臺灣博碩士論文加值系統

膝蓋退化性關節炎是年長者中最常見的關節炎疾病，會造成膝蓋疼痛、腫脹以及大大的降低病人的活動範圍。臨床診斷上，膝蓋軟骨的變異時常是退化性關節炎的主要因素。目前雖然X光是最常用來診斷退化性關節炎的工具，但其中也存在了許多限制以及X光診斷無法獲得足夠有關於膝軟骨的資訊。但是超音波卻可以輕易地對膝軟骨的厚度做量化計算，並透過評估軟骨附近的軟組織來判斷是否有發炎狀態，發炎可以視為是膝蓋退化性關節炎的前期徵兆。因此，這篇論文提出了一套應用於骨骼肌肉超音波並可自動偵測膝關節軟骨厚度的電腦輔助量化評估系統，此系統包含了對膝軟骨區域的全自動切割、更完善地找出膝軟骨上下邊界的處理，以及在膝軟骨區域的上下邊界間做精準的厚度量測，以協助骨科醫師評估病患膝軟骨的完善程度以及膝蓋退化性關節炎的嚴重程度。在量化評估系統的精確度及可靠度驗證中，共使用了67張影像進行測試與驗證，分別來自11個男性及6個女性病患。測試方法通過驗證比較系統自動產出的量化結果及骨科醫師所量測的正確結果，得知系統在厚度上的量測可達到83.69%的準確率，在量測點上的定位僅有0.842mm的誤差。因此，根據實驗結果，此系統對骨骼肌肉超音波之膝關節軟骨提供了可靠及穩定的軟骨厚度量測結果，並可如預期地克服了一些X光及超音波先天上的限制。

Knee osteoarthritis is the most common type of arthritis in the elderly, which causes knee pain, swelling, joint movement restriction to patients. Cartilage abnormalities are primary features of osteoarthritis. Although X-ray is the most common radiological examination for diagnosis of knee osteoarthritis, the radiographic diagnosis has limitations and few information of cartilage condition. Musculoskeletal ultrasound (US) is a useful technique to quantify the cartilage thickness and detect inflammation in the knee joint by evaluating the cartilage periarticular soft tissue, and inflammation was considered contribute to the progression of knee osteoarthritis. In this study, we proposed an automatic computer-aided quantitative assessment system for thickness measurement of knee cartilage in the US image. In the proposed system, cartilage area segmentation was presented to extract the cartilage area, and the boundary delineation was used to automatically detect and refine the upper and lower boundaries of knee cartilage. Then, thickness measurement was performed to measure the distance between the upper and lower boundaries of the cartilage area. In the experiment, the proposed assessment system was tested with a dataset of 67 cases, and the overall accuracy of thickness measurement achieved 83.69%. Also, the target position located by the proposed system had the overall mean difference of 0.842 mm by comparing to the ground truth measured by orthopedist. In conclusion, based on the experiment result, our system has ability to provide a confident and reliable thickness measurement of knee cartilage in musculoskeletal US, and to overcome the limitations of X-ray and ultrasound.

口試委員會審定書 i
致謝 ii
摘要 iv
Abstract v
Table of Contents vi
List of Figures viii
List of Tables x
Chapter 1 Introduction 1
Chapter 2 Materials 3
2.1 Data Acquisition 3
2.2 Ultrasonographic Knee Cartilage Measurement 4
Chapter 3 Computer-aided Quantitative Assessment System 7
3.1 Cartilage Area Segmentation 9
3.1.1 Anisotropic Diffusion Filter 9
3.1.2 Sigmoid Filter Operation 11
3.1.3 Markov Random Field Segmentation 12
3.2 Boundary Delineation 17
3.2.1 Fragment Removal 17
3.2.2 Merging Number Determination 19
3.2.3 Spline Interpolation 24
3.3 Thickness Measurement 30
Chapter 4 Results and Discussion 33
4.1 Experiment environment 33
4.2 Quality of cartilage area identification 34
4.3 Quantitative Assessment 37
4.3.1 Accuracy of Thickness Measurement 38
4.3.2 Accuracy of the Target Position Locating 45
4.4 Discussion 47
4.4.1 False Case on Thickness Measurement 47
4.4.2 False Case on Target Position Locating 51
Chapter 5 Conclusion and Future Works 53
References 55

[1]B. Heidari, "Knee osteoarthritis prevalence, risk factors, pathogenesis and features: Part I," Caspian journal of internal medicine, vol. 2, p. 205, Feb. 2011.
[2]M.-J. Berthiaume, J.-P. Raynauld, J. Martel-Pelletier, F. Labonté, G. Beaudoin, D. A. Bloch, et al., "Meniscal tear and extrusion are strongly associated with progression of symptomatic knee osteoarthritis as assessed by quantitative magnetic resonance imaging," Annals of the rheumatic diseases, vol. 64, pp. 556-563, Sep. 2004.
[3]T. Miyazaki, M. Wada, H. Kawahara, M. Sato, H. Baba, and S. Shimada, "Dynamic load at baseline can predict radiographic disease progression in medial compartment knee osteoarthritis," Annals of the rheumatic diseases, vol. 61, pp. 617-622, Jul. 2002.
[4]J. Kellgren and J. Lawrence, "Radiological assessment of osteo-arthrosis," Annals of the rheumatic diseases, vol. 16, p. 494, Dec. 1957.
[5]M. Mahesh, "Fluoroscopy: Patient Radiation Exposure Issues 1," Radiographics, vol. 21, pp. 1033-1045, Jul. 2001.
[6]J. H. Woodring and C. Lee, "Limitations of cervical radiography in the evaluation of acute cervical trauma," Journal of Trauma and Acute Care Surgery, vol. 34, pp. 32-39, Jan. 1993.
[7]J. K. Kazam, L. N. Nazarian, T. T. Miller, C. M. Sofka, L. Parker, and R. S. Adler, "Sonographic Evaluation of Femoral Trochlear Cartilage in Patients With Knee Pain," Journal of Ultrasound in Medicine, vol. 30, pp. 797-802, Jun. 2011.
[8]X. Ayral, E. Pickering, T. Woodworth, N. Mackillop, and M. Dougados, "Synovitis: a potential predictive factor of structural progression of medial tibiofemoral knee osteoarthritis–results of a 1 year longitudinal arthroscopic study in 422 patients," Osteoarthritis and Cartilage, vol. 13, pp. 361-367, May 2005.
[9]T. Spector, D. Hart, D. Nandra, D. Doyle, N. Mackillop, J. Gallimore, et al., "Low‐level increases in serum C‐reactive protein are present in early osteoarthritis of the knee and predict progressive disease," Arthritis & Rheumatism, vol. 40, pp. 723-727, Apr. 1997.
[10]J. Ledingham, M. Regan, A. Jones, and M. Doherty, "Factors affecting radiographic progression of knee osteoarthritis," Annals of the rheumatic diseases, vol. 54, pp. 53-58, Jan. 1995.
[11]S. Tarhan and Z. Unlu, "Magnetic resonance imaging and ultrasonographic evaluation of the patients with knee osteoarthritis: a comparative study," Clinical rheumatology, vol. 22, pp. 181-188, Sep. 2003.
[12]L. Friedman, K. Finlay, and E. Jurriaans, "Ultrasound of the knee," Skeletal radiology, vol. 30, pp. 361-377, Jul. 2001.
[13]M. J. Lee and K. Chow, "Ultrasound of the knee," in Seminars in musculoskeletal radiology, pp. 137-148, Jun. 2007.
[14]C.-L. Lee, M.-H. Huang, C.-Y. Chai, C.-H. Chen, J.-Y. Su, and Y.-C. Tien, "The validity of in vivo ultrasonographic grading of osteoarthritic femoral condylar cartilage: a comparison with in vitro ultrasonographic and histologic gradings," Osteoarthritis and Cartilage, vol. 16, pp. 352-358, Mar. 2008.
[15]I. Möller, D. Bong, E. Naredo, E. Filippucci, I. Carrasco, C. Moragues, et al., "Ultrasound in the study and monitoring of osteoarthritis," Osteoarthritis and Cartilage, vol. 16, pp. S4-S7, Aug. 2008.
[16]C.-H. Yoon, H.-S. Kim, J. H. Ju, W.-H. Jee, S.-H. Park, and H.-Y. Kim, "Validity of the sonographic longitudinal sagittal image for assessment of the cartilage thickness in the knee osteoarthritis," Clinical rheumatology, vol. 27, pp. 1507-1516, Dec. 2008.
[17]A. Castriota-Scanderbeg, V. De Micheli, M. Scarale, M. Bonetti, and M. Cammisa, "Precision of sonographic measurement of articular cartilage: inter-and intraobserver analysis," Skeletal radiology, vol. 25, pp. 545-549, Aug. 1996.
[18]O. Mathiesen, L. Konradsen, S. Torp-Pedersen, and U. J?rgensen, "Ultrasonography and articular cartilage defects in the knee: an in vitro evaluation of the accuracy of cartilage thickness and defect size assessment," Knee Surgery, Sports Traumatology, Arthroscopy, vol. 12, pp. 440-443, Sep. 2004.
[19]A. C. Gellhorn and M. J. Carlson, "Inter-rater, intra-rater, and inter-machine reliability of quantitative ultrasound measurements of the patellar tendon," Ultrasound in medicine & biology, vol. 39, pp. 791-796, May 2013.
[20]K. Z. Abd-Elmoniem, A. B. M. Youssef, and Y. M. Kadah, "Real-time speckle reduction and coherence enhancement in ultrasound imaging via nonlinear anisotropic diffusion," IEEE Trans.Biomedical Engineering, vol. 49, pp. 997-1014, Sep. 2002.
[21]J. S. Suri, Advances in diagnostic and therapeutic ultrasound imaging: Artech House, Jul. 2008.
[22]K. Held, E. R. Kops, B. J. Krause, W. M. Wells, R. Kikinis, and H.-W. Muller-Gartner, "Markov random field segmentation of brain MR images," IEEE transactions on medical imaging, vol. 16, pp. 878-886, Dec. 1997.
[23]R.-F. Chang, W.-J. Wu, W. K. Moon, and D.-R. Chen, "Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis," Ultrasound in Medicine & Biology, vol. 29, pp. 679-686, May 2003.
[24]G. Farnebäck and C.-F. Westin, "Improving Deriche-style recursive Gaussian filters," Journal of Mathematical Imaging and Vision, vol. 26, pp. 293-299, Nov. 2006.
[25]J.-S. Lee, "Digital image smoothing and the sigma filter," Computer Vision, Graphics, and Image Processing, vol. 24, pp. 255-269, Nov. 1983.
[26]D. T. Kuan, A. A. Sawchuk, T. C. Strand, and P. Chavel, "Adaptive noise smoothing filter for images with signal-dependent noise," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 165-177, Feb. 1985.
[27]P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 12, pp. 629-639, Jul. 1990.
[28]F. K. Quek and C. Kirbas, "Vessel extraction in medical images by wave-propagation and traceback," IEEE Trans Med Imaging, vol. 20, pp. 117-131, Feb. 2001.
[29]J. M. Thijssen, B. J. Oosterveld, and R. F. Wagner, "Gray level transforms and lesion detectability in echographic images," Ultrason Imaging, vol. 10, pp. 171-195, Jul. 1988.
[30]Z. Kato and T.-C. Pong, "A Markov random field image segmentation model for color textured images," Image and Vision Computing, vol. 24, pp. 1103-1114, Oct. 2006.
[31]S. Ribes, D. Didierlaurent, N. Decoster, E. Gonneau, L. Risser, V. Feillel, et al., "Automatic Segmentation of Breast MR Images Through a Markov Random Field Statistical Model," IEEE Transactions on Medical Imaging, vol. 33, pp. 1986-1996, Oct. 2014.
[32]M. Suliga, R. Deklerck, and E. Nyssen, "Markov random field-based clustering applied to the segmentation of masses in digital mammograms," Computerized Medical Imaging and Graphics, vol. 32, pp. 502-512, Sep. 2008.
[33]P. Belhomme, A. Elmoataz, P. Herlin, and D. Bloyet, "Generalized region growing operator with optimal scanning: application to segmentation of breast cancer images," Journal of Microscopy, vol. 186, pp. 41-50, Apr. 1997.
[34]W. Gao, X. Zhang, L. Yang, and H. Liu, "An improved Sobel edge detection," in Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on, pp. 67-71, Jul. 2010.
[35]I. J. Schoenberg and I. J. Schoenberg, Cardinal spline interpolation vol. 12: SIAM, Aug. 1973.