Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models

Near-infrared (NIR) spectroscopy technique offers many potential advantages as tool for biomedical analysis since it enables the subtle biochemical signatures related to pathology to be detected and extracted. In conjunction with advanced chemometrics, NIR spectroscopy opens the possibility of their...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Chen, Zan Lin, Chao Tan
Format: Article
Language:English
Published: Wiley 2015-01-01
Series:Journal of Chemistry
Online Access:http://dx.doi.org/10.1155/2015/619685
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173610219536384
author Hui Chen
Zan Lin
Chao Tan
author_facet Hui Chen
Zan Lin
Chao Tan
author_sort Hui Chen
collection DOAJ
description Near-infrared (NIR) spectroscopy technique offers many potential advantages as tool for biomedical analysis since it enables the subtle biochemical signatures related to pathology to be detected and extracted. In conjunction with advanced chemometrics, NIR spectroscopy opens the possibility of their use in cancer diagnosis. The study focuses on the application of near-infrared (NIR) spectroscopy and classification models for discriminating colorectal cancer. A total of 107 surgical specimens and a corresponding NIR diffuse reflection spectral dataset were prepared. Three preprocessing methods were attempted and least-squares support vector machine (LS-SVM) was used to build a classification model. The hybrid preprocessing of first derivative and principal component analysis (PCA) resulted in the best LS-SVM model with the sensitivity and specificity of 0.96 and 0.96 for the training and 0.94 and 0.96 for test sets, respectively. The similarity performance on both subsets indicated that overfitting did not occur, assuring the robustness and reliability of the developed LS-SVM model. The area of receiver operating characteristic (ROC) curve was 0.99, demonstrating once again the high prediction power of the model. The result confirms the applicability of the combination of NIR spectroscopy, LS-SVM, PCA, and first derivative preprocessing for cancer diagnosis.
format Article
id doaj-art-cbcffd2a8d0c48d181c2d08a0ff2fa76
institution OA Journals
issn 2090-9063
2090-9071
language English
publishDate 2015-01-01
publisher Wiley
record_format Article
series Journal of Chemistry
spelling doaj-art-cbcffd2a8d0c48d181c2d08a0ff2fa762025-08-20T02:19:48ZengWileyJournal of Chemistry2090-90632090-90712015-01-01201510.1155/2015/619685619685Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric ModelsHui Chen0Zan Lin1Chao Tan2Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, ChinaKey Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, ChinaKey Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, ChinaNear-infrared (NIR) spectroscopy technique offers many potential advantages as tool for biomedical analysis since it enables the subtle biochemical signatures related to pathology to be detected and extracted. In conjunction with advanced chemometrics, NIR spectroscopy opens the possibility of their use in cancer diagnosis. The study focuses on the application of near-infrared (NIR) spectroscopy and classification models for discriminating colorectal cancer. A total of 107 surgical specimens and a corresponding NIR diffuse reflection spectral dataset were prepared. Three preprocessing methods were attempted and least-squares support vector machine (LS-SVM) was used to build a classification model. The hybrid preprocessing of first derivative and principal component analysis (PCA) resulted in the best LS-SVM model with the sensitivity and specificity of 0.96 and 0.96 for the training and 0.94 and 0.96 for test sets, respectively. The similarity performance on both subsets indicated that overfitting did not occur, assuring the robustness and reliability of the developed LS-SVM model. The area of receiver operating characteristic (ROC) curve was 0.99, demonstrating once again the high prediction power of the model. The result confirms the applicability of the combination of NIR spectroscopy, LS-SVM, PCA, and first derivative preprocessing for cancer diagnosis.http://dx.doi.org/10.1155/2015/619685
spellingShingle Hui Chen
Zan Lin
Chao Tan
Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models
Journal of Chemistry
title Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models
title_full Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models
title_fullStr Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models
title_full_unstemmed Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models
title_short Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models
title_sort cancer discrimination using fourier transform near infrared spectroscopy with chemometric models
url http://dx.doi.org/10.1155/2015/619685
work_keys_str_mv AT huichen cancerdiscriminationusingfouriertransformnearinfraredspectroscopywithchemometricmodels
AT zanlin cancerdiscriminationusingfouriertransformnearinfraredspectroscopywithchemometricmodels
AT chaotan cancerdiscriminationusingfouriertransformnearinfraredspectroscopywithchemometricmodels