Microscopic Image Feature Analysis System for Thyroid Tumor Pathologic Tissue Images on High-magnification Scales

• Main Authors: Tsai, Yao-Chuan, 蔡曜全
• Other Authors: Chen, Yen-Ting
• Format: Others
• Language: zh-TW
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/83254274265655166442

碩士 === 南台科技大學 === 電機工程系 === 99 === The morphological features and image features of the nuclei represent meaningful characteristics, especially in the microscopic tissue image on high-magnification scales. Referring to the clinical empirical rules of physician, this study aims to develop a image-based classification system using the high-magnification microscopic image of thyroid tumor. The high-magnification(1000X) microscopic images of cells and tissue are important materials for clinical observation in the screening of various cancer. This study applied the adaptive region segmentation approach to extract the image of nuclei from the background and other tissues. The 13 morphological and image features of nuclei were characterized and quantified. The statistical discriminant analysis method was then applied to classify the groups based on the distribution of features. The accuracy of nuclei classification for normal follicular cells is 95.55% and the popular papillary carcinoma can be actually discriminated. From the results of the experiments, we believe that this system has the feasibility to provide the information for assisting clinical diagnosis and study for thyroid disease in the nearly future.