Classification of human colonic tissues using FTIR spectra and advanced statistical techniques
2010
One of the major public health hazards is colon cancer. There is a great necessity to develop new methods for early
detection of cancer. If colon cancer is detected and treated early, cure rate of more than 90% can be achieved.
In this study we used FTIR microscopy (MSP), which has shown a good potential in the last 20 years in the fields of
medical diagnostic and early detection of abnormal tissues.
Large database of FTIR microscopic spectra was acquired from 230 human colonic biopsies. Five different subgroups
were included in our database, normal and cancer tissues as well as three stages of benign colonic polyps, namely, mild,
moderate and severe polyps which are precursors of carcinoma.
In this study we applied advanced mathematical and statistical techniques including principal component analysis (PCA)
and linear discriminant analysis (LDA), on human colonic FTIR spectra in order to differentiate among the mentioned
subgroups' tissues. Good classification accuracy between normal, polyps and cancer groups was achieved with
approximately 85% success rate.
Our results showed that there is a great potential of developing
FTIR-micro spectroscopy as a simple, reagent-free viable
tool for early detection of colon cancer in particular the early stages of premalignancy among the benign colonic polyps.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
1
Citations
NaN
KQI