Preprocessing Strategies for Sparse Infrared Spectroscopy: A Case Study on Cartilage Diagnostics

Abstract

The aim of the study was to optimize preprocessing of sparse infrared spectral data. The sparse data were obtained by reducing broadband Fourier transform infrared attenuated total reflectance spectra of bovine and human cartilage, as well as of simulated spectral data, comprising several thousand spectral variables into datasets comprising only seven spectral variables. Different preprocessing approaches were compared, including simple baseline correction and normalization procedures, and model-based preprocessing, such as multiplicative signal correction (MSC). The optimal preprocessing was selected based on the quality of classification models established by partial least squares discriminant analysis for discriminating healthy and damaged cartilage samples. The best results for the sparse data were obtained by preprocessing using a baseline offset correction at 1800 cm−1, followed by peak normalization at 850cm−1 and preprocessing by MSC.

Infrared spectroscopy is suitable for objective assessment of articular cartilage health

“…The remaining 1,024 spectra were included in further analysis. Pre-processing by weighted multiplicative signal correction (MSC) [ 19 , 20 ] was applied. Regions of 1800–1780 ​cm −1 and 900-800 ​cm −1 were up-weighted by 15 to mitigate baseline effects.…”

The Use of Constituent Spectra and Weighting in Extended Multiplicative Signal Correction in Infrared Spectroscopy

“…For ATR spectra, there are often little signs of baseline variations since scattering does not take place in contact reflection measurements. Therefore, an EMSC with only a constant baseline (MSC) is sufficient for normalizing the spectra [ 21 ]. Since an estimated pure glucose spectrum is available, we add this spectrum to the EMSC model as an analyte spectrum, while the pure water spectrum serves as a reference spectrum.…”

“…The introduction is kept brief, as this topic has been covered several times elsewhere, see for example [ 11 ]. In the following, we describe infrared transmission experiments, while the EMSC model is also applicable to spectra recorded with different methods, as for example attenuated total reflectance (ATR) [ 21 ].…”

Preclassification of Broadband and Sparse Infrared Data by Multiplicative Signal Correction Approach

“…While previous ex vivo studies mostly utilized the entire mid-infrared spectrum to get qualitative and quantitative information about the chemical composition of cartilage samples [ 11 , 12 , 15 ], with QCLs only limited regions in the infrared spectral range can be measured. In the ongoing Horizon 2020 Photonics21 project MIRACLE [ 33 , 34 ], an arthroscopic IR fiber-optic probe coupled to a spectrometer operating seven MIR QCLs with fixed wavelengths is being developed [ 6 , 35 , 36 ].The goal is to use the probe as an in vivo diagnostic tool for analysing degeneracy status of articular cartilage during arthroscopy surgery.…”

“…Thus, an approach is needed that can preclassify sparse spectra into spectra with high analyte signals (cartilage spectra) and low analyte signals (water or low absorbance spectra). The aim of this paper was therefore to develop a viable approach for assessing sparse spectral data, and it was based on sparse data with the seven WNs as chosen in the Miracle project [ 33 , 34 ].…”