Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method

Yan Wu Chu, Feng Chen, Yun Tang, Tong Chen, Yun Xin Yu, Hong Lin Jin, Lian Bo Guo, Yong Feng Lu, Xiao Yan Zeng

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Diagnosing nasopharyngeal carcinoma (NPC) is a significant challenge because of the highly complex process. We proposed an approach to diagnose NPC serum using a combination of hyperspectral imaging and weight-based principal component analysis. Samples were prepared by pressing boric acid into pellets for use as the sera substrate. The sera, collected from 100 healthy volunteers and 60 NPC patients, was dripped onto the surface of the substrate for hyperspectral imaging. The characteristic spectral bands were selected based on the variable weight obtained from a support vector machine (SVM) model, using principal component analysis (PCA) to reduce the dimension in the extracted bands. Obtained results show that the accuracy rate, sensitivity, and specificity between the NPC sera and the sera of the healthy controls reached extremely high levels of 99.15%, 98.79%, and 99.36%, respectively. For the model's consistency evaluation, we found that the Kappa and area under the curve (AUC) of the receiver operating characteristic (ROC) curve were 0.99 and 0.98, respectively. These results suggest that the developed approach could serve as a noninvasive diagnostic and screening tool for highly accurate and consistent detection of NPC. Hence, a combination of hyperspectral imaging (HSI) and a weighted principal component analysis (WPCA)-SVM model represents a powerful and promising tool for NPC diagnosis.

Original languageEnglish (US)
Pages (from-to)28661-28671
Number of pages11
JournalOptics Express
Volume26
Issue number22
DOIs
StatePublished - Oct 29 2018

Fingerprint

serums
cancer
principal components analysis
boric acids
curves
pressing
spectral bands
pellets
screening
receivers
evaluation
sensitivity

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Chu, Y. W., Chen, F., Tang, Y., Chen, T., Yu, Y. X., Jin, H. L., ... Zeng, X. Y. (2018). Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method. Optics Express, 26(22), 28661-28671. https://doi.org/10.1364/OE.26.028661

Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method. / Chu, Yan Wu; Chen, Feng; Tang, Yun; Chen, Tong; Yu, Yun Xin; Jin, Hong Lin; Guo, Lian Bo; Lu, Yong Feng; Zeng, Xiao Yan.

In: Optics Express, Vol. 26, No. 22, 29.10.2018, p. 28661-28671.

Research output: Contribution to journalArticle

Chu, YW, Chen, F, Tang, Y, Chen, T, Yu, YX, Jin, HL, Guo, LB, Lu, YF & Zeng, XY 2018, 'Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method', Optics Express, vol. 26, no. 22, pp. 28661-28671. https://doi.org/10.1364/OE.26.028661
Chu, Yan Wu ; Chen, Feng ; Tang, Yun ; Chen, Tong ; Yu, Yun Xin ; Jin, Hong Lin ; Guo, Lian Bo ; Lu, Yong Feng ; Zeng, Xiao Yan. / Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method. In: Optics Express. 2018 ; Vol. 26, No. 22. pp. 28661-28671.
@article{070254dbe07a4a059f7b767f3546dca7,
title = "Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method",
abstract = "Diagnosing nasopharyngeal carcinoma (NPC) is a significant challenge because of the highly complex process. We proposed an approach to diagnose NPC serum using a combination of hyperspectral imaging and weight-based principal component analysis. Samples were prepared by pressing boric acid into pellets for use as the sera substrate. The sera, collected from 100 healthy volunteers and 60 NPC patients, was dripped onto the surface of the substrate for hyperspectral imaging. The characteristic spectral bands were selected based on the variable weight obtained from a support vector machine (SVM) model, using principal component analysis (PCA) to reduce the dimension in the extracted bands. Obtained results show that the accuracy rate, sensitivity, and specificity between the NPC sera and the sera of the healthy controls reached extremely high levels of 99.15{\%}, 98.79{\%}, and 99.36{\%}, respectively. For the model's consistency evaluation, we found that the Kappa and area under the curve (AUC) of the receiver operating characteristic (ROC) curve were 0.99 and 0.98, respectively. These results suggest that the developed approach could serve as a noninvasive diagnostic and screening tool for highly accurate and consistent detection of NPC. Hence, a combination of hyperspectral imaging (HSI) and a weighted principal component analysis (WPCA)-SVM model represents a powerful and promising tool for NPC diagnosis.",
author = "Chu, {Yan Wu} and Feng Chen and Yun Tang and Tong Chen and Yu, {Yun Xin} and Jin, {Hong Lin} and Guo, {Lian Bo} and Lu, {Yong Feng} and Zeng, {Xiao Yan}",
year = "2018",
month = "10",
day = "29",
doi = "10.1364/OE.26.028661",
language = "English (US)",
volume = "26",
pages = "28661--28671",
journal = "Optics Express",
issn = "1094-4087",
publisher = "The Optical Society",
number = "22",

}

TY - JOUR

T1 - Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method

AU - Chu, Yan Wu

AU - Chen, Feng

AU - Tang, Yun

AU - Chen, Tong

AU - Yu, Yun Xin

AU - Jin, Hong Lin

AU - Guo, Lian Bo

AU - Lu, Yong Feng

AU - Zeng, Xiao Yan

PY - 2018/10/29

Y1 - 2018/10/29

N2 - Diagnosing nasopharyngeal carcinoma (NPC) is a significant challenge because of the highly complex process. We proposed an approach to diagnose NPC serum using a combination of hyperspectral imaging and weight-based principal component analysis. Samples were prepared by pressing boric acid into pellets for use as the sera substrate. The sera, collected from 100 healthy volunteers and 60 NPC patients, was dripped onto the surface of the substrate for hyperspectral imaging. The characteristic spectral bands were selected based on the variable weight obtained from a support vector machine (SVM) model, using principal component analysis (PCA) to reduce the dimension in the extracted bands. Obtained results show that the accuracy rate, sensitivity, and specificity between the NPC sera and the sera of the healthy controls reached extremely high levels of 99.15%, 98.79%, and 99.36%, respectively. For the model's consistency evaluation, we found that the Kappa and area under the curve (AUC) of the receiver operating characteristic (ROC) curve were 0.99 and 0.98, respectively. These results suggest that the developed approach could serve as a noninvasive diagnostic and screening tool for highly accurate and consistent detection of NPC. Hence, a combination of hyperspectral imaging (HSI) and a weighted principal component analysis (WPCA)-SVM model represents a powerful and promising tool for NPC diagnosis.

AB - Diagnosing nasopharyngeal carcinoma (NPC) is a significant challenge because of the highly complex process. We proposed an approach to diagnose NPC serum using a combination of hyperspectral imaging and weight-based principal component analysis. Samples were prepared by pressing boric acid into pellets for use as the sera substrate. The sera, collected from 100 healthy volunteers and 60 NPC patients, was dripped onto the surface of the substrate for hyperspectral imaging. The characteristic spectral bands were selected based on the variable weight obtained from a support vector machine (SVM) model, using principal component analysis (PCA) to reduce the dimension in the extracted bands. Obtained results show that the accuracy rate, sensitivity, and specificity between the NPC sera and the sera of the healthy controls reached extremely high levels of 99.15%, 98.79%, and 99.36%, respectively. For the model's consistency evaluation, we found that the Kappa and area under the curve (AUC) of the receiver operating characteristic (ROC) curve were 0.99 and 0.98, respectively. These results suggest that the developed approach could serve as a noninvasive diagnostic and screening tool for highly accurate and consistent detection of NPC. Hence, a combination of hyperspectral imaging (HSI) and a weighted principal component analysis (WPCA)-SVM model represents a powerful and promising tool for NPC diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=85055785432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055785432&partnerID=8YFLogxK

U2 - 10.1364/OE.26.028661

DO - 10.1364/OE.26.028661

M3 - Article

C2 - 30470039

AN - SCOPUS:85055785432

VL - 26

SP - 28661

EP - 28671

JO - Optics Express

JF - Optics Express

SN - 1094-4087

IS - 22

ER -