Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/24439
標題: 頸動脈超音波頻譜影像之自動化切割與辨識研究
A Study of Automatic Segmentation and Recognition Technology for Common Carotid Artery Ultrasound Spectrum Images
作者: 陳巧旻
Chen, Chiao-Min
關鍵字: 頸動脈;common carotid artery;有效波型特徵;超音波頻譜影像;影像辨識;影像切割;effective waveform feature;ultrasound spectrum image;image recognition;image segmentation
出版社: 資訊管理學系所
引用: [1] M. S. Atkins and B. T. Mackiewich, “Fully automatic segmentation of the brain in MRI,” IEEE Transactions on Medical Imageing, Vol. 17, No. 1, 1998, pp. 98-107. [2] S. Arora, J. Acharya, A. Verma and P. K. Panigrahi, “Multilevel thresholding for image segmentation through a fast statistical recursive algorithm,” Pattern Recognition Letters, Vol. 29, No. 2, 2008, pp. 119-125. [3] Anzalone, F. Bizzarri, M. Parodi and M. Storace, “A modular supervised algorithm for vessel segmentation in red-free retinal images,” Computers in Biology and Medicine, Vol. 38, No. 8, 2008, pp. 913-922. [4] J. Babaud, A. P. Witkin, M. Baudin and R. 0. Duda, “Uniqueness of the Gaussian kernel for scale-space filtering,” IEEE Transactions on Pattern Analysis and Machine and Machine Intelligence, Vol. 8, No. 1, 1986, pp. 26-33. [5] H. D. Cheng, X. H. Jiang, Y. Sun and J. Wang, “Color image segmentation: advances and prospects,” Pattern Recognition, Vol. 34, No. 12, 2001, pp. 2259-2281. [6] J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine and Machine Intelligence, Vol. 8, No. 6, 1986, pp. 679-698. [7] F. Dirgenali and S. Kara, “Recognition of early phase of atherosclerosis using principles component analysis and artificial neural networks from carotid artery Doppler signals,” Expert Systems with Applications, Vol. 31, No. 3, 2006, pp. 643-651. [8] D. Y. Huang and C. H. Wang, “Optimal multi-level thresholding using a two-stage Otsu optimization approach,” Pattern Recognition Letters, Vol. 30, No. 3, 2009, pp. 275-284. [9] L. He, Y. Chao, K. Suzukic and K. Wu, “Fast connected-component labeling,” Pattern Recognition, Vol. 42, No. 9, 2009, pp. 1977-1987. [10] G. W. Jiji, “Colour texture classification for human tissue images”, Applied Soft Computing, Vol. 11, No. 2, 2011, pp. 1623-1630. [11] J. Jing, W. Yan, G. Xin, S. Yi and W. Qi, “Automatic measurement of the artery intima-media thickness with image empirical mode decomposition,” in Proceedings of the Imaging Systems and Techniques, 2010, Thessaloniki. [12] S. Kucheryavski, “Using hard and soft models for classification of medical images,” Chemometrics and Intelligent Laboratory Systems, Vol. 88, No. 1, 2007, pp. 100-106. [13] H. Lai, S. S. Yu, H. Y. Tseng and M. H. Tsai, “A protozoan parasite extraction scheme for digital microscopic images,” Computerized Medical Imaging and Graphics, Vol. 34, No. 2, 2010, pp. 122-130. [14] X. Li and T. Chen, “Efficient synthesis of parameterized Gaussian-like filters by approximation,” Signal Processing, Vol. 41, No. 2, 1995, pp. 119-134. [15] F. Molinari, G. Zeng and J. S. Suri, “A state of the art review on intima–media thickness (IMT) measurement and wall segmentation techniques for carotid ultrasound,” Compute Methods Programs Biomed, Vol.100, No. 3, 2010, pp. 201-221. [16] F. Molinari, G. Zeng and J. S. Suri, “Intima-Media Thickness: Setting a Standardfor a Completely Automated Method of Ultrasound Measurement,” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, Vol. 57, No. 5, 2010, pp. 1112-1124. [17] M. Mignotte, “Segmentation by fusion of histogram-based k-means clusters in different color spaces,” IEEE Transactions on Image Processing, Vol. 17, No. 5, 2008, pp. 780-787. [18] H. P. Ng, S. H. Ong, K. W. C. Foong, P. S. Gohf and W. L. Nowinski, “Masseter segmentation using an improvedwatershed algorithm with unsupervised classification,” Computers in Biology and Medicine, Vol. 38, No. 2, 2008, pp. 171-184. [19] N. Otsu, “A threshold selection method from Gray-Level histograms,” IEEE Transactions on Systems and Cybernetics, Vol. 9, No. 1, 1979, pp. 62-66. [20] D. Pascale, “A Review of RGB color spaces,” http://www.babelcolor.com/download/A%20review%20of%20RGB%20color%20spaces.pdf, 2007, pp. 2-4. [21] J. K. Park, S. H. Kim, B. S. Kim and G. Choi, “Two cases of aberrant right subclavian artery and right vertebral artery that originated from the right common carotid artery,” Korean J Radiol, Vol. 9, 2008, pp. 39-42. [22] W. C. A. Pereira, A. V. Alvarenga, A. F. C. Infantosi, L. Macrini and C. E. Pedreira, “A non-linear morphometric feature selection approach for breast tumor contour from ultrasonic images,” Computers in Biology and Medicine, Vol. 40, No. 11, 2010, pp. 912-918. [23] E. L. Rubio, “Restoration of images corrupted by Gaussian and uniform impulsive noise,” Pattern Recognition, Vol. 43, No. 5, 2010, pp. 1835-1846. [24] R. Rocha, A. Campilho, J. Silva, E. Azevedo and R. Santos, “Segmentation of the carotid intima-media region in B-mode ultrasound images,” Image and Vision Computing, Vol. 28, No. 4, pp. 614-625. [25] F. D. Santos, M. A. Gutierrez and E. T. Costa, “Determination of the variation of the intima-media thickness and the diameter of arteries from echocardiographic ultrasound image sequences,” Physics Procedia, Vol. 3, No. 1, 2010, pp. 407-413. [26] K. Somkantha and N. T. Umpon, “Boundary detection in medical images using edge following algorithm based on intensity gradient and texture gradient features,” IEEE Transactions on Biomedical Engineering, Vol. 58, No. 3, pp. 567-573. [27] K. Suzuki, I. Horiba and N. Sugie, “Linear-time connected-component labeling based on sequential local operations,” Computer Vision and Image Understanding, Vol. 89, No. 1, 2003, pp.1-23. [28] S. Tsantisa, N. Dimitropoulosc, D. Cavourasb and G. Nikiforidisa, “Morphological and wavelet features towards sonographic thyroid nodules evaluation,” Computerized Medical Imaging and Graphics, Vol. 33, No. 2, 2009, pp. 91-99. [29] Yılmaz and N. F. Guler, “Analysis of the doppler signals using largest lyapunov exponent and correlation dimension in healthy and stenosed internal carotid artery patients,” Digital Signal Processing, Vol. 20, No. 2, 2010, pp. 401-409. [30] L. Wu and Z. Xie, “Scaling theorems for Zero-Crossings,” IEEE Transactions on Pattern Analysis and Machine and Machine Intelligence, Vol. 12, No. 1, 1990, pp. 46-54. [31] Z. Wei, J. Wang, H. Nichol, S. Wiebe and D. Chapman, “A median-gaussian filtering framework for moire pattern noise removal from X-ray microscopy image,” Micron, Vol. 43, No. 2-3, 2012, pp. 170-176. [32] B. Zhang, L. Zhang, L. Zhang and F. Karray, “Retinal vessel extraction by matched filter with first-order derivative of Gaussian,” Computers in Biology and Medicine, Vol. 40, No. 4, 2010, pp. 438-445.
摘要: 
醫學影像切割與辨識技術已廣泛應用於各種疾病之診斷。現今之醫學影像輔助診斷儀器所造影之醫學影像提供的訊息是豐富的,可以保留人工判讀之資訊並且提高診斷的之準確性。隨著老年人口快速劇增,罹患慢性疾病的發病率也日漸增加,其中常見的莫過於心血管之慢性疾病。都卜勒之頸動脈血流超音波頻譜影像是目前診斷心血管疾病之重要工具,由於心血管慢性疾病大多數為頸動脈血管之病變,血管狹窄或是血管阻塞是主要的疾病原因,因此頸動脈之檢查是目前不可或缺的檢驗項目之一。本研究提出一種新的方法,能具體讀取頸動脈都卜勒血流超音波頻譜影像,並自動切割並重建都卜勒之頸動脈血流超音波頻譜影像接著透過超音波影像擷取有效之波形特徵,其有效特徵為五種,分別是: 波型區域面積之比例、水平基準線下之區域面積標籤、水平基準線下之波形面積、波形區域之最高點與波形區域之最低點為五種特徵。本研究方法可自動切割波形區域,傳統上由醫師來區分正常與五種異常之血流型態,在新系統中之五種特徵可診斷血流型態其切割重建之準確率為0.97以及辨識血流型態之準確率為0.97,顯示透過此項技術可幫助醫師正確地並有效診斷血管疾病。

Medical image segmentation and recognition technology has been widely used in the diagnosis of various diseases. The information in medical images from modern instruments is rich. With the application of image recognition technology, manual reading time can be saved and diagnostic accuracy can be enhanced.With rapid expansion of the population of elderly people, the incidence of chronic diseases also increased. The most common among them is no doubt the cardiovascular diseases. The Common Carotid Artery (CCA) ultrasound spectrum image is an important tool in diagnosis of cardiovascular diseases. As vascular stenosis or occlusions are the main pathological change of vascular disorders, carotid artery examination is essential in the diagnosis of cardiovascular diseases.This thesis proposes a new method specific to the reading of ultrasound spectrum images of common carotid artery blood flow. The proposed scheme automatically segments reconstruction the waveform image and extracts effective waveform features from the images for diagnostic purposes by using the following five criteria: the ratio of the waveform region, the waveform region area target under the horizontal baseline, the waveform region area under the horizontal baseline, the highest point of the waveform region, and the lowest point of the waveform region.The proposed scheme can automatically segment the waveform region. Traditionally used by physicians to differentiate between normal blood-flow patterns and five abnormal blood-flow types, these five criteria are now employed by the new system to digitally diagnose vascular disorders at an accuracy rate as high as 0.97 and a segments reconstruction accuracy rate as high as 0.97. With this technology, physicians can diagnose vascular disorders correctly and efficiently.
URI: http://hdl.handle.net/11455/24439
其他識別: U0005-0808201223214400
Appears in Collections:資訊管理學系

Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.