臺灣博碩士論文加值系統

　　肺是人體重要的器官之一，當發生病變時，使用醫學影像可以來輔助醫療人員更深入、更細緻、更精確地做出診斷。在醫學影像上利用影像物件切割技術，將器官或物件輪廓找出來後，可以針對這些區域做特徵分析，提供給醫師及研究人員做為他們診斷及研究時的輔助。而X光造影（X-rays）是目前最常用的醫學影像形式，主要用於檢查肺部及其它部位的變化，同時資料數量多，取得容易，所以本論文主要針對正向（postero-anterior view, PA view）的胸部X光影像作研究。
　　應用於一般影像的物件切割技術，也可以應用在醫學影像，例如Canny邊緣偵測器與近年來常用的主動輪廓模型。然而動輪廓模型必須先給定一個初始輪廓，而且過於敏感而容易受到肋骨的干擾，很難準確地偵測肺部輪廓。
　　本論文針對PA view 胸腔X 光影像提出一個快速的肺部輪廓偵測方式，利用醫療影像的特性，定位出肺域的位置後使用Canny 邊緣偵測器找出肺葉可能的邊緣。最後連接邊緣線段並經過細線化，得到了近似肺葉邊緣的輪廓線。

Lung is one of the most important organs in the body. Medical Image analysis can be used to aid the diagnosis for the clinicians, to trace the progression of diseases. By applying the object segmentation technique in medical images, the contours of organs can be detected and used to analyze the tissue characteristics. Subsequently, these can be provided to doctors and researchers to aid their works.
X-ray is the most widely used imaging modality for diagnosing diseases occurred in the chest and other anatomical organs. It is cheap and commonly taken routinely. This study investigates PA View chest radiographs.
Canny edge detector and active contour models (ACM) are widely used techniques for object segmentation in medical images. However, the main weakness of the ACM is that an initial contour must be given so that the contour can be attracted to a proper position. In addition, it is time-consuming. For application in lung segmentation, it is easy to be interfered by the rib cage.
This study proposes a fast method for lung segmentation. Salient features of chest images are used to locate the lung field. After the Canny edge detector has been adopted to detect edges and to find the approximated contours of the III
lung lobes. Finally, the contours of the lung lobe with great accuracy can be obtained.

摘要.......................................................... I
Abstract ..................................................... II
目錄......................................................... IV
表目錄....................................................... VI
圖目錄...................................................... VII
第一章 緒論.................................................. 1
第一節 研究背景........................................... 1
第二節 醫學影像的形式..................................... 1
第三節 應用於肺部醫療影像的系統........................... 4
第四節 研究動機與目的..................................... 6
第五節 名詞解釋........................................... 7
第六節 研究架構........................................... 8
第二章 文獻探討.............................................. 9
第一節 肺域定位........................................... 9
第二節 Canny邊緣檢測..................................... 13
第三節 主動輪廓模型...................................... 15
第三章 研究方法............................................. 17
第一節 影像前處理........................................ 17
第二節 肺域的定位........................................ 19
第三節 邊緣偵測.......................................... 22
第四章 實驗與討論............................................ 29
第一節 實驗材料與設備.................................... 29
第二節 實驗結果與討論.................................... 31
第五章 結論與未來工作....................................... 43
參考文獻..................................................... 44

1. M. F. McNitt-Gray, H. K. Huang, and J. W. Sayre,“Feature selection in the pattern classification problem of digital chest radiograph segmentation,” IEEE Transactions on Medical Imaging, 1995, Vol. 14, No. 3, pp. 537-547.
2. M. Brown, R. Gill, H. Talhami, L. Wilson, and B. Doust, “Model-based assessment of lung structures: Inferencing and control system,”Proceedings of SPIE Medical Imaging, San Diego, CA, 1995, Vol. 2433, pp. 167-178.
3. Tsuji, M.T. Freedman, and S.K. Mun, “Automated segmentation of anatomic regions in chest radiographs using an adaptive-sized hybrid neural network,” Medical Physics, 1998, Vol. 25, pp. 998-1007.
4. Z. Yue, A. Goshtasby, and L. V. Ackerman, “Automatic detection of rib borders in chest radiographs,” IEEE Transactions on Medical Imaging, 1995, Vol. 14, No. 3, pp. 525-536.
5. R. O. Duda and P. E. Hart, “Use of the Hough Transform to detect lines and curves in pictures,” Communication of the ACM, 1972, Vol. 15, No. 1, pp. 11-15.
6. S. G. Armato, III, M. L. Giger, and H. MacMahon, “Automated lung segmentation in digitized posteroanterior chest radiographs,” Academic Radiology, 1998, Vol. 5, No. 4, pp. 245-255.
7. M. S. Brown, L. S. Wilson, B. D. Doust, R. W. Gill, and C. Sun., “Knowledge-based method for segmentation and analysis of lung boundaries in chest x-rays images,” Computerized Medical Imaging and Graphics, 1998, Vol. 22, pp. 463-477
8. I. E. Sobel, “Camera models and machine perception,” Ph. D Thesis, Electrical Engineering department, Stanford university, Stanford, CA, 1970.
9. C. Brodley, A. Kak, C. Shyu, J. Dy, L. Broderick, and A. M. Aisen, “Content-based retrieval from medical image databases: A synergy of human interaction, machine learning and computer vision,” Proceedings of the 10th National Conference on Artificial Intelligence, Orlando, FL, USA, 1999, pp. 760-767.
10. J. F. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, November 1986, Vol. 8 No. 6, pp. 679-698.
11. K. Veropoulos, C. Campbell, and G. Learnmonth, “Image processing and neural computing used in the diagnosis of tuberculosis,” Proceedings of the Colloquium on Intelligent Methods in Healthcare and Medical Applications, York, UK, 1998.
12. M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: active contour models,” International Journal of Computer Vision, 1988, Vol. 1, No. 4, pp. 321-331.
13. C. Xu and J. Prince, “Snakes, shapes, and gradient vector flow,” IEEE Transactions on Image Processing, March 1998, Vol. 7, pp. 359-369.
14. L. Li, Y. Zheng, Ma. Kallergi, and R. A. Clark, “Improved method for automatic identification of lung regions on chest radiographs,” Academic Radiology, July 2001, Vol. 8, No. 7, pp. 629-638.
15. X. Xie, Xi Li, J. Zhang, and Y. Gong, “The window of lung fields: automatic determination and its application in chest radiograph processing,” The 3rd IASTED International Conference on Biomedical Engineering, Innsbruck, Austria, February 16-18 2005, pp. 75-79.
16. L. D. Cohen, “On active contour models and balloons,” Computer Vision, Graphics, and Image Processing: Image Understanding, 1991, Vol. 53, No. 2, pp. 211-218.
17. L. D. Cohen and I. Cohen, November, “Finite-element methods for active contour models and balloons for 2-D and 3-D images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, Vol. 15, No. 11, pp. 1131-1147.
18. C. Y. Hsu, S. H. Chen, and K. L. Wang, “Active contour model with a novel image force field,” 16th IPPR Conference on Computer Vision, Graphics and Image Processing, Kinmen, Taiwan, 2003, pp. 477-483.