Limits...
Simultaneous fingerprint and high-wavenumber fiber-optic Raman spectroscopy improves in vivo diagnosis of esophageal squamous cell carcinoma at endoscopy.

Wang J, Lin K, Zheng W, Ho KY, Teh M, Yeoh KG, Huang Z - Sci Rep (2015)

Bottom Line: A total of 1172 in vivo FP/HW Raman spectra were acquired from 48 esophageal patients undergoing endoscopic examination.The total Raman dataset was split into two parts: 80% for training; while 20% for testing.Partial least squares-discriminant analysis (PLS-DA) and leave-one patient-out, cross validation (LOPCV) were implemented on training dataset to develop diagnostic algorithms for tissue classification.

View Article: PubMed Central - PubMed

Affiliation: Optical Bioimaging Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore 117576.

ABSTRACT
This work aims to evaluate clinical value of a fiber-optic Raman spectroscopy technique developed for in vivo diagnosis of esophageal squamous cell carcinoma (ESCC) during clinical endoscopy. We have developed a rapid fiber-optic Raman endoscopic system capable of simultaneously acquiring both fingerprint (FP)(800-1800 cm(-1)) and high-wavenumber (HW)(2800-3600 cm(-1)) Raman spectra from esophageal tissue in vivo. A total of 1172 in vivo FP/HW Raman spectra were acquired from 48 esophageal patients undergoing endoscopic examination. The total Raman dataset was split into two parts: 80% for training; while 20% for testing. Partial least squares-discriminant analysis (PLS-DA) and leave-one patient-out, cross validation (LOPCV) were implemented on training dataset to develop diagnostic algorithms for tissue classification. PLS-DA-LOPCV shows that simultaneous FP/HW Raman spectroscopy on training dataset provides a diagnostic sensitivity of 97.0% and specificity of 97.4% for ESCC classification. Further, the diagnostic algorithm applied to the independent testing dataset based on simultaneous FP/HW Raman technique gives a predictive diagnostic sensitivity of 92.7% and specificity of 93.6% for ESCC identification, which is superior to either FP or HW Raman technique alone. This work demonstrates that the simultaneous FP/HW fiber-optic Raman spectroscopy technique improves real-time in vivo diagnosis of esophageal neoplasia at endoscopy.

No MeSH data available.


Related in: MedlinePlus

Receiver operating characteristic (ROC) curves for separating ESCC fromnormal esophageal tissue for the training dataset (80% of the totaldataset).The areas under the ROC curves (AUC) are 0.972, 0.928 and 0.995,respectively, using the FP, HW and the integrated FP/HW Ramantechniques.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4525386&req=5

f5: Receiver operating characteristic (ROC) curves for separating ESCC fromnormal esophageal tissue for the training dataset (80% of the totaldataset).The areas under the ROC curves (AUC) are 0.972, 0.928 and 0.995,respectively, using the FP, HW and the integrated FP/HW Ramantechniques.

Mentions: Capitalizing on the complementary biochemical/biomolecular information identified inboth the FP and HW spectral ranges, PLS-DA and LOPCV are implemented on the trainingdataset (80% of the total dataset) (Fig. 1(a)) to developrobust diagnostic model for enhancing in vivo ESCC diagnosis. ACohen’s kappa of 0.91 demonstrated a high level of agreement between theindependent pathologists for the esophageal tissue groupings29. Figure 4 shows the scattered plots of cross-validated PLS-DAposterior probability of each Raman prediction for (a) FP, (b) HW, and (c)integrated FP/HW, respectively. The diagnostic accuracy with integrated FP/HW Ramanspectroscopy is 97.3% [sensitivity of 97.0% (196/202) and specificity of 97.4%(717/736)], superior to using either FP (accuracy of 90.9%, sensitivity of 93.6%(189/202), and specificity of 90.2% (664/736)) or HW (accuracy of 85.5%, sensitivityof 78.2%(158/202), and specificity of 87.5% (644/736)) Raman technique alone. Thereceiver operating characteristic (ROC) curves are also generated (Fig. 5), with the integration areas under the ROC curves of being 0.972,0.928 and 0.995, respectively, for the FP, HW and the integrated FP/HW techniques.The above results confirm that the integrated FP/HW Raman technique provides thebest diagnostic performance for in vivo ESCC detection as compared to FP orHW Raman technique.


Simultaneous fingerprint and high-wavenumber fiber-optic Raman spectroscopy improves in vivo diagnosis of esophageal squamous cell carcinoma at endoscopy.

Wang J, Lin K, Zheng W, Ho KY, Teh M, Yeoh KG, Huang Z - Sci Rep (2015)

Receiver operating characteristic (ROC) curves for separating ESCC fromnormal esophageal tissue for the training dataset (80% of the totaldataset).The areas under the ROC curves (AUC) are 0.972, 0.928 and 0.995,respectively, using the FP, HW and the integrated FP/HW Ramantechniques.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4525386&req=5

f5: Receiver operating characteristic (ROC) curves for separating ESCC fromnormal esophageal tissue for the training dataset (80% of the totaldataset).The areas under the ROC curves (AUC) are 0.972, 0.928 and 0.995,respectively, using the FP, HW and the integrated FP/HW Ramantechniques.
Mentions: Capitalizing on the complementary biochemical/biomolecular information identified inboth the FP and HW spectral ranges, PLS-DA and LOPCV are implemented on the trainingdataset (80% of the total dataset) (Fig. 1(a)) to developrobust diagnostic model for enhancing in vivo ESCC diagnosis. ACohen’s kappa of 0.91 demonstrated a high level of agreement between theindependent pathologists for the esophageal tissue groupings29. Figure 4 shows the scattered plots of cross-validated PLS-DAposterior probability of each Raman prediction for (a) FP, (b) HW, and (c)integrated FP/HW, respectively. The diagnostic accuracy with integrated FP/HW Ramanspectroscopy is 97.3% [sensitivity of 97.0% (196/202) and specificity of 97.4%(717/736)], superior to using either FP (accuracy of 90.9%, sensitivity of 93.6%(189/202), and specificity of 90.2% (664/736)) or HW (accuracy of 85.5%, sensitivityof 78.2%(158/202), and specificity of 87.5% (644/736)) Raman technique alone. Thereceiver operating characteristic (ROC) curves are also generated (Fig. 5), with the integration areas under the ROC curves of being 0.972,0.928 and 0.995, respectively, for the FP, HW and the integrated FP/HW techniques.The above results confirm that the integrated FP/HW Raman technique provides thebest diagnostic performance for in vivo ESCC detection as compared to FP orHW Raman technique.

Bottom Line: A total of 1172 in vivo FP/HW Raman spectra were acquired from 48 esophageal patients undergoing endoscopic examination.The total Raman dataset was split into two parts: 80% for training; while 20% for testing.Partial least squares-discriminant analysis (PLS-DA) and leave-one patient-out, cross validation (LOPCV) were implemented on training dataset to develop diagnostic algorithms for tissue classification.

View Article: PubMed Central - PubMed

Affiliation: Optical Bioimaging Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore 117576.

ABSTRACT
This work aims to evaluate clinical value of a fiber-optic Raman spectroscopy technique developed for in vivo diagnosis of esophageal squamous cell carcinoma (ESCC) during clinical endoscopy. We have developed a rapid fiber-optic Raman endoscopic system capable of simultaneously acquiring both fingerprint (FP)(800-1800 cm(-1)) and high-wavenumber (HW)(2800-3600 cm(-1)) Raman spectra from esophageal tissue in vivo. A total of 1172 in vivo FP/HW Raman spectra were acquired from 48 esophageal patients undergoing endoscopic examination. The total Raman dataset was split into two parts: 80% for training; while 20% for testing. Partial least squares-discriminant analysis (PLS-DA) and leave-one patient-out, cross validation (LOPCV) were implemented on training dataset to develop diagnostic algorithms for tissue classification. PLS-DA-LOPCV shows that simultaneous FP/HW Raman spectroscopy on training dataset provides a diagnostic sensitivity of 97.0% and specificity of 97.4% for ESCC classification. Further, the diagnostic algorithm applied to the independent testing dataset based on simultaneous FP/HW Raman technique gives a predictive diagnostic sensitivity of 92.7% and specificity of 93.6% for ESCC identification, which is superior to either FP or HW Raman technique alone. This work demonstrates that the simultaneous FP/HW fiber-optic Raman spectroscopy technique improves real-time in vivo diagnosis of esophageal neoplasia at endoscopy.

No MeSH data available.


Related in: MedlinePlus