醫學領域中，可藉由許多方式檢視人體內部的構造及器官，如早期的Ｘ光片，隨後發展電腦斷層影像(Computed Tomography, CT)、核磁共振造影(Magnetic Resonance Image, MRI)、微斷層攝影（Microtomography）等各種可用於顯示各種不同部位組織構造或是病徵的影像，以輔助醫生診斷病因。本研究運用影像處理技術自動辨識下鼻甲(Inferior turbinate, IT)及上頷竇(Maxilary Sinus, MS)，擷取電腦斷層影像訊號後先對影像做灰階處理後，將其正規化並針對下鼻甲及上颔竇區域(Region of Interesting, ROI)利用參數化模板匹配(Parametric Template, PT)擷取相似度特徵值，再對下鼻甲區域(Sub Region, SR)計算波形特徵值，再透過倒傳遞類神經網路(Back Propagation Neural Network, BPNN)訓練網路資料庫以判斷是否有ROI存在，判斷為是則再接著使用等位函數法(Level Set)將下鼻甲及上頷竇輪廓框圈選出來，再透過迴歸方程擬合出體積。本研究所開發之智慧型自動辨識及計算下鼻甲與上頷竇體積於電腦斷層影像之系統與醫師圈選之結果驗證得到之系統信賴度(Kappa)為0.86、整體準確率(Accuracy)為97.92%，確實可輔助醫師診斷下鼻甲及上頷竇之病情。

In the medical field, there are many methods to examine the internal structures and organs of human body, such as X-ray, computed tomography (CT), magnetic resonance image (MRI), and microtomography (micro-CT), which can display different parts of the tissues or symptoms, to assist in diagnosis. This study used the image processing technology to automatically identify the inferior turbinate and maxillary sinus. After capturing the computed tomography signals, the grey level processing was performed on the image. The image was normalized, and the parametric template matching was used to capture the similarity eigenvalues specific to the inferior turbinate and maxillary sinus areas. The waveform eigenvalues of the inferior turbinate area were calculated, and entered into the back-propagation neural network (BPNN) training network database in order to determine whether there ROI exists. If yes, the level set method is used to circle the contour box of the inferior turbinate and maxillary sinus, and the volume was fit by the regression equation. According to the verification of the results of the intelligent and automatic CT system of inferior turbinate and maxillary sinus volume identification and calculation, in comparison to the areas circled by the physicians, the system reliability reached 0.86 and the overall accuracy rate was 97.92%. The proposed system is proven to be able to assist physicians in diagnosing the state of illness of inferior turbinate and maxillary sinus.

[1] 黃育仁、陳冠妤，“主動式輪廓超音波腫瘤影像切割”，東海大學，資訊工程與科學系，碩士論文，(2005)。
[2] 于南書，“最佳特徵選擇-乳房 X光片腫瘤偵測”，國立成功大學，資訊工程學系，碩士論文，(2004)。
[3] 游崇善，“使用腹部電腦斷層掃瞄影像之肝腫瘤自動切割方法”，慈濟大學，醫學資訊研究所，碩士論文，(2009)。
[4] 林駿丞，“濾波器應用於改良式迭代式重建法以改善微正子斷層掃描影像品質”，國立陽明大學，放射醫學科學研究所，碩士論文，(2006)。
[5] 劉俊良，“智慧型動態MRI鼻部腫瘤自動偵測系統”，國立高雄第一科技大學，資訊管理系，碩士論文，(2008)。
[6] C. L. Chang, H. H. Chang, and C. P. Hsu, “An intelligent defect inspection technique for color filter”, IEEE International Conference on Mechatronics, pp. 933-936, (2005).
[7] G. Johannsen, and J. Bille, “A threshold selection method using information measures”, Proc. 6th Int. Conference Pattern Recognition Munich, Germany, pp. 140-143, (1982).
[8] W. Tsai, “Moment-preserving thresholding: A new approach”, Computer Vision, Graphics, and Image Processing, Vol. 29, pp. 377-393, (1985).
[9] J. N. Kapur, P. K. Sahoo, and A. K. C. Wong, “A new method for gray-level picture thresholding using the entropy of the histogram”, Computer Vision, Graphics, and Image Processing, Vol. 29, pp. 273-285, (1985).
[10] N. Otsu, “A threshold selection method from gray level histogram”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. 9, No. 1, pp. 62-66, (1979).
[11] T. W. Ridler, and S. Calvard, “Picture thresholding using an iterative selection method,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 8, No. 8, pp. 630- 632, (1978).
[12] Nevin, Ahmed and Farag, ”Modified Fuzzy C-Mean In Medical Image Segmentation,” Allient Health System and the NSF(ESC-9505674) , (1978).
[13] K. Tanaka, M. Sano, S. Ohara, and M. Okudaira, “ A parametric template method and its application to robust matching,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 620–627, (2000).
[14] Y. H. Lin, C. H. Chen, “ Template matching using the parametric template vector with translation, rotation and scale invariance,” Pattern Recognition, pp.2416-2421, (2008).
[15] M. K. Hu, “Visual pattern recognition by moment invariants,” IRE Transactions on Information Theory, Vol. 8, No. 2, pp. 179-187, (1962).
[16] S. A. Dudani, K. J. Breeding, and R. B. McGhee, “Aircraft identification by moment invariants,” IEEE Transactions on Computers, Vol. C-26, No. 1, pp. 39-45, ( 1983).
[17] A Khotanzad and Y. H. Hong, “Invariant image recognition by Zernike moments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 5, pp. 489-497, (1990).
[18] S. X. Laio and M. Pawlak, “On the accuracy of Zernike moments for image analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 12, pp. 1358-1364, (1998).
[19] S. X. Liao and M. Pawlak, “On image analysis by moments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 3, pp. 254-266, (1996).
[20] H. Lin and G. P. Abousleman, “Orthogonal rotation-invariant moments for digital image processing,” IEEE Transactions on Image Processing, Vol. 17, No. 3, pp. 272-282, ( 2008).
[21] M. Bendszus, H. Urbach, B. Meyer, R. Schultheiss, and L. Solymosi, “Improved CT diagnosis of acute middle cerebral artery territory infarcts with density-difference analysis,” Neuroradiology, Vol. 39, pp. 127-131, (1997).
[22] A. Usinskas, R. A. Dobrovolskis, and B. F. Tomandl, “Ischemicstroke segmentation on CT images using joint features,” Informatica, Vol. 15, pp. 283-290, (2004).
[23] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: active contour models,” Intl. Journal of Computer Vision, Vol. 1 pp. 321-331, (1988).
[24] S. Osher, and J. A. Sethian, “Fronts propagating with curva-ture-dependent Speed: Algorithms based on Hamilton-Jacobi formulations,” J. Comput. Phys, Vol. 79，pp. 12–49, (1998).
[25] T. Chan and L. Vese, “Active contours without edges”, IEEE Trans. on Image Process, Vol. 10, No. 2, pp.266–277, (2001).
[26] E. H. Kale, E. U. Mumcuoglu, S. Hamcan, “Automatic segmentation of human facial tissue by MRI–CT fusion: A feasibility study ”, Computer Methods and Programs in Biomedicine Vol. 108, No. 3, pp. 1106-1120, (2012).
[27] S. Ghose, A. Oliver, R. Marti, X. Llado, “A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images”, Computer Methods and Programs in Biomedicine Vol. 108, No. 1, pp. 262-287(2012).
[28] C. Zohios, G. Kossioris, Y. Papaharilaou, “Geometrical methods for level set based abdominal aortic aneurysm thrombus and outer wall 2D image segmentation t”, Computer Methods and Programs in Biomedicine Vol. 107, No. 2, pp. 202-217, (2012).
[29] M. Dang, J. Modi, M. Roberts, C. Chan, “Validation study of a fast, accurate, and precise brain tumor volume measurement”, Computer Methods and Programs in Biomedicine Vol. 111, No. 2, pp. 480-487, (2013).
[30] http://baike.baidu.com/picview/264269/264269/0/79b1e936c855051d0b55a960.html#albumindex=0&picindex=1
[31] http://mypaper.pchome.com.tw/hochungte/post/1321592868
[32] G. A. Wright, “Magnetic resonance imaging” IEEE Signal Pro-cessing Magazine, pp. 56-66, (1997).
[33] G. Sebastiani, and P. Barone, “Mathematical principles of basic magnetic resonance imaging in medicine” Signal Processing, pp. 227-250, (1991).
[34] 繆紹綱等，數位影像處理活用MATLAB，全華圖書股份有限公司，(2010)。
[35] 鄒錦聰等，MATLAB程式設計，全華科技圖書股份有限公司，(2003)。
[36] 連國珍等，數位影像處理MATLAB，儒林圖書有限公司，(2009)。
[37] S. Carsten, U. Markus, and W. Christian, 機器視覺演算法與應用，新亞洲儀器股份有限公司，(2011)。
[38] 鍾國亮，影像處理與電腦視覺(第四版)，東華書局，(2008)。
[39] 羅華強，類神經網路-MATLAB的應用，第六版，清蔚科技股份有限公司，(2001)。
[40] 周鵬程等，類神經網路入門活用MATLAB，全華圖書股份有限公司，(2008)。
[41] B. D. Saunders, and R. G. Trapp, “Basic and clinical biostatistics,” Prentice-Hall International, (1990).
[42] 范振添，“醫療影像傳輸及資料探索之系統開發”，中原大學，醫學工程學系，碩士論文，(2002)。
[43] 何宗穎，“可攜式即時心電圖監控系統”，慈濟大學，醫學資訊研究所，碩士論文，(2007)。