A constituent-based preprocessing approach for characterising cartilage using NIR absorbance measurements

Cameron P. Brown, Minsi Chen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Near-infrared spectroscopy is a widely adopted technique for characterising biological tissues. The high dimensionality of spectral data, however, presents a major challenge for analysis. Here, we present a second-derivative Beer's law-based technique aimed at projecting spectral data onto a lower dimension feature space characterised by the constituents of the target tissue type. This is intended as a preprocessing step to provide a physically-based, low dimensionality input to predictive models. Testing the proposed technique on an experimental set of 145 bovine cartilage samples before and after enzymatic degradation, produced a clear visual separation between the normal and degraded groups. Reduced proteoglycan and collagen concentrations, and increased water concentrations were predicted by simple linear fitting following degradation (all $p\ll 0.05$). Classification accuracy using the Mahalanobis distance was $\gt 98\%$ between these groups.
LanguageEnglish
Article number017002
Number of pages5
JournalBiomedical Physics and Engineering Express
Volume2
Issue number1
DOIs
Publication statusPublished - 18 Jan 2016
Externally publishedYes

Fingerprint

Cartilage
Near-Infrared Spectroscopy
Proteoglycans
Collagen
Water

Cite this

@article{806c0ac370c544258ddc09768711d544,
title = "A constituent-based preprocessing approach for characterising cartilage using NIR absorbance measurements",
abstract = "Near-infrared spectroscopy is a widely adopted technique for characterising biological tissues. The high dimensionality of spectral data, however, presents a major challenge for analysis. Here, we present a second-derivative Beer's law-based technique aimed at projecting spectral data onto a lower dimension feature space characterised by the constituents of the target tissue type. This is intended as a preprocessing step to provide a physically-based, low dimensionality input to predictive models. Testing the proposed technique on an experimental set of 145 bovine cartilage samples before and after enzymatic degradation, produced a clear visual separation between the normal and degraded groups. Reduced proteoglycan and collagen concentrations, and increased water concentrations were predicted by simple linear fitting following degradation (all $p\ll 0.05$). Classification accuracy using the Mahalanobis distance was $\gt 98\{\%}$ between these groups.",
keywords = "cartilage, near infrared spectroscopy, osteoarthritis",
author = "Brown, {Cameron P.} and Minsi Chen",
year = "2016",
month = "1",
day = "18",
doi = "10.1088/2057-1976/2/1/017002",
language = "English",
volume = "2",
journal = "Biomedical Physics and Engineering Express",
issn = "2057-1976",
publisher = "IOP Publishing Ltd.",
number = "1",

}

A constituent-based preprocessing approach for characterising cartilage using NIR absorbance measurements. / Brown, Cameron P.; Chen, Minsi.

In: Biomedical Physics and Engineering Express, Vol. 2, No. 1, 017002, 18.01.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A constituent-based preprocessing approach for characterising cartilage using NIR absorbance measurements

AU - Brown, Cameron P.

AU - Chen, Minsi

PY - 2016/1/18

Y1 - 2016/1/18

N2 - Near-infrared spectroscopy is a widely adopted technique for characterising biological tissues. The high dimensionality of spectral data, however, presents a major challenge for analysis. Here, we present a second-derivative Beer's law-based technique aimed at projecting spectral data onto a lower dimension feature space characterised by the constituents of the target tissue type. This is intended as a preprocessing step to provide a physically-based, low dimensionality input to predictive models. Testing the proposed technique on an experimental set of 145 bovine cartilage samples before and after enzymatic degradation, produced a clear visual separation between the normal and degraded groups. Reduced proteoglycan and collagen concentrations, and increased water concentrations were predicted by simple linear fitting following degradation (all $p\ll 0.05$). Classification accuracy using the Mahalanobis distance was $\gt 98\%$ between these groups.

AB - Near-infrared spectroscopy is a widely adopted technique for characterising biological tissues. The high dimensionality of spectral data, however, presents a major challenge for analysis. Here, we present a second-derivative Beer's law-based technique aimed at projecting spectral data onto a lower dimension feature space characterised by the constituents of the target tissue type. This is intended as a preprocessing step to provide a physically-based, low dimensionality input to predictive models. Testing the proposed technique on an experimental set of 145 bovine cartilage samples before and after enzymatic degradation, produced a clear visual separation between the normal and degraded groups. Reduced proteoglycan and collagen concentrations, and increased water concentrations were predicted by simple linear fitting following degradation (all $p\ll 0.05$). Classification accuracy using the Mahalanobis distance was $\gt 98\%$ between these groups.

KW - cartilage

KW - near infrared spectroscopy

KW - osteoarthritis

U2 - 10.1088/2057-1976/2/1/017002

DO - 10.1088/2057-1976/2/1/017002

M3 - Article

VL - 2

JO - Biomedical Physics and Engineering Express

T2 - Biomedical Physics and Engineering Express

JF - Biomedical Physics and Engineering Express

SN - 2057-1976

IS - 1

M1 - 017002

ER -