Fast Evaluation of Unhealthy and Healthy Neonates Using Hyperspectral Features on 700-850 Nm Wavelengths,ROI Extraction,and 3D-CNN

ObjectivesHyperspectral imaging (HSI) has great potential in detecting the health conditions of neonates as it provides diagnostic information about the tissue by avoiding tissue biopsy. HSI gives more features than thermal imaging, which can obtain images in a single wavelength, as it can obtain images in a large number of wavelengths. The data obtained with hyperspectral sensors are 3-dimensional data called hypercube including first two-dimensional spatial information and third-dimensional spectral information.Material and methodsIn this study, hyperspectral data were obtained from 19 different neonates in the Neonatal Intensive Care Unit (NICU) of Selcuk University, Medical Faculty. There are 16 hypercubes from 16 unhealthy neonates, 16 hypercubes from 3 healthy neonates in a period of three months, and 32 hypercubes in total are available. For the training of 3D-CNN model, data augmentation methods, such as rotation, height shifting, width shifting, and shearing were applied to hyperspectral data. A number of 32 hypercubes taken from neonates in NICU were augmented to 160 hypercubes. Spectral signatures were examined and 51 bands in the range of 700-850 nm with distinctive features were used for the classification. The spectral dimension was reduced by applying Principal Component Analysis (PCA) to all hypercubes. In addition, it is aimed to obtain both spectral and spatial features with the 3D-CNN. For increasing the classification efficiency, ROI extraction was made and four datasets were created in different spatial dimensions. These datasets contain 160, 640, 1440, and 5760 hypercubes, respectively.ResultsThe best result was achieved by using 5760 hypercubes of 25x25x51. As a result of the classification of the hypercubes, accuracy 98.00%, sensitivity 97.22%, and specificity 98.78% were obtained. It was determined how many PCs used to achieve the best result. Further, the proposed 3D-CNN model is compared to 2D-CNN model to evaluate the performance of the study.ConclusionIt was aimed to evaluate the health status of neonates fastly by using HSI and 3D-CNN for the first time. The obtained results are an indication that HSI and 3D-CNN are very effective for the evaluation of unhealthy and healthy neonates.     

Identification of cholesterol crystals in plaques of atherosclerotic mice using hyperspectral CARS imaging

The accumulation of lipids, including cholesterol, in the arterial wall plays a key role in the pathogenesis of atherosclerosis. Although several advances have been made in the detection and imaging of these lipid structures in plaque lesions, their morphology and composition have yet to be fully elucidated, particularly in different animal models of disease. To address this issue, we analyzed lipid morphology and composition in the atherosclerotic plaques of two animal models of disease, the low density lipoprotein receptor-deficient (LDLR(-/-)) mouse and the ApoE lipoprotein-deficient (ApoE(-/-)) mouse, utilizing hyperspectral coherent anti-Stokes Raman scattering (CARS) microscopy in combination with principal component analysis (PCA). Hyperspectral CARS imaging revealed lipid-rich macrophage cells and condensed needle-shaped and plate-shaped lipid crystal structures in both mice. Spectral analysis with PCA and comparison to spectra of pure cholesterol and cholesteryl ester derivatives further revealed these lipid structures to be pure cholesterol crystals, which were predominantly observed in the ApoE(-/-) mouse model. These results illustrate the ability of hyperspectral CARS imaging in combination with multivariate analysis to characterize atherosclerotic lipid morphology and composition with chemical specificity, and consequently, provide new insight into the formation of cholesterol crystal structures in atherosclerotic plaque lesions.     

高光谱成像技术对人体面部和手掌的成像及光谱分析

目的：应用高光谱成像技术对正常人体不同部位图像进行采集,分析这些部位的光谱特征,得到正常值数据,并为该技术用于疾病诊断和中医面诊和手诊奠定基础。方法：使用高光谱成像仪,采集10例（男5女5）健康人的面部和双手掌图像,应用高光谱处理分析软件,对面和手掌划分15个分析区域,统计各分区从450-900 nm每间隔10 nm一个光谱段的各个分析区光强度值和光谱特征,并分析个体特点。结果：在面和手掌的高光谱图像上可以清晰地显示面部器官和手掌的不同部位,以580-830 nm段图像更为清晰,530 nm以下图像杂波较多。面部颧、颧下、鼻尖、眉间、额等部位和四指指丘、大小鱼际部位的反光较强,而眼、眉、嘴角和五指末端等则较弱。面部光谱双侧基本对称,而左右手的对称性在不同的个体上不尽相同。在光谱曲线上可以见到某一或者某些波长处光谱出现突变的细节。结论：高光谱成像技术可以清晰地显示人体面和手的图像,显示各部位（器官）的光谱特征;本文得到的面、手高光谱正常数据和特征将为该技术用于疾病诊断和中医辨证提供参考依据。     

Complex patterns in fossilized stromatolites revealed by hyperspectral imaging (400–2496 nm)

Hyperspectral imaging (400–2496 nm) was used to quantitatively map surface textures and compositional variations in stromatolites to determine whether complexity of textures could be used as evidence to support biogenicity in the absence of preserved biomarkers. Four samples of 2.72–2.4 Ga stromatolites from a variety of settings, encompassing marine and lacustrine environments, were selected for hyperspectral imaging. Images of the sawn surfaces of samples were processed to identify reflectance and mineral absorption features and quantify their intensity (as an index of mineral abundance) using automated feature extraction. Amounts of ferrous iron were quantified using a ratio of reflectance at 1650 and 1299 nm. Visible near infrared imagery (400–970 nm) did not reveal additional textural patterns to those obtained from visual inspection. Shortwave infrared imagery (1000–2496 nm), however, revealed complex laminar and convoluted patterns, including a distinctive texture of sharp peaks and broad, low troughs in one sample, similar to living tufted microbial mats. Spectral analysis revealed another sample to be composed of dolomite. Two other samples were dominated by calcite or chlorite ± illite. Large variations in amounts of ferrous iron were found, but ferric iron was exclusively located in the oxidation crust. Hyperspectral imaging revealed large differences between parts of a sample of biogenic and non‐biogenic origin. The former was characterized by calcite with varying amounts of ferrous iron, distributed in lenticular, convoluted patterns; the latter by Mg‐Fe chlorite with large amounts of aluminium silicate, distributed as fine laminar layers. All minerals identified by hyperspectral imaging were confirmed by thin section petrography and XRD analyses. Spatial statistics generated from quantitative minerals maps showed different patterns between these different parts of the sample. Thus, hyperspectral imaging was shown to be a powerful tool for detecting structures in stromatolites that could be used, together with other lines of evidence, to support biogenicity.     

Benefits of hyperspectral remote sensing for tracking plant invasions

Aim We aim to report what hyperspectral remote sensing can offer for invasion ecologists and review recent progress made in plant invasion research using hyperspectral remote sensing. Location United States. Methods We review the utility of hyperspectral remote sensing for detecting, mapping and predicting the spatial spread of invasive species. We cover a range of topics including the trade‐off between spatial and spectral resolutions and classification accuracy, the benefits of using time series to incorporate phenology in mapping species distribution, the potential of biochemical and physiological properties in hyperspectral spectral reflectance for tracking ecosystem changes caused by invasions, and the capacity of hyperspectral data as a valuable input for quantitative models developed for assessing the future spread of invasive species. Results Hyperspectral remote sensing holds great promise for invasion research. Spectral information provided by hyperspectral sensors can detect invaders at the species level across a range of community and ecosystem types. Furthermore, hyperspectral data can be used to assess habitat suitability and model the future spread of invasive species, thus providing timely information for invasion risk analysis. Main conclusions Our review suggests that hyperspectral remote sensing can effectively provide a baseline of invasive species distributions for future monitoring and control efforts. Furthermore, information on the spatial distribution of invasive species can help land managers to make long‐term constructive conservation plans for protecting and maintaining natural ecosystems.     

Hyperspectral imaging: a novel approach for microscopic analysis

BACKGROUND: The usefulness of the light microscope has been dramatically enhanced by recent developments in hardware and software. However, current technologies lack the ability to capture and analyze a high-resolution image representing a broad diversity of spectral signatures in a single-pass view. We show that hyperspectral imaging offers such a technology. METHODS AND RESULTS We developed a prototype hyperspectral imaging microscope capable of collecting the complete emission spectrum from a microscope slide. A standard epifluorescence microscope was optically coupled to an imaging spectrograph, with output recorded by a CCD camera. Software was developed for image acquisition and computer display of resultant X--Y images with spectral information. Individual images were captured representing Y-wavelength planes, with the stage successively moved in the X direction, allowing an image cube to be constructed from the compilation of generated scan files. This prototype instrument was tested with samples relevant to cytogenetic, histologic, cell fusion, microarray scanning, and materials science applications. CONCLUSIONS: Hyperspectral imaging microscopy permits the capture and identification of different spectral signatures present in an optical field during a single-pass evaluation, including molecules with overlapping but distinct emission spectra. This instrument can reduce dependence on custom optical filters and, in future imaging applications, should facilitate the use of new fluorophores or the simultaneous use of similar fluorophores.     

Hyperspectral characterization of re‐epithelialization in an in vitro wound model

In vitro wound models are useful for research on wound re‐epithelialization. Hyperspectral imaging represents a non‐destructive alternative to histology analysis for detection of re‐epithelialization. This study aims to characterize the main optical behavior of a wound model in order to enable development of detection algorithms. K‐Means clustering and agglomerative analysis were used to group spatial regions based on the spectral behavior, and an inverse photon transport model was used to explain differences in optical properties. Six samples of the wound model were prepared from human tissue and followed over 22 days. Re‐epithelialization occurred at a mean rate of 0.24 mm²/day after day 8 to 10. Suppression of wound spectral features was the main feature characterizing re‐epithelialized and intact tissue. Modeling the photon transport through a diffuse layer placed on top of wound tissue properties reproduced the spectral behavior. The missing top layer represented by wounds is thus optically detectable using hyperspectral imaging.     

Imaging depth variations in hyperspectral imaging: Development of a method to detect tumor up to the required tumor‐free margin width

Hyperspectral imaging is a promising technique for resection margin assessment during cancer surgery. Thereby, only a specific amount of the tissue below the resection surface, the clinically defined margin width, should be assessed. Since the imaging depth of hyperspectral imaging varies with wavelength and tissue composition, this can have consequences for the clinical use of hyperspectral imaging as margin assessment technique. In this study, a method was developed that allows for hyperspectral analysis of resection margins in breast cancer. This method uses the spectral slope of the diffuse reflectance spectrum at wavelength regions where the imaging depth in tumor and healthy tissue is equal. Thereby, tumor can be discriminated from healthy breast tissue while imaging up to a similar depth as the required tumor‐free margin width of 2 mm. Applying this method to hyperspectral images acquired during surgery would allow for robust margin assessment of resected specimens. In this paper, we focused on breast cancer, but the same approach can be applied to develop a method for other types of cancer.     

Growth characteristics of three Fusarium species evaluated by near-infrared hyperspectral imaging and multivariate image analysis

Colony growth of three Fusarium spp. on potato dextrose agar was followed by collecting near-infrared (NIR) hyperspectral images of the colonies at regular intervals after inoculation up to 55?h. After principal component analysis (PCA), two clusters were apparent in the score plot along principal component 1. Using the brushing technique, these clusters were divided into four groups of pixels with similar score values. These could be visualised as growth zones within the colonies in the corresponding score image. Three spectral bands, i.e. 1,166, 1,380 and 1,918?nm, were prominent in the multiplicative scatter corrected and Savitzky?CGolay second derivative spectra. These indicated chemical changes, associated with carbohydrates (1,166 and 1,380?nm) and protein (1,918?nm), that occurred as the mycelium grew and matured. The protein band was more prominent in the mature fungal material while the carbohydrate band was less pronounced. The younger material and the agar were characterised by the carbohydrate spectral band. Integrating whole mycelium colonies as the sum of pixels over time made it possible to construct curves that resembled growth curves; this included the lag phase, active growth phase, deceleration phase and phase of constant growth. Growth profiles constructed from individual growth zones indicated more detailed growth characteristics. The use of NIR hyperspectral imaging and multivariate image analysis (MIA) allowed one to visualise radial growth rings in the PCA score images. This would not have been possible with bulk spectroscopy. Interpreting spectral data enabled better understanding of microbial growth characteristics on agar medium. NIR hyperspectral imaging combined with MIA is a powerful tool for the evaluation of growth characteristics of fungi.     

Integrative insect taxonomy based on morphology,mitochondrial DNA,and hyperspectral reflectance profiling

Integrative taxonomy is considered a reliable taxonomic approach of closely related and cryptic species by integrating different sources of taxonomic data (genetic, ecological, and morphological characters). In order to infer the boundaries of seven species of the evacanthine leafhopper genus Bundera Distant, 1908 (Hemiptera: Cicadellidae), an integrated analysis based on morphology, mitochondrial DNA, and hyperspectral reflectance profiling (37 spectral bands from 411–870 nm) was conducted. Despite their morphological similarities, the genetic distances of the cytochrome c oxidase subunit I (COI) gene among the tested species are relatively large (5.8–17.3%). The species‐specific divergence of five morphologically similar species (Bundera pellucida and Bundera spp. 1–4) was revealed in mitochondrial DNA data and reflectance profiling. A key to identifying males is provided, and their morphological characters are described. Average reflectance profiles from the dorsal side of specimens were classified based on linear discriminant analysis. Cross‐validation of reflectance‐based classification revealed that the seven species could be distinguished with 91.3% classification accuracy. This study verified the feasibility of using hyperspectral imaging data in insect classification, and our work provides a good example of using integrative taxonomy in studies of closely related and cryptic species. © 2015 The Linnean Society of London     

基于实地调查和高光谱数据的浑善达克沙地中部植物alpha多样性遥感估测

植物群落物种多样性的快速无损估测一直是近几十年生态学领域的热点研究问题。相对于大尺度的卫星遥感数据,高光谱遥感数据具有光谱和空间分辨率高的优势。采用ASD HH2便携式高光谱仪,收集浑善达克沙地中部120个样方的高光谱数据,并对样方的alpha多样性指数进行同步测定。对高光谱遥感数据进行预处理,采用相关性分析、主成分分析和经验波段筛选法,从数百个波段中选择敏感波段。采用90个样方的高光谱数据作为训练样本,对筛选的敏感波段进行多元线性逐步回归分析,获得12个回归模型。采用另外30个样方的高光谱数据作为验证样本,对回归模型的拟合效果进行检验。结果发现,采用主成分分析法提取敏感波段的回归模型拟合效果最好,Pielou指数、Shannon-Wiener指数和Simpson指数拟合均达到显著水平。对我国植物物种多样性微尺度的快速评估和高光谱遥感具有一定参考意义,并对未来植物多样性高光谱遥感研究提出了建议。     

Investigation of human pancreatic cancer tissues by Fourier Transform Infrared Hyperspectral Imaging

Fourier‐transform infrared hyperspectral imaging (FTIR‐HSI) provides hyperspectral images containing both morphological and chemical information. It is widely applied in the biomedical field to detect tumor lesions, even at the early stage, by identifying specific spectral biomarkers. Pancreatic neoplasms present different prognoses and are not always easily classified by conventional analyses. In this study, tissue samples with diagnosis of pancreatic ductal adenocarcinoma and pancreatic neuroendocrine tumor were analyzed by FTIR‐HSI and the spectral data compared with those from healthy and dysplastic samples. Multivariate/univariate approaches were complemented to hyperspectral images, and definite spectral markers of the different lesions identified. The malignant lesions were recognizable both from healthy/dysplastic pancreatic tissues (high values of phospholipids and triglycerides with shorter, more branched and less unsaturated alkyl chains) and between each other (different amounts of total lipids, phosphates and carbohydrates). These findings highlight different metabolic pathways characterizing the different samples, well detectable by FTIR‐HSI.     

Color Measurement of Tea Leaves at Different Drying Periods Using Hyperspectral Imaging Technique

This study investigated the feasibility of using hyperspectral imaging technique for nondestructive measurement of color components (ΔL*, Δa* and Δb*) and classify tea leaves during different drying periods. Hyperspectral images of tea leaves at five drying periods were acquired in the spectral region of 380–1030 nm. The three color features were measured by the colorimeter. Different preprocessing algorithms were applied to select the best one in accordance with the prediction results of partial least squares regression (PLSR) models. Competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to identify the effective wavelengths, respectively. Different models (least squares-support vector machine [LS-SVM], PLSR, principal components regression [PCR] and multiple linear regression [MLR]) were established to predict the three color components, respectively. SPA-LS-SVM model performed excellently with the correlation coefficient (r_p) of 0.929 for ΔL*, 0.849 for Δa*and 0.917 for Δb*, respectively. LS-SVM model was built for the classification of different tea leaves. The correct classification rates (CCRs) ranged from 89.29% to 100% in the calibration set and from 71.43% to 100% in the prediction set, respectively. The total classification results were 96.43% in the calibration set and 85.71% in the prediction set. The result showed that hyperspectral imaging technique could be used as an objective and nondestructive method to determine color features and classify tea leaves at different drying periods.     

Hyperspectral leaf signature as an added dimension for species discrimination: case study of four tropical mangroves

Hyperspectral leaf reflectance of a plant provides unique information that is characteristic of that plant. The present investigation is a preliminary attempt to assess whether spectra of leaves of mangrove species recorded under field conditions contain adequate spectral information for discerning mangroves at species rank. The paper highlights the hyperspectral characteristics of leaf surfaces of four prominent tropical mangrove species, viz., Avicennia alba, Avicennia marina, Rhizophora mucronata and Sonneratia caseolaris, found in the tidal forests of India. Hyperspectral observations were recorded using a field spectroradiometer, and pre-processed and averaged reflectance values of samples for three types of arrangements, viz., (1) randomly arranged leaves, (2) dorsal leaf surfaces and (3) ventral leaf surfaces of the species were statistically tested using one-way ANOVA to see whether the values significantly differed at every spectral location. All the four species were statistically different at all the spectral locations with majority of the bands exhibiting 99% confidence level. Finally, discriminant analysis was performed to identify the bands for maximum separability for the three types of arrangement of the leaves of the species taken separately and in different combinations. The optimal Wilks’ Lambda (L) were achieved with: six, three, eleven, six, five, thirteen and eleven wavelengths for discriminating random leaves of the four species, dorsal and ventral surfaces of A. alba, A. marina, R. mucronata, S. caseolaris, upper leaf surfaces of all the species, lower leaf surfaces, respectively. Factor analysis was used as an added tool to identify the wavelengths that were uncorrelated and contained maximum information in the combination of selected wavelengths. The results confirmed the unique spectral signatures of the four species, which could be explained in terms of leaf properties unique to the species. Cellular structure and pigmentation of the isolateral leaves of S. caseolaris are very different from the dorsiventral ones of the other three, which significantly changed the reflectance characteristics of the species.     

Cutaneous wound analysis using hyperspectral imaging

A correlative bright-field and hyperspectral analysis of full-thickness, cutaneous wounds in a porcine model was undertaken to investigate the efficacy of hyperspectral imaging as an alternate method for wound identification. Analysis of a randomly selected specimen yielded distinct spectral signatures for cutaneous regions of interest including the epidermis, injured dermis, and normal dermis. The scanning of the entire specimen group using these hyperspectral signatures revealed an exclusionary, pseudo-color pattern whereby a central wound region was consistently defined by a unique spectral signature. An algorithm was derived as an objective tool for the comparison of the wound regions defined by the hyperspectral classification versus the pathologists' manual tracings. The dimensions of the wound identified in the hyperspectral assay did not differ significantly from the wound region identified by the pathologists using standard bright-field microscopy. These data indicate that hyperspectral analysis may provide a high-throughput alternative for wound estimation that approximates standard bright-field imaging and pathologist evaluation.     

Hyperspectral darkfield microscopy of PEGylated gold nanoparticles targeting CD44‐expressing cancer cells

We present a new hyperspectral darkfield imaging system with a scanned broadband supercontinuum light source. We observed the specific attachment of the functionalized gold plasmonic nanoparticles (AuNPs) targeting CD44⁺ human breast cancer cells by conventional and by proposed hyperspectral darkfield microscopy. This wide‐field and low phototoxic hyperspectral imaging system has been successful for performing spectral three‐dimensional (3D) localization and spectroscopic identification of CD44‐targeted PEGylated AuNPs in fixed cell preparations. Such spatial and spectral information is essential for the improvement of nanoplasmonic‐based imaging, disease detection and treatment in complex biological environment. Presented system capability for 3D NP tracking will also enable investigation of specific sub‐cellular activity with the use of NPs as spectral sensors. (© 2013 WILEY‐VCH Verlag GmbH &Co. KGaA, Weinheim)     

基于信号稀疏表示的高光谱散射图像苹果粉质化分类

苹果的粉质化是指苹果果肉发软、汁液减少等一系列物理和生理变化现象,采用高光谱散射图像技术结合信号稀疏表示分类算法(SRSA)研究了苹果的粉质化分类问题。首先利用平均反射算法(MEAN)提取了600～1000 nm的高光谱散射图像特征;引入遗传算法(GA)解决分类样本的不均衡问题,在此基础上,把苹果的粉质化分类问题,转化为一个求解待识别样本对于整体训练样本的稀疏表示问题。仿真结果表明,基于信号稀疏表示分类算法的苹果粉质化分类精度为79.8%,高于偏最小二乘判别分析(PLSDA)的74.8%,为苹果的粉质化分类提供了一种新的有效的方法。     

Oil Adulteration Identification by Hyperspectral Imaging Using QHM and ICA

To investigate the feasibility of identification of qualified and adulterated oil product using hyperspectral imaging(HIS) technique, a novel feature set based on quantized histogram matrix (QHM) and feature selection method using improved kernel independent component analysis (iKICA) is proposed for HSI. We use UV and Halogen excitations in this study. Region of interest(ROI) of hyperspectral images of 256 oil samples from four varieties are obtained within the spectral region of 400–720nm. Radiation indexes extracted from each ROI are used as feature vectors. These indexes are individual band radiation index (RI), difference of consecutive spectral band radiation index (DRI), ratio of consecutive spectral band radiation index (RRI) and normalized DRI (NDRI). Another set of features called quantized histogram matrix (QHM) are extracted by applying quantization on the image histogram from these features. Based on these feature sets, improved kernel independent component analysis (iKICA) is used to select significant features. For comparison, algorithms such as plus L reduce R (plusLrR), Fisher, multidimensional scaling (MDS), independent component analysis (ICA), and principle component analysis (PCA) are also used to select the most significant wavelengths or features. Support vector machine (SVM) is used as the classifier. Experimental results show that the proposed methods are able to obtain robust and better classification performance with fewer number of spectral bands and simplify the design of computer vision systems.     

Simple and robust methods for remote sensing of canopy chlorophyll content: a comparative analysis of hyperspectral data for different types of vegetation

Canopy chlorophyll content (CCC) is an essential ecophysiological variable for photosynthetic functioning. Remote sensing of CCC is vital for a wide range of ecological and agricultural applications. The objectives of this study were to explore simple and robust algorithms for spectral assessment of CCC. Hyperspectral datasets for six vegetation types (rice, wheat, corn, soybean, sugar beet and natural grass) acquired in four locations (Japan, France, Italy and USA) were analysed. To explore the best predictive model, spectral index approaches using the entire wavebands and multivariable regression approaches were employed. The comprehensive analysis elucidated the accuracy, linearity, sensitivity and applicability of various spectral models. Multivariable regression models using many wavebands proved inferior in applicability to different datasets. A simple model using the ratio spectral index (RSI; R815, R704) with the reflectance at 815 and 704 nm showed the highest accuracy and applicability. Simulation analysis using a physically based reflectance model suggested the biophysical soundness of the results. The model would work as a robust algorithm for canopy‐chlorophyll‐metre and/or remote sensing of CCC in ecosystem and regional scales. The predictive‐ability maps using hyperspectral data allow not only evaluation of the relative significance of wavebands in various sensors but also selection of the optimal wavelengths and effective bandwidths.     

Effectiveness of near-infrared spectroscopy as a non-invasive tool to discriminate spectral profiles of in vitro cultured oocytes from goats

Here, we aimed to discriminate between the spectral profiles of spent culture media after oocyte in vitro maturation (IVM) and culture (IVC) from goats of different ages subjected to repeated hormonal treatments. The profiles were discriminated using near infrared (NIR) spectroscopy combined with multivariate methods. A total of 19 goats (young = 10; old = 9) were subjected to serial hormonal stimulation (HS) with gonadotropins. Cumulus oophorus complexes (COCs) were collected using laparoscopic ovum pick-up (LOPU) and subjected to IVM and parthenogenetic activation. The initial embryos were subjected to IVC. Spent culture media were collected after oocyte IVM and on day 2 of IVC and analyzed using NIR spectroscopy. NIR spectral data were interpreted through chemometric methods, such as principle component analysis (PCA) and partial least square discriminant analysis (PLS-DA). The results of PCA analysis clearly showed a separation in the spectral profiles between the experimental groups (HS sessions; young and old animals) both after IVM and IVC. Overall, the main absorption bands were attributed to the C-H group second overtone, first overtone of O-H and N-H, and C-H combinations and may serve as molecular markers. On the other hand, the spectral data obtained using PLS-DA models provided a better classification of the groups. The results showed the possibility of discriminating young and old groups as well as the three HS sessions with high specificity, sensitivity, and accuracy using NIR spectra. Thus, the culture medium analysis using NIR spectroscopy combined with multivariate methods indicated the dissimilarities between the groups and provided an insight into the in vitro development of goat oocytes. This technique serves as an efficient, objective, rapid, and non-invasive method to discriminate spectral profiles.