Enhancing cancer diagnosis using spectroscopic information.
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 me...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2009
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/16628 |
| Summary: | 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. |
|---|