Enhancing cancer diagnosis using spectroscopic information.

• 主要作者: Huang, Ke.
• 其他作者: School of Chemical and Biomedical Engineering
• 格式: Final Year Project
• 語言: English
• 出版: 2009
• 主題: DRNTU::Engineering::Chemical engineering::Biotechnology
• 在線閱讀: http://hdl.handle.net/10356/16628
• 機構: Nanyang Technological University

Cancer diagnosis is a very important process in the cancer treatment. With mass spectroscopic information, which characterizes the serum of the patients, the diagnostic process can be implemented more efficiently. As spectroscopic information is usually with a high dimension, statistic methods are developed to reduce the dimension of the spectroscopy and reserve the information for analysis. Common methods of discriminant analysis include Fisher Discriminant Analysis (FDA), Partial Least Squares Discriminant Analysis (PLSDA) and Unsupervised Discriminant Projection (UDP). The applications of these methods to the cancer diagnosis process are described in this report. Supervised Discriminant Projection (SDP) based on UDP with supervised discriminant process instead was proposed. Comparisons were made among these methods with different parameters employed; and a most appropriate discriminant method was recommended at the end of the report.