Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/24211
標題: 以腦組織影像為基礎之星狀細胞瘤惡性期數辨識系統
Brain Tissue Image Based Malignant Astrocytoma Grading System
作者: 魏立旻
Wei, Li-Min
關鍵字: Image segmentation;影像切割;tissue images;astrocytoma;image grading system;影像組織圖;星狀細胞瘤;影像分期辨識系統
出版社: 資訊管理學系所
引用: [1]S. Arivazhagan and L. Ganesan, “Texture Segmentation Using Wavelet Transform” 2003, Pattern Recognition Letters, vol. 24, no. 16, pp. 3197-3203. [2]J. M. Chaves-Gonzalez, M. A. Vega-Rodriguez, J. A. Gomez-Pulido, and J. M. Sanchez-Perez, “Detecting Skin in Face Recognition Systems: A Colour Spaces Study,” 2010, Digital Signal Processing, vol. 20, no. 3, pp. 806-823. [3]L. M. Deangelis, “Brain Tumors,” 2001, The New England Journal of Medicine, vol. 344, no. 2, pp. 114-123. [4]R. M. Haralick, K. Shanmugam, and I. Dinstein, “Texture Features for Image Classification,” 1973, IEEE Transactions on System Man Cybernetics, vol. 3, pp. 610-621. [5]A. M. Hsu, “Image-Based Cell Counting and Feature-Based Image Segmentation”, 2009, National Chung Hsing University. [6]U. Maulik, “Medical Image Segmentation Using Genetic Algorithms,” 2009, IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 2, pp. 166-173. [7]Y. N. Mamatha and A.G. Ananth, “Texture Based Content Retrival for Satellite Images Using Filter Technique,” R.V College of Engineering. [8]K. F. Man, K. S. Tang, and S. Kwong, “Genetic Algorithms: Concepts and Designs, Springer-Verlag,” 1999, New York. [9]Mayfield Clinic, “Brain Tumors,” 2010, (http://www.mayfieldclinic.com/PE-BrainTumor.htm). [10]Medical Center, (http://www.umm.edu/patiented/articles/how_chemotherapy_used_treating_brain_tumors_000089_11.htm). [11]M. Sezgin and B. Sankur, “Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation,” 2004, Jornal of Electronic Imaging, vol. 13, no. 1, pp. 146-165. [12]F. Tsai, C. K. Chang, J. Y. Rau, T. H. Lin, and G. R. Liu,“3D Computation of Gray Level Co-occurrence in Hyperspectral Image Cubes,” 2007, Center for Space and Remote Sensing Research, National Central University, pp. 429-440. [13]P. Y. Wen and S. Kesari, “Malignant Gliomas in Adults,” 2008, The New England Journal of Medicine, vol.359, no. 5, pp. 492-507. [14]Wikipedia The Free Encyclopedia, “Astrocytoma,” (http://en.wikipedia.org/wiki/Astrocytoma). [15]Y. S. Yun, “Hybrid Genetic Algorithm with Adaptive Local Search Scheme,” 2006, Computers and Industrial Engineering, vol. 51, no. 1, pp. 128-141.
摘要: 
本篇論文主要探討醫學影像之切割及分期辨識,而研究之內容乃來自惡性腦腫瘤之星狀細胞瘤的醫學組織影像圖做影像分期辨識。本研究透過切割方法取出腦組織圖內的細胞特徵之後,應用病理細胞在影像中之特徵來對影像做分期。切割部分細分為三部分,分別切出癌細胞核(nuclear atypia),壞死細胞(necrosis), 以及正在進行減數分裂之細胞(mitoses)。影像切割完畢之後,擷取出各類細胞之細胞個數、平均面積大小、標準差等特徵。接著應用基因演算法(Genetic Algorithm)對每個特徵產生出不一樣的權重值,再去判斷影像的分期期數。
在切割過程中,針對每一種不一樣細胞的特性去做切割,像是癌細胞核屬於顏色比較黑,壞死細胞則屬顏色比較白,而減數分裂之細胞則屬於比較平滑的區域。本研究應用基因演算法(Genetic Algorithm)來找出實驗中的最佳參數。
在醫學影像上,利用影像組織圖來辨識腦腫瘤期數乃是一項新的想法。由於數位醫學影像的量化是很耗時的工作,本篇提出影像自動切割及分期辨識系統來減少耗時以及人為的判斷錯誤。本篇實驗結果主要為組織影像圖切割之後的正確率,以及特徵擷取之後得到的分期結果正確率,而測試之後的分期辨識平均正確率超過85%。

This paper proposed an image segmentation and grading system for medical tissue images, which are related to the brain tumor, called astrocytoma. In this study, the features of brain tissue image are retrieved by using the segmentation methods to future recognizing which grade of brain tumor is. The segmentation methods are broken to three sub-methods including nuclear atypia, necrosis, and mitoses cells. After segmentation, the features, such as cell number, average area, and standard deviation will be obtained. There are different weights generated by Genetic Algorithm for each feature help in judging which grade of the processing image is.
During the segmentation process, each kind of cells is segmented according to their properties in an image; for example, nuclear atypia is with lower intensities, necrosis is with higher intensities as well as mitoses is with smoother area. Using the Genetic Algorithm, the optimal parameters will be used in the experiments.
It is the first idea to recognize the tumor grade in medical tissue image. Due to dealing with the huge amount of digital images is a time consuming task, we propose an automatic image segmentation and grading method to save time and reduce the human judgment errors. The experiments mainly focus on the accuracy of both results of segmentation and image grading. On average, the accuracy of image grading is higher than 85%.
URI: http://hdl.handle.net/11455/24211
其他識別: U0005-1807201101171500
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.