臺灣博碩士論文加值系統

由於儲存在醫學資料庫中大量的影像資料不斷成長，有效的影像索引和檢索就變得非常重要。因此，需要發展一個疾病診斷的醫學影像檢索系統是當務之急。在這篇論文中，系統為協助診斷肝臟腫瘤和放射治療計畫的準備，提供3D影像檢索的功能，以及肝臟腫瘤分區位置判斷。在這系統中，著重在發展一個有效率且實用的方法，可以有效地檢索辨識出資料庫中相似的已知3D醫學影像病歷。此外，為了協助醫生規畫放射治療，也可以判斷腫瘤在肝臟的分區位置。
為了有效地檢索出相似的影像，我們已經開發了一個影像表示法，它可以捕捉腫瘤的形狀、大小和位置。這個影像表示法保有影像scaling-、translation-和rotation-invariance等特性，並且這些特性對於高準確性的影像檢索系統是必要的。為了滿足不同要求的醫生，一些相似性的措施和檢索方法，也根據我們的影像表示法被提出。最後，基於我們的影像表示法也提供肝臟腫瘤的分區位置判斷。實驗結果顯示，系統在於輔助醫生診斷肝腫瘤和放射治療規畫方面都有良好的表現。

Because the amount of pictorial information stored in medical databases is growing, efficient image indexing and retrieval becomes very important. Therefore, the need to develop a medical image retrieval system for disease diagnosis is urgent. In this thesis, a system for assisting in diagnosing the liver tumors and planning the corresponding radiation treatment is proposed. The proposed system provides the capabilities of 3D image retrieval as well as judging in which partitions of the liver the tumor is located. In the proposed system, the emphasis is on the development of an efficient and practical database for recognizing and retrieving similar patterns with known diagnoses in 3D medical images in an efficient manner. Furthermore, in order to assist physician in planning the radiation treatment, it can also judge the partitions of the liver in which the tumor is located.
To retrieve similar images efficiently, we have developed an image representation which can capture the shape, size and location of the tumor. The image representation has the properties of image scaling-, translation- and rotation-invariance, and these properties are necessary for an image retrieval system which works to a high degree of accuracy. To satisfy the different requirements of physicians, some similarity measures and a retrieval method based on our image representation approach are also proposed. Finally, a method based on our image representation to judge the partitions of liver where the tumor is located is also provided. Experiment results showed that the system has a good performance in terms of assisting physician in diagnosing the liver tumor and planning the radiation treatment.

摘要 Ⅰ
Abstract Ⅱ
目錄索引 Ⅲ
圖目錄 Ⅳ
表目錄 Ⅵ
第一章 緒論 1
1.1 前言 1
第二章 研究動機與背景 4
2.1 影像檢索系統 4
2.2 肝臟腫瘤 7
2.2.1 肝臟解剖構造 7
2.2.2 肝腫瘤的診斷及治療 12
2.3 放射線治療 16
2.3.1 放射治療之介紹 16
2.3.2 放射治療設備 19
第三章 研究方法 23
3.1 病例資料 23
3.2 影像表示法 25
3.3 腫瘤分區範圍判斷之方法 30
3.4 相似度衡量之方法 35
第四章 實驗結果及分析討論 37
4.1 實驗環境 37
4.2 實驗結果 38
第五章 結論與未來展望 71
參考文獻 73

[1]吳彥緻、簡鈺軒、戴紹國、詹以吉 “利用相似性擷取的肝癌細胞分級輔助系統,” TANET 2007台灣網際網路研討會論文集(二),2007.
[2]徐麗蘋、鄭文斌 “輔助肝部腫瘤診斷之影像資訊系統,” IMP 2009第十五屆資訊管理暨實務研討會,2009.
[3]Alajlan, Naif, Kamel, Mohamed S. and Freeman, George H., “Geometry-based image retrieval in binary image databases,” IEEE Trans. On Pattern Analysis and Machine Intelligence, vol. 30, no. 6, pp. 1003-1013, 2008.
[4]Ana, Alonso-Torres, Jaime, Ferna′ndez-Cuadrado, Inmaculada, Pinilla, Manuel, Parro′n, Emilio, de Vicente, Manuel, Lo′pez-Santamarı′a “Multidetector CT in the Evaluation of Potential Living Donors for Liver Transplantation,” Radiological Society of North America, vol. 25, no. 4, pp. 1017-1030, 2005.
[5]Chang, S. K., Shi, Q. Y. and Yan, C. W., “Iconic Indexing by 2D Strings,” IEEE Trans. On Pattern Analysis and Machine Intelligence, vol. 9, no. 3, pp. 413-428, 1987.
[6]Chen, Chung-Ming, Lu, Henry Horng-Shing, Huang, Yueng-Shiang, “Cell-based dual snake model: a new approach to extracting highly winding boundaries in the ultrasound images,” Ultrasound in Medicine and Biology, vol.28, pp. 1061-1073, 2002
[7]Couinaud, L., “Le Foie – Etudes Anatomiques et Chirurgicales,” Masson Paris, 1956.
[8]Do, M. N. and Vetterli, M. “Wavelet-based Texture Retrieval Using Generalized Gaussian Density and Kullback-Leibler Distance,” IEEE Trans. Image Processing, vol. 11, no. 2, pp. 146-158, 2002.
[9]Doherty, M, Bordes, N, Hugh, T., Pailthorpe, B (2002) “3D Visualisation of Tumours and Blood Vessels in Human Liver,” Pan-Sydney Area Workshop on Visual Information Processing (VIP2002), Sydney, Australia. Conferences in Research and Practice in Information Technology, vol. 22, 2002.
[10]Fauzi, Mohammad Faizal Ahmad, Ahmad, Wan Siti Halimatul Munirah Wan, “Efficient block-based matching for content-based retrieval of CT head images,” IEEE multimedia signal processing, 2008.
[11]Grady, J.G.O., Lake J.R., Howdle, P.D. (2000) “Comprehensive Clinical Hepatology.” Harcourt Publisher Limited, pp. 1.3-1.6.
[12]Hsieh, Shu-Ming and Hsu, Chiun-Chieh, “Graph-based representation for similarity retrieval of symbolic images,” Data & Knowledge Engineering, 2008.
[13]Huang, P. W., Dai, S. K., “Image Retrieval by Texture Similarity,” Pattern Recognition, vol. 36, pp. 665-679, 2003.
[14]Huang, P. W. and Hsu, Lipin, “A Region-Based Image Representation for Spatial Reasoning and Similarity Retrieval in Image Database Systems,” Journal of Information & Optimization Sciences, vol. 28, no. 3, pp. 377-407, 2007.
[15]Huang, P. W., Hsu, Lipin, Su, Y. W. and Lin, P. L., “Spatial Inference and Similarity Retrieval of an Image Database System Based on Extended Object’s Spanning Representation,” Journal of Visual Languages & Computing, 2008.
[16]Korn, P., Sidiropoulos, N., Faloutsos, C., Siegel, E., Protopapas, Z., “Fast and effective retrieval of medical tumor shapes,” IEEE Transactions on Knowledge and Data Engineering, vol.10, pp. 889-904, 1998.
[17]Martin Robin , Bordes Nicole , Hugh* Thomas and Pailthorpe Bernard , “Semi-Automatic Feature Delineation In Medical Images,” Information Visualisation 2004, Christchurch, New Zealand, pp. 127-132, 2004.
[18]Ng, Vincent, Cheung, David, and Fu, Ada, “Medical image retrieval by color content,” IEEE Proc, pp. 1980-1985, 1995.
[19]Soyer, Philippe, Bluemke, David A., Bliss, Donald F., Woodhouse, Christopher E. and Fishman, Elliot K., “Surgical Segmental Anatomy of the Liver: Demonstration with Spiral CT During Arterial Portography and Multiplanar Reconstruction,” American Journal of Rorntgenology, vol. 163, pp. 99-103, 1994.
[20]Yu, Sung Nien, Chiang, Chih Tsung and Hsieh, Chin Chiang, “A three-object model for the similarity searches of chest CT images,” Computerized Medical Imaging and Graphics, vol. 29, pp. 617-630, 2005.
[21]Zhou, Xiao Ming, Ang, Chuan Heng and Ling, Tok Wang, “Indexing for multipoint interactive similarity retrieval in iconic spatial image databases,” Journal of Visual Languages and Computing, vol. 10, pp. 24-38, 2008.
補充資料
[22]Ho, Shang-Yun, MD, “Clinical Application of Sonography,” Department of Radiology Changhua Christian Hospital.
[23]Hsiung, Hsiao-yun, MD, “Liver and Spleen,” Department of Radiology Taichung Veterans General Hospital.
[24]Hwang, Jen-I, MD, “Ultrasonic Diagnosis of Liver, Pancreas and Spleen,” Department of Radiology Taichung Veterans General Hospital.