1 (2000): 41-56.
[36]. Dilley A, et al. The use of cross-correlation analysis between high-frequency ultrasound images to measure longitudinal median nerve movement. Ultrasound in medicine & biology 27.9 (2001): 1211-1218.
[37]. T. Movin, A. Gad, F.P. Reinholt and C. Rolf, "Tendon pathology in long-standing achillodynia. Biopsy findings in 40 patients," Acta Orthopaedica Scandinavica, 68(2), 170–175. (1997)
[38]. Cook, J. L., et al. "Abnormal tenocyte morphology is more prevalent than collagen disruption in asymptomatic athletes' patellar tendons." Journal of orthopaedic research 22.2 (2004): 334-338.
[39]. Ali, Rehan, et al. "Automatic segmentation of adherent biological cell boundaries and nuclei from brightfield microscopy images." Machine Vision and Applications 23.4 (2012): 607-621.
[40]. Keuper, Margret, et al. "Hierarchical Markov random fields for mast cell segmentation in electron microscopic recordings." Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on. IEEE, 2011.
[41]. Díaz, Gloria, and Eduardo Romero. "Micro‐structural tissue analysis for automatic histopathological image annotation." Microscopy research and technique 75.3 (2012): 343-358.
[42]. Husham, Ahmed, et al. "Automated nuclei segmentation of malignant using level sets." Microscopy Research and Technique 79.10 (2016): 993-997.
[43]. Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66. doi:10.1109/TSMC.1979.4310076
[44]. Dos Anjos, A., & Shahbazkia, H. R. (2008). BI-level image thresholding - A fast method. In BIOSIGNALS 2008 - Proceedings of the 1st International Conference on Bio-inspired Systems and Signal Processing (Vol. 2, pp. 70–76).
[45]. Cuevas, E., Zaldivar, D., & P??rez-Cisneros, M. (2010). A novel multi-threshold segmentation approach based on differential evolution optimization. Expert Systems with Applications, 37(7), 5265–5271. doi:10.1016/j.eswa.2010.01.013
[46]. Pun, T. (1980). A new method for grey-level picture thresholding using the entropy of the histogram. Signal Processing, 2(3), 223–237. doi:10.1016/0165-1684(80)90020-1
[47]. Chang, C. I., Chen, K., Wang, J., & Althouse, M. L. G. (1994). A relative entropy-based approach to image thresholding. Pattern Recognition, 27(9), 1275–1289. doi:10.1016/0031-3203(94)90011-6
[48]. Liang, Y. C., & Cuevas J., J. R. (2012). Multilevel image thresholding using relative entropy and virus optimization algorithm. In 2012 IEEE Congress on Evolutionary Computation, CEC 2012. doi:10.1109/CEC.2012.6256435
[49]. M. Veta, P.J. van Diest, R. Kornegoor, A. Huisman, M.A. Viergever and J.P.W. Pluim, "Automatic Nuclei Segmentation in H&E Stained Breast Cancer Histopathology Images," PLoS ONE, 8(7). (2013)
[50]. S. Wienert, D. Heim, K. Saeger, A. Stenzinger, M. Beil, P. Hufnagl, … and F. Klauschen, "Detection and Segmentation of Cell Nuclei in Virtual Microscopy Images: A Minimum-Model Approach," Scientific Reports 2. (2012)
[51]. S. Naik, S. Doyle, M. Feldman, J. Tomaszewski and A. Madabhushi, "Gland Segmentation and Computerized Gleason Grading of Prostate Histology by Integrating Low- , High-level and Domain Specific Information," In Proceedings of 2nd Workshop on Microscopic Image Analysis with Applications in Biology (pp. 1–8). (2007)
[52]. Kendall, David G. "A survey of the statistical theory of shape." Statistical Science (1989): 87-99.
[53]. Wold S, Esbensen K, Geladi P. Principal component analysis. Chemom Intell Lab Syst. 1987;2:37-52. doi:10.1016/0169-7439(87)80084-9.
[54]. Goldberg DE. Genetic Algorithms in Seach, Optimization, and Machine Learning.; 1989.
[55]. Laws, Kenneth I. Textured image segmentation. No. USCIPI-940. University of Southern California Los Angeles Image Processing INST, 1980.
[56]. Gibson JJ. The perception of the visual world. (1950).
[57]. Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. IJCAI. Vol. 81. No. 1. 1981.
[58]. Xing, Fuyong, and Lin Yang. "Robust nucleus/cell detection and segmentation in digital pathology and microscopy images: a comprehensive review." IEEE reviews in biomedical engineering 9 (2016): 234-263.
[59]. Amin, Morteza Moradi, et al. "Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier." Journal of medical signals and sensors 5.1 (2015): 49.
[60]. Wienert, Stephan, et al. "Detection and segmentation of cell nuclei in virtual microscopy images: a minimum-model approach." Scientific reports 2 (2012): srep00503.
[61]. Chen, Xiaowei, Xiaobo Zhou, and Stephen TC Wong. "Automated segmentation, classification, and tracking of cancer cell nuclei in time-lapse microscopy." IEEE Transactions on Biomedical Engineering 53.4 (2006): 762-766.
[62]. Mallat, Stephane G. "A theory for multiresolution signal decomposition: the wavelet representation." IEEE transactions on pattern analysis and machine intelligence 11.7 (1989): 674-693.
[63]. Haralick RM, Shanmugam K, Dinstein I. Textural Features for Image Classification. IEEE Trans Syst Man Cybern. 1973;SMC-3:610-621.
[64]. Tsiaparas NN, Golemati S, Andreadis I, Stoitsis JS, Valavanis I, Nikita KS. Comparison of Multiresolution Features for Texture Classification of Carotid Atherosclerosis From B-Mode Ultrasound. IEEE Trans Inf Technol Biomed. 2011;15(1):130-137.
[65]. Chang CC, Lin CJ. LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol. 2011;2(27).
[66]. Fan, Rong-En, Pai-Hsuen Chen, and Chih-Jen Lin. "Working set selection using second order information for training support vector machines." Journal of machine learning research 6.Dec (2005): 1889-1918.
[67]. Guerini H, Pessis E, Theumann N, et al. Sonographic appearance of trigger fingers. J Ultrasound Med. 2008;27(10):1407-1413.
[68]. Miyamoto H, Miura T, Isayama H, Masuzaki R, Koike K, Ohe T. Stiffness of the first annular pulley in normal and trigger fingers. J Hand Surg Am. 2011;36(9):1486-1491.
[69]. Sato J, Ishii Y, Noguchi H, Takeda M. Sonographic appearance of the flexor tendon, volar plate, and A1 pulley with respect to the severity of trigger finger. J Hand Surg Am. 2012;31(1):2012-2020.
[70]. Kapur, Jagat Narain, Prasanna K. Sahoo, and Andrew KC Wong. "A new method for gray-level picture thresholding using the entropy of the histogram." Computer vision, graphics, and image processing 29.3 (1985): 273-285.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2022-09-05起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2022-09-05起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw