Study On Spectral Parameters And The Support Vector Machine In Surface Enhanced Raman Spectroscopy Of Serum For The Detection Of Colon Cancer
colon cancer; colorectal-cancer; discrimination; Optics; parameters; Physics; scattering sers; support; surface enhanced Raman spectroscopy; tumors; vector machine
Surface enhanced Raman spectroscopy (SERS) has been recognized as an effective tool for the analysis of tissue samples and biofluids. In this work, a total of 27 spectral parameters were chosen and compared using SERS. Four parameters with the highest prediction ability were selected for further support vector machine (SVM) analysis. As a comparison, principal component analysis (PCA) was used on the same dataset for feature extraction. SVM was used with the above two data reduction methods separately to differentiate colon cancer and the control groups. Serum taken from 52 colon cancer patients and 60 healthy volunteers were collected and tested by SERS. The accuracy for Parameter-SVM was 95.0%, the sensitivity was 96.2%, and the specificity was 95.5%, which was much higher than the results using only one parameter, while for PCA-SVM, the results are 93.3%, 92.3%, and 92.9%, respectively. These results demonstrate that the SERS analysis method can be used to identify serum differences between colon cancer patients and normal people.
Li X Z; Yang T Y; Li S Q; Yao J; Song Y T; Wang D L; Ding J H
Laser Physics Letters
2015
2015-11
Journal Article or Conference Abstract Publication
<a href="http://doi.org/10.1088/1612-2011/12/11/115603" target="_blank" rel="noreferrer noopener">10.1088/1612-2011/12/11/115603</a>
Raman Spectroscopy Combined With Principal Component Analysis And K Nearest Neighbour Analysis For Non-invasive Detection Of Colon Cancer
colon cancer; colorectal-cancer; component analysis; diagnosis; guideline; hemoglobin; k nearest neighbour analysis; operation; Optics; Physics; principal; Raman spectroscopy; regression; serum; spectra; surveillance
This paper attempts to investigate the feasibility of using Raman spectroscopy for the diagnosis of colon cancer. Serum taken from 75 healthy volunteers, 65 colon cancer patients and 60 post-operation colon cancer patients was measured in this experiment. In the Raman spectra of all three groups, the Raman peaks at 750, 1083, 1165, 1321, 1629 and 1779 cm(-1) assigned to nucleic acids, amino acids and chromophores were consistently observed. All of these six Raman peaks were observed to have statistically significant differences between groups. For quantitative analysis, the multivariate statistical techniques of principal component analysis (PCA) and k nearest neighbour analysis (KNN) were utilized to develop diagnostic algorithms for classification. In PCA, several peaks in the principal component (PC) loadings spectra were identified as the major contributors to the PC scores. Some of the peaks in the PC loadings spectra were also reported as characteristic peaks for colon tissues, which implies correlation between peaks in PC loadings spectra and those in the original Raman spectra. KNN was also performed on the obtained PCs, and a diagnostic accuracy of 91.0% and a specificity of 92.6% were achieved.
Li X Z; Yang T Y; Li S Q; Wang D L; Song Y T; Zhang S
Laser Physics
2016
2016-03
Journal Article or Conference Abstract Publication
<a href="http://doi.org/10.1088/1054-660x/26/3/035702" target="_blank" rel="noreferrer noopener">10.1088/1054-660x/26/3/035702</a>
Fourier Transform Infrared Imaging Spectroscopic Analysis Of Tissue Engineered Cartilage: Histologic And Biochemical Correlations
Biochemistry & Molecular Biology; bioreactor; chondrocytes; collagen; Fourier transform infrared imaging spectroscopy; hollow fiber bioreactor; hollow-fiber; human articular-cartilage; magnetic-resonance microscopy; matrix; Medical Imaging; model; mri techniques; Nuclear Medicine &; Optics; osteoarthritis; proteoglycans; Radiology; tissue engineered cartilage; tissue engineering
The composition of cartilage is predictive of its in vivo performance. Therefore, the ability to assess its primary macromolecular components, proteoglycan (PG) and collagen, is of great importance. In the current study, we hypothesized that PG content and distribution in tissue engineered cartilage could be determined using Fourier-transform infrared imaging spectroscopy (FT-IRIS). The cartilage was grown from chondrocytes within a hollow fiber bioreactor (HFBR) system previously used extensively to study cartilage development. FT-IRIS analysis showed a gradient of PG content, with the highest content in the center near the nutritive fibers and the lowest near the interior surface of the HFBR. Further, we found significantly greater PG content in the region near culture medium inflow (45.0%) as compared to the outflow region (24.7%) (p < 0.001). This difference paralleled the biochemically determined glycosaminoglycan difference of 42.6% versus 27.8%. In addition, FT-IRIS-determined PG content at specific positions within the tissue sections correlated with histologically determined PG content (R=50.73, p=50.007). In summary, FT-IRIS determination of PG correlates with histological determination of PG and yields quantitatively similar results to biochemical determination of glycosaminoglycan in developing cartilage. (c) 2005 Society of Photo-Optical Instrumentation Engineers.
Kim M; Bi X H; Horton W E; Spencer R G; Camacho N P
Journal of Biomedical Optics
2005
2005-05
Journal Article or Conference Abstract Publication
<a href="http://doi.org/10.1117/1.1922329" target="_blank" rel="noreferrer noopener">10.1117/1.1922329</a>
STEREOPHOTOGRAMMETRIC METHOD FOR BREAST-CANCER DETECTION
Optics; Spectroscopy
Sheffer D B; Herron R E; Morek W M; Proiettiorlandi F; Loughry C W; Hamor R H; Liebelt R A; Varga R S
Proceedings of the Society of Photo-Optical Instrumentation Engineers
1983
1983
Journal Article
n/a