Abstract
Early diagnosis and early medical treatments are the keys to save the patients lives and improve their living quality. Fourier transform infrared (FTIR) spectroscopy can be used to distinguish malignant from normal tissues at the molecular level. In the present paper, programs were made with chemometrics method of pattern recognition to classify unknown tissue samples. Spectral data were pretreated by using smoothing, SNV and RHM method. Cross validation was used to test the discrimination effect of KNN method. A total of 63 gastric tissue samples were employed in this study, including 26 cases of normal tissue samples and 37 cases of cancerous tissue samples. The recognition results of the KNN method showed that the correctness of classification achieved 91.7%.
| Original language | English |
|---|---|
| Pages (from-to) | 439-443 |
| Number of pages | 5 |
| Journal | Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis |
| Volume | 27 |
| Issue number | 3 |
| State | Published - Mar 2007 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 3 Good Health and Well-being
Keywords
- Cancer
- FTIR
- KNN
- Pattern recognition
Fingerprint
Dive into the research topics of 'Application of KNN method to cancer diagnosis using Fourier-transform infrared spectroscopy'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver