Limits...
Label-free blood serum detection by using surface-enhanced Raman spectroscopy and support vector machine for the preoperative diagnosis of parotid gland tumors.

Yan B, Li B, Wen Z, Luo X, Xue L, Li L - BMC Cancer (2015)

Bottom Line: When the leave-one-sample-out method was used, support vector machine (SVM) played an outstanding performance in the classification of the SERS spectra with the high accuracy (84.1 % ~ 88.3 %), sensitivity (82.2 % ~ 97.4 %) and specificity (73.7 % ~ 86.7 %).However, different cross validaiton methods could effect the accuracy and a further study involing a great number of samples should be needed.And the internal relation between the spectra and patients should be established in the further study.

View Article: PubMed Central - PubMed

Affiliation: Department of Otolaryngology Head and Neck Surgery, the First Affiliated Hosipital of Xiamen University, Xiamen, China.

ABSTRACT

Background: It is difficult for the parotid gland neoplasms to make an accurate preoperative diagnosis due to the restriction of biopsy in the parotid gland neoplasms. The aim of this study is to apply the surface-enhanced Raman spectroscopy (SERS) method for the blood serum biochemical detection and use the support vector machine for the analysis in order to develop a simple but accurate blood serum detection for preoperative diagnosis of the parotid gland neoplasms.

Methods: The blood serums were collected from four groups: the patients with pleomorphic adenoma, the patients with Warthin's tumor, the patients with mucoepidermoid carcinoma and the volunteers without parotid gland neoplasms. Au nanoparticles (Au NPs) were mixed with the blood serum as the SERS active nanosensor to enhance the Raman scattering signals produced by the various biochemical materials and high quality SERS spectrum were obtained by using the Raman microscope system. Then the support vector machine was utilized to analyze the differences of the SERS spectrum from the blood serum of different groups and established a diagnostic model to discriminate the different groups.

Results: It was demonstrated that there were different intensities of SERS peaks assigned to various biochemical changes in the blood serum between the parotid gland tumor groups and normal control group. Compared with the SERS spectra of the normal serums, the intensities of peaks assigned to nucleic acids and proteins increased in the SERS spectra of the parotid gland tumor serums, which manifested the differences of the biochemical metabolites in the serum from the patients with parotid gland tumors. When the leave-one-sample-out method was used, support vector machine (SVM) played an outstanding performance in the classification of the SERS spectra with the high accuracy (84.1 % ~ 88.3 %), sensitivity (82.2 % ~ 97.4 %) and specificity (73.7 % ~ 86.7 %). Though the accuracy, sensitivity and specificity decreased in the leave-one-patient-out cross validation, the mucoepidermoid carcinoma was still easier to diagnose than other tumors.

Discussion: The specific molecular differences of parotid gland tumors and normal serums were significantly demonstrated through the comparison between the various SERS spectra.But compared with the serum SERS spectra reported in the other studies, some differences exist between the spectra in this study and the ones reported in the lietratures. These differences may result from the various nano-particles, the different preparation of serum and equipment parameters, and we could need a further research to find an exact explanation.Based on the SERS spectra of the serum samples, SVM have shown a giant potential to diagnose the parotid gland tumors in our preliminary study. However, different cross validaiton methods could effect the accuracy and a further study involing a great number of samples should be needed.

Conclusions: This exploratory research demonstrated the great potential of SERS combined with SVM into a non-invasive clinical diagnostic method for preoperative diagnosis of parotid gland tumors. And the internal relation between the spectra and patients should be established in the further study.

No MeSH data available.


Related in: MedlinePlus

a Comparison of the PA and normal group. b Comparison of the WT and normal group. c Comparison of the MEC and normal group
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4595250&req=5

Fig3: a Comparison of the PA and normal group. b Comparison of the WT and normal group. c Comparison of the MEC and normal group

Mentions: After the SERS measurement, a total of 454 SERS spectra were obtained successfully from the 91 serum samples, including 101 spectra of PA samples, 105 spectra of WT samples, 95 spectra of MEC samples and 153 spectra of normal samples. The mean SERS spectra of different samples before the spectral normalization were shown in the Fig. 2. Then compared with the normalized mean SERS spectra of the normal groups, the PA groups showed the increase in the peaks at 548, 724, 747, 933, 1094, 1328, 1371, 1445, 1698 cm−1 but the decrease in the peaks at 295, 1551, 1607 cm−1, which was shown in the subtracted spectrum in Fig. 3a. There were also differences in the mean SERS spectra between the normal groups and the WT groups, the subtracted spectra in Fig. 3b showed the increase in the peaks at 296, 450, 543, 727, 744, 1084, 1140, 1264, 1326, 1373, 1444 and 1699 cm−1 but the only decrease in the peak at 1548 cm−1. The subtracted spectrum from the MEC and normal groups showed the increase in the peaks at 548, 723, 934, 1127, 1329, 1368 and 1441 cm−1 but the decrease in the peaks at 292, 1261, 1541 and 1607 cm−1, which was shown in the Fig. 3c. All these peaks can be assigned to different biochemical components and molecular structures such as nucleic acids and proteins, and in order to better understand the different peaks in the subtracted spectra, Table. 2 lists the characteristic assignments of peaks at different Raman shifts based on the previous literatures and studies. In the parotid tumors groups, compared with the normal groups, the intensities of peaks at the 720–750 cm−1 and 900–1450 cm−1 regions increased, which were assigned to the molecular structures in the nucleic acids, proteins and lipids, but the intensities of peaks at the around 1500–1600 cm−1 region decreased, which were assigned to some special molecular bond or vibration. The assignments of major peaks can be shown in Table 2. And based on these differences of peaks, the spectra of different tumors and normal groups can be classified and diagnosed.Fig. 2


Label-free blood serum detection by using surface-enhanced Raman spectroscopy and support vector machine for the preoperative diagnosis of parotid gland tumors.

Yan B, Li B, Wen Z, Luo X, Xue L, Li L - BMC Cancer (2015)

a Comparison of the PA and normal group. b Comparison of the WT and normal group. c Comparison of the MEC and normal group
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4595250&req=5

Fig3: a Comparison of the PA and normal group. b Comparison of the WT and normal group. c Comparison of the MEC and normal group
Mentions: After the SERS measurement, a total of 454 SERS spectra were obtained successfully from the 91 serum samples, including 101 spectra of PA samples, 105 spectra of WT samples, 95 spectra of MEC samples and 153 spectra of normal samples. The mean SERS spectra of different samples before the spectral normalization were shown in the Fig. 2. Then compared with the normalized mean SERS spectra of the normal groups, the PA groups showed the increase in the peaks at 548, 724, 747, 933, 1094, 1328, 1371, 1445, 1698 cm−1 but the decrease in the peaks at 295, 1551, 1607 cm−1, which was shown in the subtracted spectrum in Fig. 3a. There were also differences in the mean SERS spectra between the normal groups and the WT groups, the subtracted spectra in Fig. 3b showed the increase in the peaks at 296, 450, 543, 727, 744, 1084, 1140, 1264, 1326, 1373, 1444 and 1699 cm−1 but the only decrease in the peak at 1548 cm−1. The subtracted spectrum from the MEC and normal groups showed the increase in the peaks at 548, 723, 934, 1127, 1329, 1368 and 1441 cm−1 but the decrease in the peaks at 292, 1261, 1541 and 1607 cm−1, which was shown in the Fig. 3c. All these peaks can be assigned to different biochemical components and molecular structures such as nucleic acids and proteins, and in order to better understand the different peaks in the subtracted spectra, Table. 2 lists the characteristic assignments of peaks at different Raman shifts based on the previous literatures and studies. In the parotid tumors groups, compared with the normal groups, the intensities of peaks at the 720–750 cm−1 and 900–1450 cm−1 regions increased, which were assigned to the molecular structures in the nucleic acids, proteins and lipids, but the intensities of peaks at the around 1500–1600 cm−1 region decreased, which were assigned to some special molecular bond or vibration. The assignments of major peaks can be shown in Table 2. And based on these differences of peaks, the spectra of different tumors and normal groups can be classified and diagnosed.Fig. 2

Bottom Line: When the leave-one-sample-out method was used, support vector machine (SVM) played an outstanding performance in the classification of the SERS spectra with the high accuracy (84.1 % ~ 88.3 %), sensitivity (82.2 % ~ 97.4 %) and specificity (73.7 % ~ 86.7 %).However, different cross validaiton methods could effect the accuracy and a further study involing a great number of samples should be needed.And the internal relation between the spectra and patients should be established in the further study.

View Article: PubMed Central - PubMed

Affiliation: Department of Otolaryngology Head and Neck Surgery, the First Affiliated Hosipital of Xiamen University, Xiamen, China.

ABSTRACT

Background: It is difficult for the parotid gland neoplasms to make an accurate preoperative diagnosis due to the restriction of biopsy in the parotid gland neoplasms. The aim of this study is to apply the surface-enhanced Raman spectroscopy (SERS) method for the blood serum biochemical detection and use the support vector machine for the analysis in order to develop a simple but accurate blood serum detection for preoperative diagnosis of the parotid gland neoplasms.

Methods: The blood serums were collected from four groups: the patients with pleomorphic adenoma, the patients with Warthin's tumor, the patients with mucoepidermoid carcinoma and the volunteers without parotid gland neoplasms. Au nanoparticles (Au NPs) were mixed with the blood serum as the SERS active nanosensor to enhance the Raman scattering signals produced by the various biochemical materials and high quality SERS spectrum were obtained by using the Raman microscope system. Then the support vector machine was utilized to analyze the differences of the SERS spectrum from the blood serum of different groups and established a diagnostic model to discriminate the different groups.

Results: It was demonstrated that there were different intensities of SERS peaks assigned to various biochemical changes in the blood serum between the parotid gland tumor groups and normal control group. Compared with the SERS spectra of the normal serums, the intensities of peaks assigned to nucleic acids and proteins increased in the SERS spectra of the parotid gland tumor serums, which manifested the differences of the biochemical metabolites in the serum from the patients with parotid gland tumors. When the leave-one-sample-out method was used, support vector machine (SVM) played an outstanding performance in the classification of the SERS spectra with the high accuracy (84.1 % ~ 88.3 %), sensitivity (82.2 % ~ 97.4 %) and specificity (73.7 % ~ 86.7 %). Though the accuracy, sensitivity and specificity decreased in the leave-one-patient-out cross validation, the mucoepidermoid carcinoma was still easier to diagnose than other tumors.

Discussion: The specific molecular differences of parotid gland tumors and normal serums were significantly demonstrated through the comparison between the various SERS spectra.But compared with the serum SERS spectra reported in the other studies, some differences exist between the spectra in this study and the ones reported in the lietratures. These differences may result from the various nano-particles, the different preparation of serum and equipment parameters, and we could need a further research to find an exact explanation.Based on the SERS spectra of the serum samples, SVM have shown a giant potential to diagnose the parotid gland tumors in our preliminary study. However, different cross validaiton methods could effect the accuracy and a further study involing a great number of samples should be needed.

Conclusions: This exploratory research demonstrated the great potential of SERS combined with SVM into a non-invasive clinical diagnostic method for preoperative diagnosis of parotid gland tumors. And the internal relation between the spectra and patients should be established in the further study.

No MeSH data available.


Related in: MedlinePlus