腕隧道症候群和板機指為常見的手部疾病，而超音波系統在軟組織的功能和臨床病理診斷上已有廣泛的應用。近年來的研究指出，正中神經的位移和變形在腕隧道症候群患者和健康成人之間有明顯的差異，而臨床上肌腱的位移則為診斷板機指患者的重要依據之一。此外研究也發現腕隧道症候群和板機指經常發生在同一位患者上。然而在超音波影像序列中，組織位移並不一定平行於超音波探頭，而且斑點雜訊和其他外在因素等影響使得手動追蹤和測量更加困難且主觀。
本篇研究提出了兩種不同的追蹤方法，分別針對超音波影像序列上橫切面的正中神經和縱切面的肌腱組織進行追蹤。在正中神經方面，本篇提出之演算法使用機器學習方法在第一幀上先定位出正中神經的位置，再利用光流法和主動輪廓模型進行正中神經輪廓的追蹤。而在肌腱組織上，提出的方法結合光流法和區塊匹配方法，先利用光流法提供大致的估計位移，再由區塊匹配方法在超音波影像序列中計算出最佳的肌腱位移。
兩種提出的追蹤方法皆利用專家的手動追蹤結果進行評估。在正中神經的追蹤方法上，提出的方法在輪廓上有平均約0.88的相似度和4.46像素的輪廓平均誤差，而整體位移上正中神經中心點的誤差約為3.52像素。另外在肌腱追蹤的部分，追蹤方法先利用假體超音波影像序列進行驗證並和其他傳統方法比較，實驗結果顯示提出方法得出的結果較接近手動圈選結果且較其他方法穩定。
未來此方法可應用在臨床診斷上，觀察病患和健康成人的組織面積變化與位移等參數，並藉由這些參數區分疾病的嚴重程度。

In clinical diagnosis, ultrasound is an important technique and has been widely used for many common hand diseases such as carpal tunnel syndrome (CTS) and trigger finger. Recent studies show that the displacement and deformation of the median nerve and the tendon between healthy subjects and patients have significant difference. Moreover, CTS may occur with trigger finger patients more often. However, some problems, such as speckle noise, out-of-plane, etc., make it hard to track and measure manually in the ultrasound images.
This study presents two novel tracking strategies for the median nerve and the tendon in transverse and longitudinal view, respectively. To track the contour of the median nerve in the traverse ultrasound image sequence, the proposed method adopts the machine learning method for localization; then optical flow and active contour model are used to track and refine the contour in the ultrasound image sequences. To track the motion of the tendon, the proposed method integrates optical flow and block matching method to calculate the optimal tendon motion between ultrasound image frames.
In median nerve tracking, the accuracy of the proposed method is about 0.88 in average Dice similarity coefficient, 4.46 pixels in average mean of absolute difference, and 3.52 pixel for average center difference. In tendon tracking, the proposed method is validated by the phantom ultrasound sequence and compared with some classical tracking methods. The experimental results reveal that the proposed method is better and more stable than the comparative methods in most cases.
In the future, the proposed methods can further be applied in patient data to obtain clinical parameters such as the area and velocity of the tissues. By comparing the parameters between patients and normal subjects, the indexes use to distinguish the symptomatic and asymptomatic can then be defined.

[1] A. Isam, G. Christina, J. Ragnar, E. Ornstein, J. Ranstam and I. Rosén, "Prevalence of carpal tunnel syndrome in a general population," Jama, vol. 282, no. 2, pp. 153-158, 1999.
[2] G. Ron, W. J. Preston, R. Ralph, B. Rollin, G. T. Y. and S. T. M., "Prevalence and incidence of stenosing flexor tenosynovitis (trigger finger) in a meat-packing plant," Journal of occupational and environmental medicine, vol. 40, no. 6, pp. 556-560, 1998.
[3] Y. Wang, C. Zhao, S. M. Passe, A. Filius, A. R. Thoreson, K.-n. An and P. C. Amadio, "Transverse ultrasound assessment of median nerve deformation and displacement in the human carpal tunnel during wrist movements," Ultrasound in medicine & biology, vol. 40, no. 1, pp. 53-61, 2014.
[4] S. A. Rottgers, D. Lewis and R. A. Wollstein, "Concomitant presentation of carpal tunnel syndrome and trigger," Journal of brachial plexus and peripheral nerve injury, vol. 4, no. 1, p. 13, 2009.
[5] C. Jablecki, M. Andary, M. Floeter, R. Miller, C. Quartly, M. Vennix and J. Wilson, "Practice parameter: electrodiagnostic studies in carpal tunnel syndrome report of the American Association of Electrodiagnostic Medicine, American Academy of Neurology, and the American Academy of Physical Medicine and Rehabilitation," Neurology, vol. 58, no. 11, pp. 1589-1592, 2002.
[6] E. R. Wiesler, G. D. Chloros, M. S. Cartwright, B. P. Smith, J. Rushing and F. O. Walker, "The Use of Diagnostic Ultrasound in Carpal Tunnel Syndrome," The Journal of hand surgery, vol. 31, no. 5, pp. 726-732, 2006.
[7] A. Arampatzis, S. Stafilidis, G. DeMonte, K. Karamanidis, G. Morey-Klapsing and G. Brüggemann, "Strain and elongation of the human gastrocnemius tendon and aponeurosis during maximal plantarflexion effort," Journal of biomechanics, vol. 38, no. 4, pp. 833-841, 2005.
[8] R. E. Kalman, "A New Approach to Linear Filtering and Prediction Problems," Journal of basic Engineering, vol. 82, no. 1, pp. 35-45, 1960.
[9] J. Guerrero, S. E. Salcudean, J. A. McEwen, B. A. Masri and S. Nicolaou, "Real-Time Vessel Segmentation and Tracking for Ultrasound Imaging Applications," IEEE transactions on medical imaging, vol. 26, no. 8, pp. 1079-1090, 2007.
[10] R. Li, B. Zeng and M. L. Liou, "A New Three-Step Search Algorithm for Block Motion Estimation," IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, vol. 4, no. 4, pp. 438-442, 8 1994.
[11] S. Golemati, A. Sassano, M. J. Lever, A. A. Bharath, S. Dhanjil and A. N. Nicolaides, "Carotid Artery Wall Motion Estimated from B-mode Ultrasound using Region Tracking and Block Matching," Ultrasound in medicine & biology, vol. 29, no. 3, pp. 387-399, 2003.
[12] B. Cohen and I. Dinstein, "New maximum likelihood motion estimation schemes for noisy ultrasound images," Pattern Recognition, vol. 35, no. 2, pp. 455-463, 2002.
[13] J. Barron, D. Fleet, S. Beauchemin and T. Burkitt, "Performance of Optical Flow Techniques," Computer Vision and Pattern Recognition, pp. 236-242, 1992.
[14] Q. Li, D. Ni, W. Yi, S. Chen, T. Wang and X. Chen, "Use of optical flow to estimate continuous changes in muscle thickness from ultrasound image sequences," Ultrasound in medicine & biology, vol. 39, no. 11, pp. 2194-2201, 2013.
[15] G. Zahnd, M. Orkisz, A. Sérusclat, P. Moulin and D. Vray, "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, vol. 17, no. 5, p. 573–585, 2013.
[16] J. H. Lee and S. M. Kim, "Estimating contrast agent motion from ultrasound images using an anisotropic diffusion-based optical flow technique," Computers in Biology and Medicine, vol. 43, no. 11, pp. 1853-1862, 2013.
[17] M. G. Danilouchkine, F. Mastik and A. F. W. v. d. Steen, "Improving IVUS Palpography by Incorporation of Motion Compensation Based on Block Matching and Optical Flow," IEEE transactions on ultrasonics, ferroelectrics, and frequency control, vol. 55, no. 11, pp. 2392-2404, 2008.
[18] D. Tenbrinck, S. Schmid, X. Jiang, K. Schäfers and J. Stypmann, "Histogram-based optical flow for motion estimation in ultrasound imaging," Journal of Mathematical Imaging and Vision, pp. 1-13, 2013.
[19] S. J. Pearson, T. Ritchings and A. S. Mohamed, "The Use of Normalized Cross-Correlation Analysis for Automatic Tendon Excursion Measurement in Dynamic Ultrasound Imaging," Journal of applied biomechanics, vol. 29, no. 2, pp. 165-173, 2013.
[20] J.-W. H.Korstanje, RuudW.Selles, HenkJ.Stam, StevenE.R.Hovius and JohanG.Bosch, "Development and validation of ultrasound speckle tracking to quantify tendon displacement," Journal of biomechanics, vol. 43, no. 7, pp. 1373-1379, 2010.
[21] K. J. STEGMAN, S. DJURICKOVIC and N. DECHEV, "IN VIVO ESTIMATION OF FLEXOR DIGITORUM SUPERFICIALIS TENDON DISPLACEMENT WITH SPECKLE TRACKING ON 2-D ULTRASOUND IMAGES USING LAPLACIAN, GAUSSIAN AND RAYLEIGH TECHNIQUES," Ultrasound in medicine & biology, vol. 40, no. 3, p. 568–582, 2014.
[22] S. S. Lee, G. S. Lewis and S. J. Piazza, "An Algorithm for Automated Analysis of Ultrasound Images to Measure Tendon Excursion in Vivo," Journal of applied biomechanics, vol. 24, no. 1, pp. 75-82, 2008.
[23] K. Karamanidis, A. Travlou, P. Krauss and U. Jaekel, "Use of a Lucas–Kanade-Based template tracking algorithm to examine in vivo tendon excursion during voluntary contraction using ultrasonography," Ultrasound in medicine & biology, vol. 42, no. 7, pp. 1689-1700, 2016.
[24] B. Chuang, J. Hsu, L. Kuo, I. Jou, F. Su and Y. Sun, "Tendon motion tracking in an ultrasound image sequence using optical flow based block matching," Biomedical engineering online, vol. 16, no. 1, p. 47, 2017.
[25] Y.-H. Lin, M.-Y. Hsieh, F.-C. Su and S.-H. Wang, "Assessment of the Kinetic Trajectory of the Median Nerve in the Wrist by High-Frequency Ultrasound," Sensors, vol. 14, no. 5, pp. 7738-7752, 2014.
[26] T.-T. Kuo, M.-R. Lee, Y.-Y. Liao, J.-P. Chen, Y.-W. Hsu and C.-K. Yeh, "Assessment of Median Nerve Mobility by Ultrasound Dynamic Imaging for Diagnosing Carpal Tunnel Syndrome," PloS one, vol. 11, no. 1, p. e0147051, 2016.
[27] T. F. Chan and L. A. Vese, "Active Contours Without Edges," IEEE Transactions on image processing, vol. 10, no. 2, pp. 266-277, 2001.
[28] M. Kass, A. Witkin and D. Terzopoulos, "Snakes: Active Contour Models," International journal of computer vision, vol. 1, no. 4, pp. 321-331, 1988.
[29] M. Qian, L. Niu, Y. Xiao, C. Wang, W. Qiu and H. Zheng, "Ultrasound Contrast Image Segmentation Using a Modified Level Set Method," Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, pp. 5127-5130, 2013.
[30] D.-R. Chen, R.-F. Chang, W.-J. Wu, W. K. Moon and W.-L. Wu, "3-D breast ultrasound segmentation using active contour model," Ultrasound in medicine & biology, vol. 29, no. 7, pp. 1017-1026, 2003.
[31] A. Rodtook and S. S. Makhanov, "Multi-feature gradient vector flow snakes for adaptive segmentation of the ultrasound images of breast cancer," Journal of Visual Communication and Image Representation, vol. 24, no. 8, pp. 1414-1430, 2013.
[32] A. Hafiane, P. Vieyres and A. Delbos, "Phase-based probabilistic active contour for nerve detection in ultrasound images for regional anesthesia," Computers in Biology and Medicine, vol. 52, pp. 88-95, 2014.
[33] Y.-W. Wang, C.-J. Chen, S.-F. Huang and Y.-S. Horng, "Segmentation of Median Nerve by Greedy Active Contour Detection Framework on Strain Ultrasound Images," J. Inf. Hiding Multimedia Signal Process, vol. 6, no. 2, pp. 371-378, 2015.
[34] O. Hadjerci, A. Hafiane, D. Conte, P. Makris, P. Vieyres and A. Delbos, "Computer-aided detection system for nerve identification using ultrasound images: a comparative study," Informatics in Medicine Unlocked, vol. 3, pp. 29-43, 2016.
[35] "Siemens Healthineers Global," Siemens, [Online]. Available: https://www.healthcare.siemens.com/.
[36] Y. Yu and S. T. Acton, "Speckle reducing anisotropic diffusion," IEEE Transactions on image processing, vol. 11, no. 11, pp. 1260-1270, 2002.
[37] Y. Yu and S. T. Acton, "Edge detection in ultrasound imagery using the instantaneous coefficient of variation," IEEE Transactions on Image Processing, vol. 13, no. 12, pp. 1640-1655, 2004.
[38] J. E. Goetz, D. R. Thedens, N. M. Kunze, E. A. Lawler and T. D. Brown, "Day-to-day variability of median nerve location within the carpal tunnel," Clinical Biomechanics, vol. 25, no. 7, pp. 660-665, 2010.
[39] C. Cortes and V. Vapnik, "Support-Vector Networks," Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
[40] M. Felsberg and G. Sommer, "The Monogenic Signal," IEEE Transactions on Signal Processing, vol. 49, no. 12, pp. 3136-3144, 2001.
[41] P. Kovesi, "Symmetry and asymmetry from local phase," Tenth Australian joint conference on artificial intelligence, vol. 190, pp. 2-4, 1997.
[42] B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," pp. 674-679, 1981.
[43] E. H. Adelson, C. H. Anderson, J. R. Bergen, P. J. Burt and J. M. Ogden, "Pyramid methods in image processing," RCA engineer, vol. 29, no. 6, pp. 33-41, 1984.
[44] J.-H. Hsu, "Tendon Motion Tracking Based on Global Motion Trend for Ultrasound Image Sequence (Master's thesis)," 2015.
[45] J.-Y. Bouguet, "Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm," Intel Corporation, vol. 5, no. 1-10, p. 4, 2001.
[46] D. C. Hoaglin, "John W. Tukey and data analysis," Statistical Science, pp. 311-318, 2003.