Spectral Processing Methods Research Articles

NIR Hyperspectral Imaging Technology Combined with Multivariate Methods to Identify Shrimp Freshness

In this study, a hyperspectral imaging system of 866.4–1701.0 nm, combined with a variety of spectral processing methods were adopted to identify shrimp freshness. To gain the optimal model combination, three preprocessing methods (Savitzky-Golay first derivative (SG1), multivariate scatter correction (MSC), and standard normal variate (SNV)), three characteristic wavelength extraction algorithms (random frog algorithm (RFA), uninformative variables elimination (UVE), and competitive adaptive reweighted sampling (CARS)), and four discriminant models (partial least squares discrimination analysis (PLS-DA), least squares support vector machine (LSSVM), random forest (RF), and extreme learning machine (ELM)) were employed for experimental study. First of all, due to the full wavelength modeling analysis, three preprocessing methods were utilized to preprocess the original spectral data. The analysis showed that the spectral data processed by the SNV method had the best performance among the four discriminant models. Secondly, due to the characteristic wavelength modeling analysis, three characteristic wavelength extraction algorithms were utilized to extract the characteristic wavelength of the SNV-processed spectral data. It was found that the CARS algorithm achieved the best performance among the three characteristic wavelength extraction algorithms, and the combining adoption of the ELM model and different characteristic wavelength extraction algorithms obtained the best results. Therefore, the model based on SNV-CARS-ELM obtained the best performance and was elected as the optimal model. Lastly, for accurately and explicitly displaying the refrigeration days of shrimps, the original hyperspectral images of shrimps were substituted into the SNV-CARS-ELM model, thus obtaining the general classification accuracy of 97.92%, and the object-wise method was used to visualize the classification results. As a result, the method proposed in this study can effectively detect the freshness of shrimps.

Remote Compact Seismic Sensor for the Moving Person Detection

The results of the development of a remote compact seismic sensor for the detection of a moving person, as well as sensor testing, are presented in this letter. A choice of a seismic transducer and a seismic signal processing unit is justified. Characteristics of seismic signals from a moving person are analyzed, and an algorithm for the person detection is proposed. As tests have shown, the developed seismic sensor has high-level parameters, which allows it to be successfully used both for reconnaissance purposes and for a various objects guard. It is shown that such parameters can be achieved in a relatively simple device that uses temporal parameters of seismic signals without the use of complex and energy expenditure spectral, time-frequency, statistical, learning, or self-learning information processing methods.

Rapid Determination of Total Polar Compounds in Frying Oil Using ATR‐FTIR Combined with Extended Partial Least Squares Regression

AbstractA method of rapidly determining the total polar compounds (TPCs) in frying oils using attenuated total reflectance‐Fourier transform infrared spectroscopy combined with partial least squares (PLS) regression is developed. Oils of various types and geographic origins are used to ensure that the proposed model is robust. The first derivative spectrum is selected as the spectral processing method. The interval PLS, forward interval PLS, and backward interval PLS algorithms are compared in terms of their performance. A correlation coefficient (R2) of 0.9942, a root mean square error of calibration (RMSEC) of 1.1, a root mean square error of prediction (RMSEP) of 2.30, a residual predictive deviation (RPD) of 4.1, and a limit of detection (LOD) of 1.65% are obtained by the fiPLS33 model with fewer latent variables and a lower spectral interval number. In addition, sub‐models using a single type of oil showed higher performance (R2 0.9957–0.9998, RMSEC 0.12–0.92, RMSEP 0.79–1.58, RPD 4.79–9.64, LOD 0.66–1.26%) than the general model. The TPC models developed are accurate, stable, and adaptable, and they can be used to analyze general frying oil samples quickly, regardless of the oil type, and to analyze samples of specific oil types accurately.Practical applications: The content of TPCs is an important indicator of whether the oil has been overused and whether it will be harmful during the frying process. However, traditional chemical methods are time‐consuming, and they have not been used to determine large‐sized samples. In addition, due to a lack of regional optimization, most studies on determining TPCs with FTIR give unsatisfactory model performance. A general TPC model that incorporates several oil types and regional optimization is expected to improve prediction performance. Therefore, the proposed method represents a rapid and accurate tool for measuring TPCs in edible fats and oils.

Research on spectral processing methods of the carbon/oxygen spectral logging in sandstone

The inelastic spectrum-based carbon/oxygen spectral logging has been widely applied in the interpretation of residual oil saturation. The effects of traditional spectral processing methods for obtaining inelastic spectrum are influenced by salinity (including pore fluid salinity and borehole fluid salinity), clay content, porosity, etc. The interpretation accuracy thereof needs to be improved. In this paper, we proposed a new method for obtaining inelastic spectrum. To validate the new method and compare it with the traditional methods, the numerical simulation method (Monte Carlo) is used to simulate different formation models. The result shows that in addition to sandstone formation with clay, the new method improves the interpretation accuracy of oil saturation.

Regional scale prospecting for non-sulphide zinc deposits using ASTER data and different spectral processing methods

ABSTRACT The Ravar-Kuhbanan-Bahabad belt (RKBB) in Central Iran contains several carbonate-hosted non-sulphide Zn (zinc)-Pb (lead) deposits. The Gujer Zn mine area located in the middle of the RKBB was selected as the case study. Due to its large extent, dolomitic envelope in carbonate host rocks can be considered as a more appropriate exploratory target than small Zn-rich gossans or blind karst filling ore. Based on previous studies, the occurrence of red sandstone as a candidate of supplying metal for mineralization and evaporate as sulphate source for mineralized liquids in the vicinity of carbonate rocks can be important exploratory key in the RKBB. Non-sulphide Zn deposits were formed through oxidation of primary Mississippi Valley-type (MVT) deposits in the study area. Remote sensing studies were undertaken using visible to near-infrared (VNIR) and shortwave infrared (SWIR) bands of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) with the objective of lithological mapping. Five traverse lines containing a total of 81 samples were designed and followed with subsequent chemical analysis, thin section studies, and spectroscopy to verify the results. Two types of carbonates, namely, magnesian dolomite as host rock and surrounding calcitic limestone, were realized through using magnesium oxide (MgO) to calcium oxide (CaO) ratio. Based on spectroscopy studies, calcite and dolomite showed distinct absorption features at 2.35 µm and 2.32 µm, respectively, in ASTER band 8 while a shoulder at 2.25 µm was seen in ASTER band 7 for dolomite. Three image processing methods including spectral angle mapper (SAM), linear spectral unmixing (LSU), and mixture-tuned matched-filtering (MTMF) were applied to separate dolomite and limestone. The accuracy of image classification was numerically estimated using a confusion matrix. Limestone with the accuracy of 95.83% was more precisely enhanced using MTMF method compared to SAM and LSU methods. Highest accuracy of 75% for dolomite was obtained through using LSU method. Red sandstone and evaporate units were classified using MTMF and SAM/LSU methods, respectively. Rock units with the highest accuracy were selected and simply overlain on an image of ASTER in a GIS platform to create the potential map of the study area. Results showed that ASTER data can be successfully used to prepare a potential map for regional scale prospecting for carbonate-hosted non-sulphide Zn-Pb deposits in geological setting and climate condition similar to the RKBB.

Mapping changes in sarcoplasmatic and myofibrillar proteins in boiled pork using hyperspectral imaging with spectral processing methods

Hyperspectral imaging technology was investigated to examine the changes of sarcoplasmatic and myofibrillar proteins contents in boiled pork. Different spectral pre-processing methods were employed to improve the partial least squares regression (PLSR) models. Seven optimal wavelengths in the region of 400–2000 nm without spectral pre-processing were used to build the best PLSR model for predicting the sarcoplasmatic proteins contents with R2p of 0.9185 and RMSEP of 2.50 mg/g. Based on multiplicative scatter correction (MSC) method, eight wavelengths in the region of 400–1000 nm were also selected to construct the best predictive PLSR model for myofibrillar protein contents with R2p of 0.9161 and RMSEP of 2.71 mg/g. The changes in sarcoplasmatic and myofibrillar proteins contents of boiled pork during different cooking periods were successfully visualized.

Near real-time enumeration of live and dead bacteria using a fibre-based spectroscopic device

A rapid, cost-effective and easy method that allows on-site determination of the concentration of live and dead bacterial cells using a fibre-based spectroscopic device (the optrode system) is proposed and demonstrated. Identification of live and dead bacteria was achieved by using the commercially available dyes SYTO 9 and propidium iodide, and fluorescence spectra were measured by the optrode. Three spectral processing methods were evaluated for their effectiveness in predicting the original bacterial concentration in the samples: principal components regression (PCR), partial least squares regression (PLSR) and support vector regression (SVR). Without any sample pre-concentration, PCR achieved the most reliable results. It was able to quantify live bacteria from 108 down to 106.2 bacteria/mL and showed the potential to detect as low as 105.7 bacteria/mL. Meanwhile, enumeration of dead bacteria using PCR was achieved between 108 and 107 bacteria/mL. The general procedures described in this article can be applied or modified for the enumeration of bacteria within populations stained with fluorescent dyes. The optrode is a promising device for the enumeration of live and dead bacterial populations particularly where rapid, on-site measurement and analysis is required.

Analysis of broadening mechanism of ionospheric echo spectrum and spectrum sharpening method

High-frequency sky wave detection equipment must rely on the ionosphere as the propagation medium in the early warning and sea state remote sensing tasks. The ionosphere is time-varying and unstable, which will change the characteristics of the high-frequency electromagnetic wave propagating through it, resulting in the broadening of the echo spectrum, thus seriously affecting the detection of targets and the inversion of sea state parameters. The reason and mechanism of the echo spectrum expansion are analyzed in detail from the dispersion effect, phase contamination and multimode propagation. The bandwidth of the dispersion effect is different from that of the high frequency detection equipment. When the bandwidth of the sky wave equipment is 3–30 MHz, the bandwidths of the dispersion effect are 41.6–57.4 kHz and 0.17–10.8 MHz. The multi-quasi-parabolic ionospheric model is used to discuss the frequency selection measures to avoid multimode propagation. The modulation process of ionospheric contamination to echo is studied theoretically. It is shown that the non-linear phase contamination will cause the energy of echo to diffuse in frequency domain and to be unable to accumulate. To solve the problem of phase contamination which is difficult to solve in practice, a contamination correction method without estimating the instantaneous frequency of the echo is proposed. In the method the consistency principle of signal subspace and signal frequency vector expansion space is used, and therefore the phase contamination term can be well estimated. Based on the real data, the contamination correction results from the proposed method, phase gradient autofocus method, maximum entropy spectral analysis method and time-frequency processing method are given. The results show that the new method is a better method and can effectively sharpen the broadened echo spectrum.

Identification of Bacteria by Surface-Enhanced Raman Spectra after Peroxide Treatment

Surface-enhanced Raman spectroscopy (SERS) is a prospective method for the detection and identification of microorganisms. Hereby we describe the method for the registration of bacterial SERS spectra, including the mild oxidation sample treatment for the additional amplification of SERS signal. We also propose the spectral data processing method for the calculation of distinguishing criteria for the bacterial spectra.

Estimating soil texture from vis–NIR spectra

SummaryVis–NIR spectroscopy is a low‐cost method for proximal soil sensing, enabling rapid analysis of soil texture as an alternative to more laborious analytical methods. In this study we used partial least squares regression (PLSR) and random forest (RF) models trained on vis–NIR spectra of 173 soil samples from across Germany to estimate soil sand (63–2000 µm), silt (2–63 µm) and clay (< 2 µm) contents. Models were trained with different spectral processing methods. Texture was also estimated by averaging results across different models and by calculating each fraction as the difference from 100% of the sum of the other fractions. The PLSR models predicted clay and sand best, whereas RF performed better for predicting silt fractions. Spectral processing did not improve clay predictions, but standardized normal variate spectra predicted the silt fraction best, and log‐inverse spectra improved modelling of the sand fraction. The best models explained > 90% of variance in the evaluation samples of the textural fractions. Residual prediction deviations were > 3 for all fractions, which together with good accuracy indicated excellent model performance. Model averaging across the top three performing models improved the predictive performance of all fractions. Calculating each fraction from the sum of the other two fractions predicted only the sand fraction well, but increased model bias. In addition, we evaluated the models for their reliability at predicting the cumulative sum of the three fractions for samples of unknown textural composition (n = 1186). In a novel approach, we identified poorly predicted samples by propagating errors from the model uncertainties for the individual soil fractions, namely those samples whose cumulative sum lies outside the range covered by 100% ± propagated error from the three fractions. This new method provides the opportunity to optimize analyses efficiently because these samples can be prioritized and used to check and update the models.Highlights Partial least squares regression and random forest models of vis–NIR spectra predict soil texture reliably. Cumulative sums of independently predicted fractions enabled error estimation. Error propagation allowed robust classification of the whole soil texture. Error propagation identified poorly predicted samples, optimizing laboratory resources.

Research on the spectral phase correction method for the atmospheric detection in open space.

During the atmospheric detection process in open space, the excessive phase noise is introduced into the signal, due to the atmospheric turbulence, which causes the intensity and phase fluctuation. In the previous study, a spectral data processing method based on the co-frequency and dual-wave has been used to reduce the influence of the scintillation noise from the atmospheric turbulence in open space, while the influence of the phase noise remains to be solved. So the wavelength modulated signal is theoretically analyzed at first. On studying the relationship between the dual-waves in one cycle to eliminate the phase fluctuation and reduce the phase fluctuation caused by the atmospheric turbulence, a new method of the spectral phase correction for the open space atmospheric detection has been proposed. An atmospheric detection experiment on the phase correction in the open space based on co-frequency and dual-wave has been carried out. The results show that the maximum fluctuation of the spectral signal processed with this method is 1.06%, while the power spectral density fluctuation is suppressed below 50Hz, and the Allan analysis result is 8.8 × 10-8(1s). Compared with the traditional concentration inversion method using 2f-wavelength modulation and the classical light intensity elimination, the proposed phase correction method can effectively reduce the fluctuation of random noise caused by the short-term atmospheric turbulence and the laser flashing to improve the stability of the concentration measurement, which has practical engineering value.

Spectral Characterization and Molecular Dynamics Simulation of Pesticides Based on Terahertz Time-Domain Spectra Analyses and Density Functional Theory (DFT) Calculations.

This work provides the experimental and theoretical fundamentals for detecting the molecular fingerprints of six kinds of pesticides by using terahertz (THz) time-domain spectroscopy (THz-TDS). The spectra of absorption coefficient and refractive index of the pesticides, chlorpyrifos, fipronil, carbofuran, dimethoate, methomyl, and thidiazuron are obtained in frequencies of 0.1–3.5 THz. To accurately describe the THz spectral characteristics of pesticides, the wavelet threshold de-noising (WTD) method with db 5 wavelet fucntion, 5-layer decomposition, and soft-threshold de-noising was used to eliminate the spectral noise. The spectral baseline correction (SBC) method based on asymmetric least squares smoothing was used to remove the baseline drift. Spectral results show that chlorpyrifo had three characteristic absorption peaks at 1.47, 1.93, and 2.73 THz. Fipronil showed three peaks at 0.76, 1.23, and 2.31 THz. Carbofuran showed two peaks at 2.72 and 3.06 THz. Dimethoate showed three peaks at 1.05, 1.89, and 2.92 THz. Methomyl showed five peaks at 1.01, 1.65, 1.91, 2.72, and 3.20 THz. Thidiazuron showed four peaks at 0.99, 1.57, 2.17, and 2.66 THz. The density functional theory (DFT) of B3LYP/6-31G+(d,p) was applied to simulate the molecular dynamics for peak analyzing of the pesticides based on isolated molecules. The theoretical spectra are in good agreement with the experimental spectra processed by WTD + SBC, which implies the validity of WTD + SBC spectral processing methods and the accuracy of DFT spectral peak analysis. These results support that the combination of THz-TDS and DFT is an effective tool for pesticide fingerprint analysis and the molecular dynamics simulations.

ASTER Spectral Analysis for Host Rock Associated with Porphyry Copper-molybdenum Mineralization

ABSTRACT This study is an attempt to understand the application of spectral image processing methods to ASTER data for mapping host rock associated with porphyry copper-molybdenum mineralization. The application of remote sensing in identifying variations in surface mineralogy, structural elements, and lithologic contacts can help in identifying such relations. Signatures collected from the Advanced Spaceborne Thermal Emission Reflection Radiometer (ASTER) data is used to map the host rock of Zafarqand area. The study area is located in the central segment of the Urumieh–Dokhtar volcanic belt of Iran. The Urumieh-Dokhtar is a potential zone for exploration of new porphyry copper deposits. Band ratio, band math, false colour composites and principal component analysis techniques are used to refine the different lithologic units in the area. These methods showed the discrimination of acidic igneous rock from intermediate igneous rock and the boundary between igneous rocks using the shortwave infrared bands (SWIR) of ASTER at regional scale. Results have proven to be effective and in accordance with the results of field observations, ore microscopy examination and with reference geological map. In conclusion, the image processing methods used can provide cost-effective information to discover possible locations of porphyry copper and epithermal gold mineralization prior to detailed and costly ground investigations. The extraction of spectral information from ASTER data can produce comprehensive and accurate information for copper and gold resource investigations around the world, including those yet to be discovered.

High Speed Intact Protein Characterization Using 4X Frequency Multiplication, Ion Trap Harmonization, and 21 Tesla FTICR-MS

Mass spectrometric characterization of large biomolecules, such as intact proteins, requires the specificity afforded by ultrahigh resolution mass measurements performed at both the intact mass and product ion levels. Although the performance of time-of-flight mass analyzers is steadily increasing, the choice of mass analyzer for large biomolecules (e.g., proteins >50 kDa) is generally limited to the Fourier transform family of mass analyzers such as Orbitrap and ion cyclotron resonance (FTICR-MS), with the latter providing unmatched mass resolving power and measurement accuracy. Yet, protein analyses using FTMS are largely hindered by the low acquisition rates of spectra with ultrahigh resolving power. Frequency multiple detection schemes enable FTICR-MS to overcome this fundamental barrier and achieve resolving powers and acquisition speeds 4× greater than the limits imposed by magnetic field strength. Here we expand upon earlier work on the implementation of this technique for biomolecular characterization. We report the coupling of 21T FTICR-MS, 4X frequency multiplication, ion trapping field harmonization technology, and spectral data processing methods to achieve unprecedented acquisition rates and resolving power in mass spectrometry of large intact proteins. Isotopically resolved spectra of multiply charged ubiquitin ions were acquired using detection periods as short as 12 ms. Large proteins such as apo-transferrin (MW = 78 kDa) and monoclonal antibody (MW = 150 kDa) were isotopically resolved with detection periods of 384 and 768 ms, respectively. These results illustrate the future capability of accurate characterization of large proteins on time scales compatible with online separations.

Assessing low-maturity organic matter in shales using Raman spectroscopy: Effects of sample preparation and operating procedure

Laser Raman spectroscopy is used to assess the thermal maturity of organic matter in sedimentary rocks, particularly organic-rich mudstones. However, discrepancies exist between quantified Raman spectral parameters and maturity values obtained by vitrinite reflectance. This has prevented the adoption of a standard protocol for the determination of thermal maturity of organic matter (OM) by Raman spectroscopy. We have examined the factors influencing the Raman spectra obtained from low-maturity OM in potential shale gas reservoir rocks. The inconsistencies in Raman results obtained are due to three main factors that are critically evaluated: (1) different operational procedures, including experiment setup and spectral processing methods; (2) different methods of sample preparation; (3) the analysis of diverse types of OM. These factors are scrutinized to determine the sources of inconsistency and potential bias in Raman results, and guidance is offered on the development of robust and reproducible analytical protocols. We present two new Raman parameters for un-deconvolved spectra named the DA1/GA ratio (area ratio of 1100–1400 cm−1/1550–1650 cm−1) and SSA (scaled spectrum area: sum of total area between 1100 and 1700 cm−1) that offer potential maturity proxies. An automated spreadsheet procedure is presented that processes raw Raman spectra and calculates several of the most commonly used Raman parameters, including the two new variables.

Capability of crop water content for revealing variability of winter wheat grain yield and soil moisture under limited irrigation

Winter wheat (Triticum aestivum L.) is a major crop in the Guanzhong Plain, China. Understanding its water status is important for irrigation planning. A few crop water indicators, such as the leaf equivalent water thickness (EWT: g cm−2), leaf water content (LWC: %) and canopy water content (CWC: kg m−2), have been estimated using remote sensing techniques for a wide range of crops, yet their suitability and utility for revealing winter wheat growth and soil moisture status have not been well studied. To bridge this knowledge gap, field-scale irrigation experiments were conducted over two consecutive years (2014 and 2015) to investigate relationships of crop water content with soil moisture and grain yield, and to assess the performance of four spectral process methods for retrieving these three crop water indicators. The result revealed that the water indicators were more sensitive to soil moisture variation before the jointing stage. All three water indicators were significantly correlated with soil moisture during the reviving stage, and the correlations were stronger for leaf water indicators than that of the canopy water indicator at the jointing stage. No correlation was observed after the heading stage. All three water indicators showed good capabilities of revealing grain yield variability in jointing stage, with R2 up to 0.89. CWC had a consistent relationship with grain yield over different growing seasons, but the performances of EWT and LWC were growing-season specific. The partial least squares regression was the most accurate method for estimating LWC (R2=0.72; RMSE=3.6%) and comparable capability for EWT and CWC. Finally, the work highlights the usefulness of crop water indicators to assess crop growth, productivity, and soil water status and demonstrates the potential of various spectral processing methods for retrieving crop water contents from canopy reflectance spectrums.

Processing degraded speech for text dependent speaker verification

This work explores the use of speech enhancement for enhancing degraded speech which may be useful for text dependent speaker verification system. The degradation may be due to noise or background speech. The text dependent speaker verification is based on the dynamic time warping (DTW) method. Hence there is a necessity of the end point detection. The end point detection can be performed easily if the speech is clean. However the presence of degradation tends to give errors in the estimation of the end points and this error propagates into the overall accuracy of the speaker verification system. Temporal and spectral enhancement is performed on the degraded speech so that ideally the nature of the enhanced speech will be similar to the clean speech. Results show that the temporal and spectral processing methods do contribute to the task by eliminating the degradation and improved accuracy is obtained for the text dependent speaker verification system using DTW.

Artifact Correction in Temperature-Dependent Attenuated Total Reflection Infrared (ATR-IR) Spectra.

A spectral processing method was developed and tested for analyzing temperature-dependent attenuated total reflection infrared (ATR-IR) spectra of aliphatic polyesters. Spectra of a bio-based, biodegradable polymer, 3.9 mol% 3HHx poly[(R)-3-hydroxybutyrate- co-(R)-3-hydroxyhexanoate] (PHBHx), were analyzed and corrected prior to analysis using two-dimensional correlation spectroscopy (2D-COS). Removal of the temperature variation of diamond absorbance, correction of the baseline, ATR correction, and appropriate normalization were key to generating more reliable data. Both the processing steps and order were important. A comparison to differential scanning calorimetry (DSC) analysis indicated that the normalization method should be chosen with caution to avoid unintentional trends and distortions of the crystalline sensitive bands.

Chemotaxonomy as a tool for interpreting the cryptic diversity of Poaceae pollen

The uniform morphology of different species of Poaceae (grass) pollen means that identification to below family level using light microscopy is extremely challenging. Poor taxonomic resolution reduces recoverable information from the grass pollen record, for example, species diversity and environmental preferences cannot be extracted. Recent research suggests Fourier Transform Infra-red Spectroscopy (FTIR) can be used to identify pollen grains based on their chemical composition. Here, we present a study of twelve species from eight subfamilies of Poaceae, selected from across the phylogeny but from a relatively constrained geographical area (tropical West Africa) to assess the feasibility of using this chemical method for identification within the Poaceae family. We assess several spectral processing methods and use K-nearest neighbour (k-nn) analyses, with a leave-one-out cross-validation, to generate identification success rates at different taxonomic levels. We demonstrate we can identify grass pollen grains to subfamily level with an 80% success rate. Our success in identifying Poaceae to subfamily level using FTIR provides an opportunity to generate high taxonomic resolution datasets in research areas such as palaeoecology, forensics, and melissopalynology quickly and at a relatively low cost.

Automated Quantification of Tumor Viability in a Rabbit Liver Tumor Model after Chemoembolization Using Infrared Imaging

The rabbit VX2 tumor is a fast-growing carcinoma model commonly used to study new therapeutic devices, such as catheter-based therapies for patients with inoperable hepatocellular carcinoma. The evaluation of tumor viability after such locoregional therapies is essential to directing hepatocellular carcinoma management. We used infrared microspectroscopy for the automatic characterization and quantification of the VX2 liver tumor viability after drug-eluting beads transarterial chemoembolization (DEB-TACE). The protocol consisted of K-means clustering followed by principal component analysis (PCA) and linear discriminant analysis (LDA). The K-means clustering was used to classify the spectra from the infrared images of control or treated tumors and to build a database of many tissue spectra. On the basis of this reference library, the PCA-LDA analysis was used to build a predictive model to identify and quantify automatically tumor viability on unknown tissue sections. For the DEB group, the LDA model determined that the surface of tumor necrosis represented 91.6% ± 8.9% (control group: 33.1% ± 19.6%; Mann-Whitney P = 0.0004) and the viable tumor 2.6% ± 4% (control group: 62.2% ± 15.2%; Mann-Whitney P = 0.0004). Tissue quantification measurements correlated well with tumor necrosis (r = 0.827, P < 0.0001) and viable tumor (r = 0.840, P < 0.0001). Infrared imaging and PCA-LDA analysis could be helpful for easily assessing tumor viability.