喉部為人類重要呼吸通道與發聲機制，臨床上耳鼻喉科醫師為使用喉閃頻內視鏡(Strobo-laryngoscope)進行觀察喉部聲帶(Vocal fold)運動行為與檢測聲帶疾病，由於目前醫師診斷病情是以人工方式於電腦螢幕上挑選影像，為此本研究設計一套自動化聲帶疾病辨識系統，利用醫師實際拍攝影片作為實驗分析樣本，結合影像處理技術，將自動地從影片中擷取聲帶張開最大位置與聲帶閉合最小位置影像，以取代醫師挑選過程並提升診斷效率。實際拍攝過程存在著人為因素而導致拍攝晃動模糊畫面以及非聲帶影像，因此於實驗中加入紋理分析，量測影像平滑度及熵值(Entropy)，以此建立一套篩選淘與汰制度，有效地提升擷取聲帶閉合最小位置影像正確性。此外，聲帶張開最大位置影像經實驗流程，利用影像處理自動分析聲門(Glottis)區域影像及發聲聲帶振動位置，從中取得聲帶生理參數，並繪製黏膜(Mucosa)波動曲線圖，作為聲帶發聲健康輔助依據。本研究聲帶疾病辨識系統主要針對正常聲帶(Normal)、聲帶麻痺(Vocal paralysis)與聲帶結節(Vocal nodule)，求取聲帶生理參數並應用決策樹(Decision tree)演算法做為分類聲帶疾病之分類器，其辨識率為92.6%，經加入影像後處理其辨識率可提升至98.7%，最後本研究對聲帶癌症(Vocal cancer)與聲帶瘜肉(Vocal polyp)之病變組織區域，量測紋理特徵並將其建立一統計數據表，以本系統協助醫師於臨床上參考評估。

Larynx is the main breathing channel and vocal mechanism. Clinically, otolaryngologists use strobo-laryngoscopes to observe the movements of vocal fold and diagnose vocal fold disorders. As the current diagnostic method is to select images on the computer screen manually, this study attempted to design a set of automatic vocal fold diseases identification system. Using the films taken by doctors as the samples for experimental analysis, this study used image processing techniques to capture the images of the vocal fold opening to the maximum position and closing to the minimum position in order to replace the manual image selection process and enhance diagnostic efficiency. As the filming process may involve human factors that cause blurred images and non-vocal fold image, this study included texture analysis to measure the image smoothness and entropy, in order to develop a set of selection and elimination system that can effectively enhance the accuracy of the capture images. Moreover, for the images of the vocal fold opening to the maximum position, image processing was used to automatically analyze the glottis images and vibration position of the vocal fold, in order to obtain physiological parameters and plot the mucosa fluctuation diagram as the references for vocal fold health promotion. The vocal fold diseases identification system can be used to obtain the physiological parameters for normal, vocal paralysis, and vocal nodules. Decision tree method was used as a classier to categorize the vocal fold diseases. The identification accuracy was proven to be 92.6%, and it could be improved to 98.7% after combining image processing. Finally, the study measures texture feature and establishes a statistic table in the area of lesions between vocal cancer and vocal polyp. This system can serve as a reference for clinical use.

[1] Chodara, A. M., Krausert, C. R., and Jiang, J. J., “Kymographic Characterization of Vibration in Human Vocal Folds With Nodules and Polyps” , The Laryngoscope, Vol. 122, No. 1, pp. 58-65 (2012).
[2] Švec, J. G., and Schutte, H. K., “Videokymography: High-Speed Line Scanning of Vocal Fold Vibration” , Journal of Voice, Vol. 10, No. 2, pp. 201-205 (1996).
[3] E ysholdt, U., Rosanowski, F., and Hoppe, U., “Vocal Fold Vibration Irregularities Caused by Different Types of Laryngeal Asymmetry” , Eur Arch of Otorhinolaryngol, Vol. 260, No. 8, pp. 412-417 (2003).
[4] Larsson, H., Hertegård, S., Lindestad, P. –Å., and Hammarberg, B., “Vocal Fold Vibrations: High-Speed Imaging, Kymography, and Acoustic Analysis: A Preliminary Report” , The Laryngoscope, Vol. 110, No. 12, pp. 2117-2122 (2000).
[5] Mergell, P., Herzel, H., and Titze, I. R., “Irregular Vocal-Fold Vibration—High-speed Observation and Modeling” , Acoustical Society of America, Vol. 108, No. 6, pp. 2996-3002 (2000).
[6] Chen, X., Bless, D., and Yan, Y., “A Segmentation Scheme Based on Rayleigh Distribution Model for Extracting Glottal Waveform from High-speed Laryngeal Images” , Proceedings of IEEE International Conference of the Engineering in Medicine and Biology Society, Shanghai, pp. 6269-6272 (2005).
[7] Méndez, A., García, B., Ruiz, I., and Iturricha, I., “Glottal Area Segmentation Without Initialization Using Gabor Filters” , Proceedings of IEEE International Symposium on Signal Processing and Information Technology, Sarajevo, pp. 18-22 (2008).
[8] Yan, Y., Chen, X., and Bless, D., “Automatic Tracing of Vocal-Fold Motion From High-Speed Digital Images” , IEEE Transactions on Biomedical Engineering, Vol. 53, No. 7, pp. 1394-1400 (2006).
[9] Zorrilla, A. M., and Zapirain, B. G., “Vocal Folds Paralysis Study Using a Pre-processing Stage of Gabor Filtering and Chan-Vese Segmentation” , Proceedings of IEEE International Symposium on Signal Processing and Information Technology, Luxor, pp. 360-365 (2010).
[10] Méndez, A., García, B., Vicente, J., Ruiz, I., and Sánchez, K., “Objective Model of Vocal Folds, Based on Glottal Closure, Opening Angles and Morphologic Criteria” , Proceedings of IEEE International Symposium on Signal Processing and Its Applications, Sharjah, pp. 1-4 (2007).
[11] Schade, G., Leuwer, R., Kraas, M., Rassow, B., and Hess, M. M., “Laryngeal Morphometry with a New Laser ‘Clip On’ Device” , Lasers in Surgery and Medicine, Vol. 34, No. 5, pp. 363-367 (2004).
[12] Larsson, H., and Hertegård, S., “Vocal Fold Dimensions in Professional Opera Singers as Measured by Means of Laser Triangulation” , Journal of Voice, Vol. 22, No. 6, pp. 734-739 (2008).
[13] Zorrilla, A. M., El-Zehiry, N., Zapirain, B. G., and Elmaghraby, A., “Pathological Vocal Folds Diagnosis Using Modified Active Contour Models” , Proceedings of IEEE International Conference on Information Sciences Signal Processing and their Applications, Kuala Lumpur, pp. 504-507 (2010).
[14] Verikas, A., Gelzinis, A., Valincius, D., Bacauskiene, M., and Uloza, V., “Multiple Feature Sets Based Categorization of Laryngeal Images” , Computer Methods and Programs in Biomedicine, Vol. 85, No. 3, pp. 257-266 (2007).
[15] Qin, X., Wang, S., and Wan, M., “Improving Reliability and Accuracy of Vibration Parameters of Vocal Folds Based on High-Speed Video and Electroglottography” , IEEE Transactions on Biomedical Engineering, Vol. 56, No. 6, pp. 1744-1754 (2009).
[16] Zhang, Y., Jiang, J. J., and Appel, A., “Spatiotemporal Vibratory Dynamics of Vocal Fold Scar Using High-speed Digital Imaging” , Electronics Letters, Vol. 46, No. 7, pp. 483-484 (2010).
[17] Yu Zhang, Regner, M. F., and Jiang, J. J., “Theoretical Modeling and Experimental High-Speed Imaging of Elongated Vocal Folds” , IEEE Transactions on Biomedical Engineering, Vol. 58, No. 10, pp. 2725-2731 (2011).
[18] 張斌編著(1996)。《耳鼻喉科學》。臺北：正中。
[19] Pontes, P., Kyrillos, L., Behlau, M., Biase, N. D., and Pontes, A., “Vocal Nodules and Laryngeal Morphology” , Journal of Voice, Vol. 16, No. 3, pp. 408-414 (2002).
[20] Klein, A. M., Lehmann, M., Hapner, E. R., and Johns, M. M., “Spontaneous Resolution of Hemorrhagic Polyps of the True Vocal Fold” , Journal of Voice, Vol. 23, No. 1, pp. 132-135 (2009).
[21] 謬紹綱譯(2008)。《數位影像處理》。臺北：普林斯頓國際。
[22] 謬紹綱譯(2005)。《數位影像處理─運用MATLAB》。臺北：東華。
[23] 楊高波、杜青松編著(2010)。《MATLAB圖像/視頻處理應用及實例》。北京：電子工業。
[24] Gabor, D., “Theory of Communication” , Journal of the Institute of Electrical Engineers, Vol. 93, pp.429-457 (1946).
[25] Daugman, J. G., “Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters” , Journal of the Optical Society of America A, Vol. 2, No. 2, pp. 1160-1169 (1985).
[26] Liu, C., and Wechsler, H., “Independent Component Analysis of Gabor Features for Face Recognition” , IEEE Transactions on Neural Networks, Vol. 14, No. 4, pp. 919-928 (2003).
[27] Gottschlich, C., “Curved-Region-Based Ridge Frequency Estimation and Curved Gabor Filters for Fingerprint Image Enhancement” , IEEE Transactions on Image Processing, Vol. 21, No. 4, pp. 2220-2227 (2012).
[28] Lin, Z., and Lu, B., “Iris recognition method based on the optimized Gabor filters” , International Congress on Image and Signal Processing, Yantai, Vol. 4, pp. 1868-1872 (2010).
[29] Mehrotra, R., Namuduri, K. R., and Ranganathan, N., “Gabor Filter-Based Edge Detection” , Pattern Recognition, Vol. 25, No. 12, pp. 1479-1494 (1992).
[30] Otus, N., “A Threshold Selection Method from Gray-Level Histograms” , IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp.62-66 (1979).
[31] 王晉中譯(2005)。《MATLAB 7 在工程上的應用》。臺北：麥格羅希爾。
[32] Quinlan, J. R., C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers, San Mateo, CA (1993).
[33] Quinlan, J. R., “Induction of Decision Tress” , Machine Learning, Vol. 1, pp. 81-106 (1986).
[34] Shannon, C. E., “A Mathematical Theory of Communication” , The Bell System Technical Journal, Vol. 27, pp. 379-423 (1948).
[35] 陳垚光等編著(2011)。《經通MATLAB GUI設計》。北京：電子工業。