Scatter Correction Research Articles

Detection of wheat saccharification power and protein content using stacked models integrated with hyperspectral imaging.

Wheat is one of the key ingredients used to make Chinese liquor, and its saccharification power and protein content directly affect the quality of the liquor. In pursuit of a non-destructive assessment of wheat components and the optimization of raw material proportions in liquor, this study introduces a precise predictive model that integrates hyperspectral imaging (HSI) with stacked ensemble learning (SEL). This study extracted hyperspectral information from 14 different varieties of wheat and employed various algorithms for preprocessing. It was observed that multiplicative scatter correction (MSC) emerged as the most effective spectral preprocessing method. The feature wavelengths were extracted from the preprocessed spectral data using three different feature extraction methods. Then, single models (support vector machine (SVM), backpropagation neural network (BPNN), random forest (RF), and gradient boosting tree (XGBoost)) and a SEL model were developed to compare the prediction accuracies of the SEL model and the single models based on the full-band spectral data and the characteristic wavelengths. The findings indicate that the MSC-competitive adaptive reweighted sampling-SEL model demonstrated the highest prediction accuracy, with Rp 2 (test set-determined coefficient) values of 0.9308 and 0.9939 for predicting the saccharification power and protein content and root mean square error of the test set values of 0.0081 U and 0.0116 g kg-1, respectively. The predictive model established in this study, integrating HSI and SEL models, accurately detected wheat saccharification power and protein content. This validation underscores the practical potential of the SEL model and holds significant importance for non-destructive component analysis of raw materials used in liquor. © 2024 Society of Chemical Industry.

UMC-PET: a fast and flexible Monte Carlo PET simulator

Objective. The GPU-based Ultra-fast Monte Carlo positron emission tomography simulator (UMC-PET) incorporates the physics of the emission, transport and detection of radiation in PET scanners. It includes positron range, non-colinearity, scatter and attenuation, as well as detector response. The objective of this work is to present and validate UMC-PET as a a multi-purpose, accurate, fast and flexible PET simulator. Approach. We compared UMC-PET against PeneloPET, a well-validated MC PET simulator, both in preclinical and clinical scenarios. Different phantoms for scatter fraction (SF) assessment following NEMA protocols were simulated in a 6R-SuperArgus and a Biograph mMR scanner, comparing energy histograms, NEMA SF, and sensitivity for different energy windows. A comparison with real data reported in the literature on the Biograph scanner is also shown. Main results. NEMA SF and sensitivity estimated by UMC-PET where within few percent of PeneloPET predictions. The discrepancies can be attributed to small differences in the physics modeling. Running in a 11 GB GeForce RTX 2080 Ti GPU, UMC-PET is ∼1500 to ∼2000 times faster than PeneloPET executing in a single core Intel(R) Xeon(R) CPU W-2155 @ 3.30 GHz. Significance. UMC-PET employs a voxelized scheme for the scanner, patient adjacent objects (such as shieldings or the patient bed), and the activity distribution. This makes UMC-PET extremely flexible. Its high simulation speed allows applications such as MC scatter correction, faster SRM estimation for complex scanners, or even MC iterative image reconstruction.

Quantitative Analysis of Near-Infrared Spectroscopy Using the BEST-1DConvNet Model

In the quest for enhanced precision in near-infrared spectroscopy (NIRS), in this study, the application of a novel BEST-1DConvNet model for quantitative analysis is investigated against conventional support vector machine (SVM) approaches with preprocessing such as multiplicative scatter correction (MSC) and standard normal variate (SNV). We assessed the performance of these methods on NIRS datasets of diesel, gasoline, and milk using a Fourier Transform Near-Infrared (FT-NIR) spectrometer having a wavelength range of 900–1700 nm for diesel and gasoline and 4000–10,000 nm for milk, ensuring comprehensive spectral capture. The BEST-1DConvNet’s effectiveness in chemometric predictions was quantitatively gauged by improvements in the coefficient of determination (R2) and reductions in the root mean square error (RMSE). The BEST-1DConvNet model achieved significant performance enhancements compared to the MSC + SNV + 1D + SVM model. Notably, the R2 value for diesel increased by approximately 48.85% despite a marginal RMSE decrease of 0.92%. R2 increased by 11.30% with a 3.32% RMSE reduction for gasoline, and it increased by 8.71%, accompanied by a 3.51% RMSE decrease for milk. In conclusion, the BEST-1DConvNet model demonstrates superior predictive accuracy and reliability in NIRS data analysis, marking a substantial leap forward in spectral analysis technology. This advancement could potentially streamline their integration into various industrial applications and highlight the role of convolutional neural networks in future chemometric methodologies.

Technical NEMA NU2-2018 Performance Assessment of Time-of-Flight-Integrated Digital PET-CT System.

Aim The objective of this study includes the NEMA (National Electrical Manufacturer Association) NU2-2018 performance evaluation of the uMIvista PET-CT (positron emission tomography-computed tomography) system. Methods The latest NEMA NU2-2018 guidelines have been followed for the evaluation of performance parameters of this PET-CT scanner: axial, tangential, and radial spatial resolution, sensitivity, counting losses, scatter, randomness, random and counting loss correction, image quality, time and energy resolution, image uniformity, and image registration alignment post installation of country first uMIvista PET-CT. Results The measured NEMA sensitivity of the uMIvista PET scanner was 12.053 cps/kBq. The spatial resolutions of the PET were measured as tangential, radial, and transaxial spatial resolutions at 10 mm, with 3.01 mm, 2.95 mm, and 2.93 mm, respectively; at 100 mm, with 3.17 mm, 3.42 mm, and 3.05 mm, respectively; and at 200 mm, with 3.65 mm, 4.54 mm, and 3.17 mm, respectively, at full-width half-maximum (FWHM); while at full-width tenths-maximum (FWTM), the values at 10 mm were 5.79 mm, 5.57 mm, and 5.69 mm, respectively, and at 100 mm were 5.59 mm, 5.96 mm, and 5.91 mm, respectively. The measured time-of-flight (TOF) timing resolution was 302.294 ps and the measured energy resolution was 11.76% with FWHM and FWTM. Conclusion The NEMA NU2-2018 performances of this TOF-integrated digital PET-CT system are extremely good in all parameters.

Effect of Combined Non-Wood and Wood Spectra of Biomass Chips on Rapid Prediction of Ultimate Analysis Parameters Using near Infrared Spectroscopy

The ultimate analysis parameters, including carbon (C), hydrogen (H), nitrogen (N), and oxygen (O) content in biomass, were rarely found to be predicted by non-destructive tests to date. In this research, we developed partial least squares regression (PLSR) models to predict the ultimate analysis parameters of chip biomass using near-infrared (NIR) raw spectra of non-wood and wood samples from fast-growing tree and agricultural residue and nine different traditional spectral preprocessing techniques. These techniques include first derivative (sd1), second derivative (sd2), constant offset, standard normal variate (SNV), multiplicative scatter correction (MSC), vector normalization, min-max normalization, mean centering, sd1 + vector normalization, and sd1 + MSC. Additionally, we employed a genetic algorithm (GA), successive projection algorithm (SPA), multi-preprocessing (MP) 5-range, and MP 3-range to develop a PLSR model for rapid prediction. A dataset consisting of 120 chip biomass samples was utilized for model development in which the samples were non-wood samples of 65–67% and wood samples of 33–35%, and the model performance was evaluated and compared. The selection of the optimum performing model was mainly based on criteria such as the coefficient of determination in the prediction set (R2P), root mean square error of the prediction set (RMSEP), and the ratio of prediction to deviation (RPD). The optimal model for weight percentage (wt.%) of C was obtained using GA–PLSR, yielding R2P, RMSEP, and RPD values of 0.6954, 1.1252 wt.%, and 1.8, respectively. Similarly, for wt.% of O, the most effective model was obtained using the multi-preprocessing PLSR–5 range method with R2P of 0.7150, RMSEP of 1.3088 wt.%, and RPD of 1.9. For wt.% of N, the optimal model was obtained using the MP PLSR-3 range method, resulting in R2P, RMSEP, and RPD values of 0.6073, 0.1008 wt.%, and 1.6, respectively. However, wt.% of the H model provided R2P, RMSEP, and RPD values of 0.5162, 0.2322 wt.%, and 1.5, respectively. Notably, the limit of quantification (LOQ) values for C, H, and O were lower than the minimum reference values used during model development, indicating a high level of sensitivity. However, the LOQ for N exceeded the minimum reference value, implying the samples to be predicted by the model must be in the range of reference range in the calibration set. By scatter plot analysis, the effect of combined non-wood and wood spectra of biomass chips on rapid prediction of ultimate analysis parameters using NIR spectroscopy was investigated. To include different species in a model, the species have to be not only in the different values of the constituents to make a wider range for a robust model, but also must provide their trend line characteristics in the scatter plot, i.e., correlation coefficient (R), slope, and intercept (same slope and slope approached to 1, and intercept is same (no gap) and approached zero, high R approached to 1). The effect of the R, slope, and intercept to obtain the better-optimized model was studied. The results show that the different species affected the model performance of each parameter prediction in a different manner, and by scatter plot analysis, which of these species were affecting the model negatively and how the model could be improved was indicated. This is the first time the effect has been studied by the principle of a scatter plot.

Stratified diagnosis of cotton canopy spectral characteristics based on CWT-SPA and its relationship with moisture, nitrogen, and SPAD values

ABSTRACT Cotton is an economically valuable crop worldwide, and accurate and rapid leaf moisture content, nitrogen content, and soil plant analysis development (SPAD) value estimations are crucial for cotton growth. In this study, high-resolution spectral data were collected for the Tahe 2 cotton variety in Alar City, Xinjiang. The raw spectra were preprocessed using four methods: first derivative, standard normal variate transformation, second derivative, and multiplicative scatter correction. Wavelet coefficients at multiple scales were generated from the raw spectra using a continuous wavelet transform (CWT) and CWT with first derivative (CWT-FD). A quantitative detection model combining CWT and CWT-FD with successive projection algorithm – partial least squares (SPA-PLS) was developed to estimate the leaf moisture content, nitrogen content, and SPAD values. The performances of the different scales and methods for estimating these parameters were compared. Six stratification methods were employed to determine the optimal modelling results and decomposition scales for the parameters under various stratification schemes. The results demonstrated that the CWT and CWT-FD methods significantly improved the accuracy of estimating cotton canopy spectral characteristics related to the parameters, surpassing that of conventional spectral processing methods. The mexh, db5, and db5 wavelet basis functions, along with scale 3, were identified as the optimal modelling choices for moisture content, nitrogen content, and SPAD values throughout the cotton plant growth period. Among the six vertical stratification structures of cotton, the CWT and CWT-FD methods, along with the three wavelet basis functions, achieved the best results for the three parameters in the upper layer. The optimal relative percent deviation values for the three parameters of typical leaves ranged from 1.603 to 2.016, indicating satisfactory modelling performance. These findings provide a theoretical foundation for accurately estimating leaf moisture content, nitrogen content, and SPAD values using spectral technology, enabling the simultaneous extraction and monitoring of multiple physiological indicators.

The Impact of Dual and Triple Energy Window Scatter Correction on I-123 Postsurgical Thyroid SPECT/CT Imaging Using a Phantom with Small Sizes of Thyroid Remnants.

I-123 is preferential over I-131 for diagnostic SPECT imaging after a thyroidectomy to determine the presence and size of residual thyroid tissue for radioiodine ablation. Scattering degrades the quality of I-123 SPECT images, primarily due to the penetration of high-energy photons into the main photopeak. The objective of this study was to quantitatively and qualitatively investigate the impact of two widely used window-based scatter correction techniques, the dual energy window (DEW) and triple energy window (TEW) techniques, in I-123 postsurgical SPECT/CT thyroid imaging using an anthropomorphic phantom with small sizes of remnants and anatomically correct surrounding structures. For this purpose, non-scatter-corrected, DEW and TEW scatter-corrected SPECT/CT acquisitions were performed for 0.5-10 mL remnants within a phantom, with 0.5-12.6 MBq administered activities within the remnants, and without and with background-to-remnant activity ratios of 5% and 10%. The decrease in photons, the noise and non-uniformity in the background region due to scatter correction were measured, as well as the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) from small remnants. The images were also visually evaluated by two experienced nuclear medicine physicians. Scatter correction decreased photons to a higher extent in larger regions than smaller regions. Larger remnants yielded higher SNR and CNR values, particularly at lower background activities. It was found from the quantitative analysis and the qualitative evaluation that TEW scatter correction performed better than DEW scatter correction, particularly at higher background activities, while no significant differences were reported at lower background activities. Scatter correction should be applied in I-123 postsurgical SPECT/CT imaging to improve the image contrast and detectability of small remnants within the background.

Strategies for deep learning-based attenuation and scatter correction of brain 18 F-FDG PET images in the image domain.

Attenuation and scatter correction is crucial for quantitative positron emission tomography (PET) imaging. Direct attenuation correction (AC) in the image domain using deep learning approaches has been recently proposed for combined PET/MR and standalone PET modalities lacking transmission scanning devices or anatomical imaging. In this study, different input settings were considered in the model training to investigate deep learning-based AC in the image space. Three different deep learning methods were developed for direct AC in the image space: (i) use of non-attenuation-corrected PET images as input (NonAC-PET), (ii) use of attenuation-corrected PET images with a simple two-class AC map (composed of soft-tissue and background air) obtained from NonAC-PET images (PET segmentation-based AC [SegAC-PET]), and (iii) use of both NonAC-PET and SegAC-PET images in a Double-Channel fashion to predict ground truth attenuation corrected PET images with Computed Tomography images (CTAC-PET). Since a simple two-class AC map (generated from NonAC-PET images) can easily be generated, this work assessed the added value of incorporating SegAC-PET images into direct AC in the image space. A 4-fold cross-validation scheme was adopted to train and evaluate the different models based using 80 brain 18 F-Fluorodeoxyglucose PET/CT images. The voxel-wise and region-wise accuracy of the models were examined via measuring the standardized uptake value (SUV) quantification bias in different regions of the brain. The overall root mean square error (RMSE) for the Double-Channel setting was 0.157±0.08 SUV in the whole brain region, while RMSEs of 0.214±0.07 and 0.189±0.14 SUV were observed in NonAC-PET and SegAC-PET models, respectively. A mean SUV bias of 0.01±0.26% was achieved by the Double-Channel model regarding the activity concentration in cerebellum region, as opposed to 0.08±0.28% and 0.05±0.28% SUV biases for the network that uniquely used NonAC-PET or SegAC-PET as input, respectively. SegAC-PET images with an SUV bias of -1.15±0.54%, served as a benchmark for clinically accepted errors. In general, the Double-Channel network, relying on both SegAC-PET and NonAC-PET images, outperformed the other AC models. Since the generation of two-class AC maps from non-AC PET images is straightforward, the current study investigated the potential added value of incorporating SegAC-PET images into a deep learning-based direct AC approach. Altogether, compared with models that use only NonAC-PET and SegAC-PET images, the Double-Channel deep learning network exhibited superior attenuation correction accuracy.

The determination of the optimal threshold on measurement of thyroid volume using quantitative SPECT/CT for Graves' hyperthyroidism

PurposeTo investigate the optimal threshold for measuring thyroid volume in patients with Grave's hyperthyroidism (GH) by SPECT/CT.Materials and methodsA 53 mL butterfly-shaped hollow container made of two 45-degree transparent elbows was put into a NEMA IEC phantom tank. The butterfly-shaped container and the tank were then filled with Na99mTcO4 of different radioactive concentrations, respectively, which could simulate thyroid gland with GH by different target-to-background ratios (T/B) (200:1, 600:1, 1000:1). The different T/B of planar imaging and SPECT/CT were acquired by a Discovery NM/CT 670 Pro SPECT/CT. With Thyroid software (Version 4.0) of GE-Xeleris workstation, the region of the thyroid gland in planar imaging was delineated. The thyroid area and average long diameter of both lobes were substituted into the Allen formula to calculate the thyroid volume. The calculation error was compared with the actual volume. Q-Metrix software was used to perform CT-based attenuation correction, scatter correction, resolution recovery. Ordered-subsets expectation maximization was used to reconstruct SPECT data. 20%, 25%, 30%, 40%, 50%, 60% thresholds were selected to automatically delineate the volume of interest and compared with the real volume, which determinated the optimal threshold. We measured the thyroid volume of 40 GH patients using the threshold and compared the volumes obtained by planar imaging and ultrasound three-dimensional. The differences of the volumes with different T/B and thresholds were compared by the ANOVA and least significant difference t test. The volumes delineated by SPECT/CT were evaluated using ANOVA, least significant difference t test, correlation analysis and, linear regression and Bland–Altman concordance test plot. The differences and consistency of thyroid volume were compared among the above three methods.ResultsThere was no significant difference in the results between different T/B models (P > 0.05). The thyroid volume calculated by the planar imaging formula method was higher than the real volume, with an average overestimation of 22.81%. The volumes delineated by SPECT/CT threshold automatically decreased while the threshold increased. There were significant differences between groups with different thresholds (P < 0.001). With an average error of 3.73%, the thyroid volume analyzed by the threshold of 25% was close to the results of ultrasound measurement (P > 0.05). Thyroid volume measured by planar imaging method was significantly higher than ultrasound and SPECT/CT threshold automatic delineation method (P < 0.05). The agreement between the SPECT/CT 25% threshold and ultrasound (r = 0.956, b = 0.961) was better than that between the planar imaging and ultrasound (r = 0.590, b = 0.574). The Bland–Altman plot also showed that the thyroid volume measured by the 25% threshold automatic delineation method was in good agreement with the ultrasound measurement.ConclusionsThe T/B has no effect on the measurement of thyroid volume in GH patients; planar imaging method can significantly overestimate thyroid volume in GH patients, and 25% threshold automatic delineation method can obtain more accurate thyroid volume in GH patients.

Performance Improvement of Partial Least Squares Regression Soluble Solid Content Prediction Model Based on Adjusting Distance between Light Source and Spectral Sensor according to Apple Size.

Apples are widely cultivated in the Republic of Korea and are preferred by consumers for their sweetness. Soluble solid content (SSC) is measured non-destructively using near-infrared (NIR) spectroscopy; however, the SSC measurement error increases with the change in apple size since the distance between the light source and the near-infrared sensor is fixed. In this study, spectral characteristics caused by the differences in apple size were investigated. An optimal SSC prediction model applying partial least squares regression (PLSR) to three measurement conditions based on apple size was developed. The three optimal measurement conditions under which the Vis/NIR spectrum is less affected by six apple size levels (Levels I-VI) were selected. The distance from the apple center to the light source and that to the sensor were 125 and 75 mm (Distance 1), 123 and 75 mm (Distance 2), and 135 and 80 mm (Distance 3). The PLSR model applying multiplicative scatter correction pretreatment under Distance 3 measurement conditions showed the best performance for Level IV-sized apples (Rpre2 = 0.91, RMSEP = 0.508 °Brix). This study shows the possibility of improving the SSC prediction performance of apples by adjusting the distance between the light source and the NIR sensor according to fruit size.

Establishment of a general prediction model for protein content in various varieties and colors of peas using visible-near-infrared spectroscopy

Non-destructive and swift detection of protein content in peas holds significant importance for screening superior germplasm resources. This study aimed to construct a general detection model of pea protein content. Spectral detection data of pea proteins were analyzed across three bands: 400 ∼ 982 nm, 982 ∼ 2520 nm, and 400 ∼ 2520 nm. The spectral data were preprocessed by 16 different methods. The successive projections algorithm (SPA) and uninformative variables elimination (UVE) algorithms were used to screen characteristic wavelengths. Pea protein content prediction models were established by using partial least squares regression (PLSR) and extreme learning machine (ELM). Following analysis, the best modeling band was 400 ∼ 982 nm. The optimal prediction model was multiplicative scatter correction (MSC)-SPA-ELM. The correlation coefficients for the calibration and validation sets were 0.8851 and 0.8595, respectively, with root mean square errors of 0.8933 g/100 g and 1.0565 g/100 g.The ratio of error range (RER) was 9.23. These results suggest that this study offers a viable solution for non-destructive and rapid pea protein detection across diverse regions, varieties, and colors.

Comparison of principal component regression (PCR) and partial least square regression (PLSR) modeling methods for quantifying polyethylene (PE) in recycled polypropylene (rPP) with near-infrared spectrometry (NIR)

Recycled polypropylene (rPP) often contains a small amount of polyethylene (PE). Since polypropylene (PP) and PE are incompatible, the presence of PE compromises the performance of rPP materials and needs to be closely monitored. In our previous work, Raman and near-infrared (NIR) spectrometries were evaluated to monitor PE content in rPP with partial least square regression (PLSR) modeling. The NIR spectrometry exhibited a wider application range, but the accuracy of the prediction models might be further improved. In the current work, a different modeling method, principal component regression (PCR) was employed to analyze PE content in rPP with NIR spectrometry. Spectrum pretreatment methods, including multivariate scatter correction (MSC), standard normal variate transformation (SNV), smoothing, and first derivative, were investigated to improve the NIR spectrum quality. Forward and backward interval methods were used to optimize spectral range selection. The outcomes were compared with our previous PLSR modeling results. The highest accuracy in independent validation was achieved by a PCR model with an R 2 of 0.9991 and a root-mean-square error of prediction (RMSEP) of 0.1596 PE%. On the other hand, a PLSR model achieved the lowest RMSEP of 0.9712 PE% for a non-colored post-consumer rPP sample. The PCR models might be sensitive to interference and more suitable for post-industrial materials, which have a simpler chemical composition. The PLSR models might have better stability and be more suitable for complicated post-consumer samples. Both the PCR and PLSR models were successfully applied to a gray commercial rPP sample.

Performance and usefulness evaluation of a software-based scatter correction technique for mammographic images

Although physical grids improve contrast in radiographic images by reducing scattered radiation, various artifacts such as grid shadow, moire, and cutoff result in increased patient doses. To overcome these problems, this study evaluates the applicability and usefulness of a material thickness-based scatter-correction technique for mammography. Specifically, this study aims to compare and evaluate the performance of mammography using the proposed software-based scatter correction framework and a physical grid. The proposed technique enables scatter correction based on pre-calculated parameters of a thickness-based scatter kernel at a water slab phantom and an empirical quantity of scatter components in a mammographic system. In the Monte Carlo simulation and experiment, the proposed framework displayed an intensity profile and full width at half maximum that closely approximated those seen in the physical grid. In addition, by applying the proposed framework to the ACR phantom, it was verified that all structures, including specks, were distinctly distinguished. The results demonstrate that the X-ray scatter-correction method with a software-based framework for mammography is applicable to the field of diagnostic imaging, as this approach yields image quality equivalent to that achieved with physical grids while also enabling a reduction in radiation doses for patients.

Recent advances in combined Positron Emission Tomography and Magnetic Resonance Imaging

Abstract Hybrid imaging modalities combine two or more medical imaging techniques offering exciting new possibilities to image the structure, function and biochemistry of the human body in far greater detail than has previously been possible to improve patient diagnosis. In this context, simultaneous Positron Emission Tomography and Magnetic Resonance (PET/MR) imaging offers great complementary information, but it also poses challenges from the point of view of hardware and software compatibility. The PET signal may interfere with the MR magnetic field and vice-versa, posing several challenges and constrains in the PET instrumentation for PET/MR systems. Additionally, anatomical maps are needed to properly apply attenuation and scatter corrections to the resulting reconstructed PET images, as well motion estimates to minimize the effects of movement throughout the acquisition. In this review, we summarize the instrumentation implemented in modern PET scanners to overcome these limitations, describing the historical development of hybrid PET/MR scanners. We pay special attention to the methods used in PET to achieve attenuation, scatter and motion correction when it is combined with MR, and how both imaging modalities may be combined in PET image reconstruction algorithms.

Accuracy Evaluation of Visible-Near Infrared Spectroscopy for Detecting Insect Damage in Acorns of Quercus acuta

Abstract This study aimed to test near-infrared spectroscopy to assess insect damage to oak acorns collected from a seed orchard of Quercus acuta in Jeju Island, Korea. A total of 550 acorns were sorted into 362 sound and 178 unsound (insect-damaged) acorns, followed by near-infrared spectroscopy. To minimize spectral data errors, preprocessing techniques such as first derivative, multiplicative scatter correction, standard normal variate, and Savitzky-Golay filter were applied, along with multivariate analysis methods like partial least squares. Then the model performance, including accuracy and precision, was evaluated using the Variable Importance in Projection. The near-infrared wavelength of the acorns showed strong absorption peaks at 660~720nm and a slight downward trend at 900~1000nm. The most effective model for distinguishing unsound acorns was Savitzky-Golay filtering treatment applied in the 400~1000nm range and used partial least squares, showing prediction accuracy of 86 % (p&lt;0.05). The performance was significantly influenced by absorption points at 660~720nm and 960~1000nm, with the latter range believed to be affected by changes in moisture and carbohydrates due to insect damage. The former range showed lower classification capability due to chlorophyll and color variation but affected the model performance when used with near-infrared wavelength range. These findings can narrow down the scope of investigation for future research using wider wavelength ranges or multispectral analysis.

Integrating near-infrared hyperspectral imaging with machine learning and feature selection: Detecting adulteration of extra-virgin olive oil with lower-grade olive oils and hazelnut oil

Detecting adulteration in extra virgin olive oil (EVOO) is particularly challenging with oils of similar chemical composition. This study applies near-infrared hyperspectral imaging (NIR-HSI) and machine learning (ML) to detect EVOO adulteration with hazelnut, refined olive, and olive pomace oils at various concentrations (1%, 5%, 10%, 20%, 40%, and 100% m/m). Savitzky-Golay filtering, first and second derivatives, multiplicative scatter correction (MSC), standard normal variate (SNV), and their combinations were used to preprocess the spectral data, with Principal Component Analysis (PCA) reducing dimensionality. Classification was performed using Partial Least Squares-Discriminant Analysis (PLS-DA) and ML algorithms, including k-Nearest Neighbors (k-NN), Naïve Bayes, Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). PLS-DA, k-NN, RF, SVM, NB, and ANN models achieved accuracy rates of 97.0–99.0%, 96.2–100%, 96.5–100%, 98.6–99.5%, 93.9–99.7%, and 99.2–100%, respectively, in discriminating between pure EVOO, adulterants, and adulterated oils. PLS-DA, RF, SVM, and ANN significantly outperformed Naïve Bayes (p < 0.05) in binary classification, with Matthews correlation coefficient (MCC) values exceeding 0.90. All the binary classifiers except Naïve Bayes, when coupled with SNV/MSC, Savitzky-Golay smoothing and derivatives, consistently achieved perfect scores (1.0) for accuracy, sensitivity, specificity, F1 score, precision, and MCC in distinguishing pure EVOO from adulterated oils. No significant differences (p > 0.05) in model performance were found between those using full spectra and those based on key variable selection. However, PLS-DA and ANN significantly outperformed k-NN, RF, and SVM (p < 0.05), with MCC values ranging from 0.95 to 1.00, indicating superior classification performance. These findings demonstrate that combining NIR-HSI with machine learning, along with key variable selection, potentially offers an effective, non-destructive solution for detecting adulteration in EVOO and combating fraud in the olive oil industry.

High-accuracy classification and origin traceability of peanut kernels based on near-infrared (NIR) spectroscopy using Adaboost - Maximum uncertainty linear discriminant analysis

Peanut kernels, known for their high nutritional value and palatability, are classified as nut food. In this study, peanut kernel samples from six distinct cities in Shandong Province, China, were examined to categorize and trace their origins. Near-infrared (NIR) spectra of samples were captured using a portable NIR-M-R2 spectrometer. After the application of Savitzky-Golay (SG) filtering, the classification was attempted using principal component analysis (PCA) plus linear discrimination analysis (LDA). Additionally, maximum uncertainty linear discriminant analysis (MLDA) was applied for comparison. A specific number of eigenvectors could respectively maximize the classification accuracies, 81.48% for PCA + LDA and 76.54% for MLDA. In order to further improve the classification accuracies, Adaboost-MLDA was proposed to develop a stronger classifier. This method, after 18 iterations, achieved remarkable effects, achieving a high accuracy of 95.06%. In a similar vein, the enhancement with preprocessing techniques multiplicative scatter correction (MSC) + SG and standard normal variate (SNV) + SG raised accuracies to 98.77% and 97.53%, respectively. The results of classifying first-order and second-order derivative spectra using Adaboost-MLDA were also described, achieving accuracies near 100%. The experiment demonstrates that integrating Adaboost with NIR spectroscopy offers a highly accurate method for peanut kernel classification, promising for practical applications in food quality control.

Loopy Orthogonal Signal Correction Scatter Correction in Non-Invasive Blood Glucose

Spectroscopy is the study of matter based on light, sound, or particles emitted, absorbed, or reflected as well as the study of methods for generating and analyzing spectra. The spectrum has systematic diversity, namely the presence of light scattering and differences in the size of objects. The spectroscopic output allows for scattering shifts, because the same object measured several times does not exactly produce the same spectrum. Problems found in the spectrum can be overcome by pre-processing the data, namely the scatter correction method. Scatter correction is used to reduce the physical properties in the spectrum so that the information obtained is relatively the same for each spectrum, produces good estimates, and can be interpreted well. One of the spectroscopic tools that utilize infrared light is a non-invasive blood glucose level measuring device. The output of the tool is the time domain and intensity spectrum. Each object from the resulting spectrum still has noise, so scatter correction can be applied to this data. The purpose of this study was to perform a loopy Orthogonal Signal Correction (OSC) scatter correction method on time domain spectrum data on intensity on a non-invasive blood glucose level measuring device. The OSC method uses the concept of orthogonality to the mean by drawing the intensity value, weighting it, calculating the vector loading and then making corrections to the initial intensity. Based on the analysis, the loopy OSC method is better than OSC because the convergence is more accurate, the mean difference is smaller, the variance is smaller and the value converges on all the values tested. Based on exploration and the average difference, the loopy OSC method is better able to form the same pattern for each replication. This also shows that an object that is measured repeatedly has been able to be identified as the same object.

IMPROVING THE QUANTIFICATION ACCURACY OF Tc-99m MIBI DUAL-PHASE PARATHYROID SPECT/CT: A MONTE CARLO SIMULATION STUDY

Objective: Quantitative parathyroid SPECT imaging is a technique used to assess Primary hyperparathyroidism that may have potential in the identification and differentiation of parathyroid lesions as well as the estimation of disease severity. Studying the effect of data acquisition parameters on the quantification error is important for maximizing the accuracy of this diagnostic technique. In this study we examine the effects of different data acquisition parameters, namely the type of collimator, scatter correction status and reconstruction iteration number on the quantification accuracy using computer simulation. Methods: The SIMIND Monte Carlo Simulation and CASToR iterative reconstruction program was used to simulate a commercially available SPECT camera (Siemens Symbia Intevo Gamma Camera) with a crystal size of 29.55cm and 128x128 matrix size. A digital cylindrical phantom filled with water was constructed. A 0.36 cm radius spherical adenoma filled with a uniform 1MBq radioactivity is placed within the phantom. Low-Energy High Resolution (LEHR) and Low Energy Ultra High Resolution (LEUHR) collimator models are tested. Along with the presence of Scatter correction and differing iteration numbers (x16, x32). An image FOV based calibration method was used to gather quantitative information and checked against the input radioactivity. Results: The presence of scatter correction caused a 15-20% relative improvement in quantification accuracy. The optimal number of iterations produced a 10% relative improvement. Overall, accuracies as good as 7% in estimated activity concentration could be observed. Conclusion: The optimization of parameters can provide a significant improvement in quantification accuracy.

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection.

Monitoring the biochemical pigment contents in individual plants is crucial for assessing their health statuses and physiological states. Fast, low-cost measurements of plants' biochemical traits have become feasible due to advances in multispectral imaging sensors in recent years. This study evaluated the field application of proximal multispectral imaging combined with feature selection and regressive analysis to estimate the biochemical pigment contents of poplar leaves. The combination of 6 spectral bands and 26 vegetation indices (VIs) derived from the multispectral bands was taken as the group of initial variables for regression modeling. Three variable selection algorithms, including the forward selection algorithm with correlation analysis (CORR), recursive feature elimination algorithm (RFE), and sequential forward selection algorithm (SFS), were explored as candidate methods for screening combinations of input variables from the 32 spectral-derived initial variables. Partial least square regression (PLSR) and nonlinear support vector machine regression (SVR) were both applied to estimate total chlorophyll content (Chla+b) and carotenoid content (Car) at the leaf scale. The results show that the nonlinear SVR prediction model based on optimal variable combinations, selected by SFS using multiple scatter correction (MSC) preprocessing data, achieved the best estimation accuracy and stable prediction performance for the leaf pigment content. The Chla+b and Car models developed using the optimal model had R2 and RMSE predictive statistics of 0.849 and 0.825 and 5.116 and 0.869, respectively. This study demonstrates the advantages of using a nonlinear SVR model combined with SFS variable selection to obtain a more reliable estimation model for leaf biochemical pigment content.