The technology of laser-induced auto-fluorescence spectroscopy was used on serum for the diagnosis of lung cancer. We
use principal component analysis and discriminant analysis to analyze spectra, and got an accuracy of 88% in
distinguishing lung cancer patients and healthy people.
Raman spectroscopy of tissues has been widely studied for the diagnosis of various cancers, but biofluids were seldom
used as the analyte because of the low concentration. Herein, serum of 30 normal people, 46 colon cancer, and 44 rectum
cancer patients were measured Raman spectra and analyzed. The information of Raman peaks (intensity and width) and
that of the fluorescence background (baseline function coefficients) were selected as parameters for statistical analysis.
Principal component regression (PCR) and partial least square regression (PLSR) were used on the selected parameters
separately to see the performance of the parameters. PCR performed better than PLSR in our spectral data. Then linear
discriminant analysis (LDA) was used on the principal components (PCs) of the two regression method on the selected
parameters, and a diagnostic accuracy of 88% and 83% were obtained. The conclusion is that the selected features can
maintain the information of original spectra well and Raman spectroscopy of serum has the potential for the diagnosis of
Surface enhanced Raman spectroscopy (SERS) has shown the advantage of detecting low concentration biofluids
presently. Saliva SERS of 21 lung cancer patients and 22 normal people were measured and differentiated in this paper.
Intensities of most peaks of lung cancer patients are weaker than that of normal people, some are stronger but with a
small change rate. Those peaks were assigned to proteins and nucleic acids which indicate a corresponding decrease of
substance in saliva. Principal component analysis (PCA) and linear discriminant analysis (LDA) were used to deduce
and discriminate the two groups of data, resulted in accuracy, sensitivity, and specificity being 84%, 94%, and 81%,
respectively. In conclusion, SERS of saliva has the ability of predicting lung cancer.
In this paper, 514.5nm argon ion laser induced human serum Raman and auto-fluorescence spectra of normal, liver
cirrhosis and liver cancer were measured and analyzed. The spectral differences between these three types of serums
were observed and given brief explanations. Three parameters α, φ and Δλ were introduced to describe characteristics of
each type of spectrum. Experimental results showed that these parameters might be applicable for discrimination of
normal, liver cirrhosis and liver cancer, which will provide some reference values to explore the method of laser spectral
diagnosis of cancer.
In this paper, Raman spectra of human serum were measured using Raman spectroscopy, then the spectra was analyzed
by multivariate statistical methods of principal component analysis (PCA). Then linear discriminant analysis (LDA) was
utilized to differentiate the loading score of different diseases as the diagnosing algorithm. Artificial neural network
(ANN) was used for cross-validation. The diagnosis sensitivity and specificity by PCA-LDA are 88% and 79%, while
that of the PCA-ANN are 89% and 95%. It can be seen that modern analyzing method is a useful tool for the analysis of
serum spectra for diagnosing diseases.