Scatter Correction Research Articles

Nondestructive detection of mango soluble solid content in hyperspectral imaging based on multi-combinatorial feature wavelength selection

AbstractThis paper explores the prediction of the soluble solid content (SSC) in the visible and near-infrared (400–1,000 nm) regions of Baise mango. Hyperspectral images of Baise mangoes with wavelengths of 400–1,000 nm were obtained using a hyperspectral imaging system. Multiple scatter correction (MSC) was chosen to remove the effect of noise on the accuracy of the partial least squares (PLS) regression model. On this basis, the characteristic wavelengths of mango SSC were selected using the competitive adaptive reweighted sampling (CARS), genetic algorithm (GA), uninformative variable elimination (UVE), and combined CARS + GA-SPA, CARS + UVE-SPA, and GA + UVE-SPA characteristic wavelength methods. The results show that the combined MSC-CARS + GA-SPA-PLS algorithm can reduce redundant information and improve the computational efficiency, so it is an effective method to predict the SSC of mangoes.

Differential privacy preserved federated transfer learning for multi-institutional 68Ga-PET image artefact detection and disentanglement

PurposeImage artefacts continue to pose challenges in clinical molecular imaging, resulting in misdiagnoses, additional radiation doses to patients and financial costs. Mismatch and halo artefacts occur frequently in gallium-68 (68Ga)-labelled compounds whole-body PET/CT imaging. Correcting for these artefacts is not straightforward and requires algorithmic developments, given that conventional techniques have failed to address them adequately. In the current study, we employed differential privacy-preserving federated transfer learning (FTL) to manage clinical data sharing and tackle privacy issues for building centre-specific models that detect and correct artefacts present in PET images.MethodsAltogether, 1413 patients with 68Ga prostate-specific membrane antigen (PSMA)/DOTA-TATE (TOC) PET/CT scans from 3 countries, including 8 different centres, were enrolled in this study. CT-based attenuation and scatter correction (CT-ASC) was used in all centres for quantitative PET reconstruction. Prior to model training, an experienced nuclear medicine physician reviewed all images to ensure the use of high-quality, artefact-free PET images (421 patients’ images). A deep neural network (modified U2Net) was trained on 80% of the artefact-free PET images to utilize centre-based (CeBa), centralized (CeZe) and the proposed differential privacy FTL frameworks. Quantitative analysis was performed in 20% of the clean data (with no artefacts) in each centre. A panel of two nuclear medicine physicians conducted qualitative assessment of image quality, diagnostic confidence and image artefacts in 128 patients with artefacts (256 images for CT-ASC and FTL-ASC).ResultsThe three approaches investigated in this study for 68Ga-PET imaging (CeBa, CeZe and FTL) resulted in a mean absolute error (MAE) of 0.42 ± 0.21 (CI 95%: 0.38 to 0.47), 0.32 ± 0.23 (CI 95%: 0.27 to 0.37) and 0.28 ± 0.15 (CI 95%: 0.25 to 0.31), respectively. Statistical analysis using the Wilcoxon test revealed significant differences between the three approaches, with FTL outperforming CeBa and CeZe (p-value < 0.05) in the clean test set. The qualitative assessment demonstrated that FTL-ASC significantly improved image quality and diagnostic confidence and decreased image artefacts, compared to CT-ASC in 68Ga-PET imaging. In addition, mismatch and halo artefacts were successfully detected and disentangled in the chest, abdomen and pelvic regions in 68Ga-PET imaging.ConclusionThe proposed approach benefits from using large datasets from multiple centres while preserving patient privacy. Qualitative assessment by nuclear medicine physicians showed that the proposed model correctly addressed two main challenging artefacts in 68Ga-PET imaging. This technique could be integrated in the clinic for 68Ga-PET imaging artefact detection and disentanglement using multicentric heterogeneous datasets.

Dual-energy head cone-beam CT using a dual-layer flat-panel detector: Hybrid material decomposition and a feasibility study.

Flat panel detector (FPD) based cone-beam computed tomography (CT) has made tremendous progress in the last two decades, with many new and advanced medical and industrial applications keeping emerging from diagnostic imaging and image guidance for radiotherapy and interventional surgery. The current cone-beam CT (CBCT), however, is still suboptimal for head CT scan which requires a high standard of image quality. While the dual-layer FPD technology is under extensive development and is promising to further advance CBCT from qualitative anatomic imaging to quantitative dual-energy CT, its potential of enabling head CBCT applications has not yet been fullyinvestigated. The relatively moderate energy separation from the dual-layer FPD and the overall low signal level especially at the bottom-layer detector, could raise significant challenges in performing high-quality dual-energy material decomposition (MD). In this work, we propose a hybrid, physics and model guided, MD algorithm that attempts to fully use the detected x-ray signals and prior-knowledge behind head CBCT using dual-layer FPD. Firstly, a regular projection-domain MD is performed as initial results of our approach and for comparison as conventional method. Secondly, based on the combined projection, a dual-layer multi-material spectral correction (dMMSC) is applied to generate beam hardening free images. Thirdly, the dMMSC corrected projections are adopted as a physics-model based guidance to generate a hybrid MD. A set of physics experiments including fan-beam scan and cone-beam scan using a head phantom and a Gammex Multi-Energy CT phantom are conducted to validate our proposedapproach. The combined reconstruction could reduce noise by about 10% with no visible resolution degradation. The fan-beam studies on the Gammex phantom demonstrated an improved MD performance, with the averaged iodine quantification error for the 5-15 mg/ml iodine inserts reduced from about 5.6% to 3.0% by the hybrid method. On fan-beam scan of the head phantom, our proposed hybrid MD could significantly reduce the streak artifacts, with CT number nonuniformity (NU) in the selected regions of interest (ROIs) reduced from 23 Hounsfield Units (HU) to 4.2 HU, and the corresponding noise suppressed from 31 to 6.5 HU. For cone-beam scan, after scatter correction (SC) and cone-beam artifact reduction (CBAR), our approach can also significantly improve image quality, with CT number NU in the selected ROI reduced from 24.2 to 6.6 HU and the noise level suppressed from 22.1 to 8.2HU. Our proposed physics and model guided hybrid MD for dual-layer FPD based head CBCT can significantly improve the robustness of MD and suppress the low-signal artifact. This preliminary feasibility study also demonstrated that the dual-layer FPD is promising to enable head CBCT spectralimaging.

Hyperspectral Estimation of SPAD Value of Cotton Leaves under Verticillium Wilt Stress Based on GWO–ELM

Rapid and non-destructive estimation of the chlorophyll content in cotton leaves is of great significance for the real-time monitoring of cotton growth under verticillium wilt (VW) stress. The spectral reflectance of healthy and VW cotton leaves was determined using hyperspectral technology, and the original spectra were processed using Savitzky–Golay (SG) smoothing, and on its basis through mean centering, standard normal variate (SG-SNV), multiplicative scatter correction (SG-MSC), reciprocal second-order differentiation, and logarithmic second-order differentiation ([lg(SG)]″) preprocessing operations. The characteristic bands were selected based on the correlation coefficient, vegetation index, successive projection algorithm (SPA), and competitive adaptive reweighted sampling (CARS). The single-factor model, back propagation neural network of particle swarm optimization algorithm, and extreme learning machine (ELM) of a grey wolf optimizer (GWO) algorithm were constructed to compare and explore the ability of each model to estimate the soil plant analysis development (SPAD) value of cotton under VW stress. The results showed that spectral pretreatment could improve the correlation between characteristic bands and SPAD values. SG-MSC and SG-SNV showed better changes in the five pretreatments, and the maximum correlation coefficients of healthy and VW cotton leaves were higher than 0.74. Compared with SPA, the accuracy of model estimation based on CARS-extracted characteristic bands was higher, and the estimation accuracy of the multi-factor model was better than that of the single-factor model under each pretreatment. For healthy cotton leaves, [lg(SG)]″–CARS–GWO–ELM was the optimal model, with a modeling and validation set R2 of 0.956 and 0.887, respectively. For VW cotton leaves, SG-MSC–CARS–GWO–ELM was the optimal model, with a modeling and validation set R2 of 0.832 and 0.824, respectively. Therefore, the GWO–ELM model constructed under different pretreatments combined with characteristic extraction methods can be used for the estimation of leaf SPAD values under VW stress to dynamically monitor VW stress in cotton and provide a theoretical reference for precision agriculture.

Rapid detection of maize seed germination rate based on Gaussian process regression with selection kernel function

Near-infrared spectroscopy (NIR) detection technology enables nondestructive analysis of samples. To achieve fast detection of maize seed germination rates using NIR spectroscopy, 245 samples of maize seeds from three different varieties were purchased from the market and subjected to artificial aging to obtain maize seeds with varying levels of vigor. NIR spectroscopy was collected for each sample, and germination experiments were performed. The Monte Carlo cross-validation method was employed to eliminate 12 outliers, and the baseline correction method along with multiplicative scatter correction (MSC) was applied to the NIR. Partial least squares (PLS), support vector machine (SVM) models, and Gaussian process regression (GPR) models based on different kernel functions were established for detecting maize germination rates. Through comparison of the results of different models, it was found that the GPR model based on the Matern32 kernel function performed best. The R² values for the training and testing sets of this model were 0.9727 and 0.9599, respectively. Experimental results showed that the Matern32-GPR model exhibited greater stability and superior capability in detecting maize seed germination rates. This method can provide a reference for other applications based on NIR detection.

A quantitative CBCT pipeline based on 2D antiscatter grid and grid-based scatter sampling for image-guided radiation therapy.

Quantitative accuracy is critical for expanding the role of cone beam CT (CBCT) imaging from target localization to quantitative treatment monitoring and plan adaptations in radiation therapy. Despite advances in CBCT image quality improvement methods, quantitative accuracy gap between CBCT and multi-detector CT (MDCT) remains. In this work, a physics-driven approach was investigated that combined robust scatter rejection, raw data correction and iterative image reconstruction to further improve CBCT image quality and quantitative accuracy, referred to as quantitative CBCT (qCBCT). QCBCT approach includes tungsten 2D antiscatter grid hardware, residual scatter correction with grid-based scatter sampling, image lag, and beam hardening correction for offset detector geometry linac-mounted CBCT. Images were reconstructed with iterative image reconstruction to reduce image noise. qCBCT was evaluated using a variety of phantoms to investigate the effect of object size and its composition on image quality, and image quality was benchmarked against clinical CBCT and gold standard MDCT images used for treatment planning. QCBCT provided statistically significant improvement in CT number accuracy and reduced image artifacts when compared to clinical CBCT images. When compared to gold standard MDCT, mean HU errors in qCBCT and clinical CBCT were 17±9 and 38±29 HU, respectively. Magnitude of phantom size dependent HU variations were comparable between MDCT and qCBCT images. With iterative reconstruction, contrast-to-noise ratio improved by 25% when compared to clinical CBCT protocols. Combination of novel scatter suppression techniques and other data correction methods in qCBCT provided CT number accuracy comparable to gold standard MDCT used for treatment planning. This approach may potentially improve CBCT's promise in fulfilling the tasks that demand high quantitative accuracy, such as online dose calculations and treatment response assessment, in image guided radiation therapy.

A methodological approach to preprocessing FTIR spectra of adulterated sesame oil.

Fourier transform infrared (FTIR) spectroscopy is established as an effective and fast method for the confirmation of the authenticity of food and among other, edible oils. However, no standard procedure is available for applying preprocessing as a vital step in obtaining accurate results from spectra. This study proposes a methodological approach to preprocessing FTIR spectra of sesame oil adulterated with vegetable oils (canola oil, corn oil, and sunflower oil). The primary preprocessing methods investigated are orthogonal signal correction (OSC), standard normal variate transformation (SNV), and extended multiplicative scatter correction (EMSC). Other preprocessing methods are used both as standalone methods and in combination with the primary preprocessing methods. The preprocessing results are compared using partial least squares regression (PLSR). OSC alone or with detrending were the most accurate in predicting the adulteration level of sesame oil, with a maximum coefficient of prediction (R2p) range of 0.910 to 0.971 for different adulterants.

Environmentally friendly method in determining the water content of coffee by NIR Spectroscopy

Coffee quality could be determined from several aspects, one of those is the water content inside. Along the storage, it must be low and for coffee export it must be below 12.5%. Nowadays, the determination of water content is conducted by the chemical method like the gravimetry method which spend time, destructive also can not represent all of the products. Therefore, it is not in line with the industries which need an actual measurement that could measure all of the products nondestructively and also keep considering the environment. This study aimed to develop a PLS model to determine the water content of green bean coffee, nondestructively. This study used green bean coffee from several region in Indonesia with a high range data concentration (7.18% - 12.16%), a NIR wavelength of 1000-2500 nm, followed by determination of water content using gravimetry method. After that, the NIR data was processed using data pretreatment such as normalization, first derivative, second derivative, multiple scatter correction and standard normal variate and followed by the calibration using PLS and validation. Result showed that NIR spectroscopy could be used to calculate the percentage of water inside coffee beans, indicated by high R value above 0.8% and high consistency above 90%.

Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study.

The challenges in cancer diagnosis underline the need for continued research and development of new diagnostic tools and methods. This study aims to explore an effective, noninvasive, and convenient diagnostic tool using urine based near-infrared spectroscopy (NIRS) analysis combined with machine learning algorithm. Urine samples were collected from a total of 327 participants, including 181 cancer cases and 146 healthy controls. These participants were randomly spit into train set (n=218) and test set (n=109). NIRS analysis (4,000 ∼10,000 cm-1) was performed for each sample in both train and test sets. Five pretreatment methods, including Savitzky-Golay (SG) smoothing, multiplicative scatter correction (MSC), baseline removal (BSL) with fitting polynomials to be used as baselines, the first derivative (DERIV1), and the second derivative (DERIV2), and combination with "scaling" and "center", were investigated. Then partial least-squares (PLS) and linear support-vector machine (SVM) classification models were established, and prediction performance was evaluated in test set. NIRS had greatly overlapping in peaks, and PCA analysis failed in separation between cancers and healthy controls. In modeling with urine based NIRS data, PLS model showed its highest prediction accuracy of 0.780, with DERIV2, "scaling" and "center" pretreatment, while linear SVM displayed its best prediction accuracy of 0.844, with raw NIRS. With optimization in SVM, the prediction accuracy could improve to 0.862, when the top 262 features were involved as variables. This pilot study combining urine based NIRS analysis and machine learning is effective and convenient that might facilitate in cancer diagnosis, encouraging further evaluation with a large-size multi-center study.

Identification of growth years for Puerariae Thomsonii Radix based on hyperspectral imaging technology and deep learning algorithm

Puerariae Thomsonii Radix (PTR) is not only widely used in disease prevention and treatment but is also an important raw material as a source of starch and other food. The growth years of PTR are closely related to its quality. The rapid and nondestructive identification of growth year is essential for the quality control of PTR and other traditional Chinese medicines. In this study, we proposed a convolutional neural network (CNN)-based classification framework in conjunction with hyperspectral imaging (HSI) technology for the rapid identification of the growth years of PTRs. Traditional treatment methods (i.e., multiplicative scatter correction, standard normal variate, and Savitzky-Golay smoothing) combined with machine learning algorithms (i.e., random forest, logistic regression, naive Bayes, and eXtreme gradient boost) were used as baseline models. Among them, the F1-score of CNN-based models based on PTRs’ outer surfaces was over 90%, outperforming all the other baseline models. These results showed that it was feasible to use a deep learning algorithm in conjunction with HSI technology to identify the growth years of PTR. This method provides a fast, nondestructive, and simple method of identifying the growth years of PTR. It can be easily applied to other scenarios, such as for the identification of the locality or years of growth for other traditional Chinese herbs.

Calibration of Proximate Content of Arabica Sidikalang Green Bean Coffee Using NIRS and PLS

Generally, coffee bean’s content measurement is conducted destructively, where it is known to be less effective. Measurement using the Near Infrared Spectroscopy (NIRS) method could be an alternative to a rapid determination of the chemical content non-destructively. The study aimed to obtain a partial least square (PLS) calibration model of water, lipid and carbohydrate content in Sidikalang Arabica green bean coffee. This method can predict the chemical content assisted with several data pretreatments, namely multiple scatter correction (MSC), standard normal variative (SNV), normalization, first derivative (dg1), second derivative (dg2), combination of dg 1 + MSC and combination of dg2 + MSC. Results showed that the best calibration model for water content was obtained using normalization with 6 PLS factor with r value of 0.574. moreover, the best calibration model in lipid content was obtained using MSC with 5 PLS factor with r value of 0.647, and the best calibration model for carbohydrate was using MSC with 6 PLS factors with r value of 0.563. The model obtained from this study is categorized into a moderate model and could be use in simulations with predictive values ​​with moderate accuracy. Generally, coffee bean’s content measurement is conducted destructively, where it is known to be less effective. Measurement using the Near Infrared Spectroscopy (NIRS) method could be an alternative to a rapid determination of the chemical content non-destructively. The study aimed to obtain a partial least square (PLS) calibration model of water, lipid and carbohydrate content in Sidikalang Arabica green bean coffee. This method can predict the chemical content assisted with several data pretreatments, namely multiple scatter correction (MSC), standard normal variative (SNV), normalization, first derivative (dg1), second derivative (dg2), combination of dg 1 + MSC and combination of dg2 + MSC. Results showed that the best calibration model for water content was obtained using normalization with 6 PLS factor with r value of 0.574. moreover, the best calibration model in lipid content was obtained using MSC with 5 PLS factor with r value of 0.647, and the best calibration model for carbohydrate was using MSC with 6 PLS factors with r value of 0.563. The model obtained from this study is categorized into a moderate model and could be use in simulations with predictive values ​​with moderate accuracy.

Scattering correction for samples with cylindrical domains measured with polarized infrared spectroscopy

Scattering artifacts are one of the most common effects distorting transmission spectra in Fourier-Transform Infrared spectroscopy. Their increased impact, strongly diminishing the quantitative and qualitative power of IR spectroscopy, is especially observed for structures with a size comparable to the radiation wavelength. To tackle this problem, a wide range of preprocessing techniques based on the Extended Multiplicative Scattering Correction method was developed, using physical properties to remove scattering presence in the spectra. However, until recently those algorithms were mostly focused on spherically shaped samples, for example, cells. Here, an algorithm for samples with cylindrical domains is described, with additional implementation of a linearly polarized light case, which is crucial for the growing field of polarized IR imaging and spectroscopy. An open-source code with GPU based implementation is provided, with a calculation time of several seconds per spectrum. Optimizations done to improve the throughput of this algorithm allow the application of this method into the standard preprocessing pipeline of small datasets.

Prediction of heavy metals in polluted mangrove soils in Brazil with the highest reported levels of mercury using near-infrared spectroscopy.

Infrared reflectance spectroscopy has demonstrated potential as a tool for monitoring and preventing contamination in different environments. The objective of this study was to evaluate the usage of near-infrared spectroscopy for predicting heavy-metal contamination in mangrove soils from the Botafogo River estuary located in Pernambuco State, Northeastern Brazil. These soils exhibit the highest mercury (Hg) levels ever reported for Brazilian mangrove soils. Sixty-one samples (obtained at depths ranging from 0 to 5cm) were collected and measured using near-infrared (1000-2500nm) reflectance spectroscopy. Preprocessing methods were applied, and partial least squares regression was used to build prediction models for attributes such as clay content, soil organic matter (SOM), pH, Eh, and concentrations of Cr, Cu, Hg, Ni, Pb, and Zn. The models were evaluated using root mean squared error (RMSE), the adjusted coefficient of determination (R2adj), bias, the ratio of performance to interquartile distance (RPIQ), and Lin's concordance correlation coefficient (CCC). The best outcomes were noted for concentrations of Cr, Cu, Hg, Ni, and Pb (RPIQ > 2.5 and R2adj > 0.80); second-best outcomes were found for Zn and SOM (RPIQ > 1.5 and R2adj > 0.70). Clay content, pH and Eh exhibited the poorest outcomes (RPIQ < 1.5). The importance of spectral preprocessing is highlighted, notably with Savitzky-Golay derivatives and Multiplicative Scatter Corrections, which boosted performance for most of the variables. Near-infrared spectroscopy can be efficiently used to predict Cr, Cu, Hg, Ni, Pb and SOM and represents a technique complementary to traditional analyses.

Hybrid method for accurate starch estimation in adulterated turmeric using Vis-NIR spectroscopy

Turmeric is widely used as a health supplement and foodstuff in South East Asian countries because of its medicinal benefits. Like several other plants and peppers, turmeric is prone to exploitation because of its economic value, rising consumer need, and essential food element that adds colour and flavour. Due to this, quick and comprehensive testing processes are needed to detect adulterants in turmeric. In this study, pure turmeric powders were mixed with starch in proportions ranging from 0 to 50% with a 1% variation to obtain different combinations. Reflectance spectra of pure turmeric and starch mixed samples were recorded using a JASCO-V770 spectrometer from 400 to 2050 nm. The recorded spectra were pre-processed using a Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV). The Savitzky-Golay (SG) filter was initially applied to these original (X), MSC, and SNV-corrected spectra. Secondly, the Extra Tree Regressor (ETR) feature selection method was employed to select the best features. Finally, principal component analysis (PCA) was used to reduce the dimension of the selected features. The stacked generalization method was applied to improve the performance of this work. Both regressors and classifier stacking techniques have been tested with different classification and regression methods. The K-Nearest Neighbours (KNN), Decision Tree (DT), and Random Forest (RF) models were used as base learners, and Logistic Regression (LRC) was used as a meta-model for classification and Linear Regression (LR) for regression analysis. The proposed method achieved the best regression performance with r 2 of 0.999, Root Mean Square Error (RMSE) of 0.206, Ratio of Performance to Deviation (RPD) of 73.73, and Range Error Ratio (RER) of 480.58, whereas 100% F1 score and Matthew’s Correlation Coefficient (MCC) classification performance.

基于可见/近红外高光谱成像无损预测猕猴桃可溶性固形物含量

Soluble solid content (SSC) is a major quality index of kiwifruits. Visible near-infrared (Vis/NIR) hyperspectral imaging with the genetic algorithm (GA) was adopted in this study to realize the non-destructive prediction of kiwifruit SSC. A laboratory Vis/NIR hyperspectral imaging system was established to collect the hyperspectral imaging of 120 kiwifruit samples at a range of 400–1100 nm. The average reflectance spectral data of the region of interest of the kiwifruit hyperspectral imaging were obtained after different preprocessing method, namely, Savitzky–Golay smoothing (SG), multiplicative scatter correction (MSC), and their combination method. The prediction models of partial least squares regression, multiple linear regression, and least squares support vector machine (LS-SVM) were built for determining kiwifruit SSC by using the average reflectance spectral data and effective feature wavelength variables selected by GA, respectively. The results show that SG+MSC is the best preprocessing method. The precisions of the prediction models built using the effective feature wavelength variables selected by GA are higher than that established using full average reflectance spectral data. The GA-LS-SVM prediction model has a best performance with correlation coefficient for prediction (R=0.932) and standard error of prediction (SEP=0.536° Bx) for predicting kiwifruit SSC. The prediction accuracy has been improved by 5.6% compared with that of the prediction models established by using the full-band reflectance spectral data. This study provides an effective method for non-destructive detection of kiwifruit SSC.

An unsupervised dual contrastive learning framework for scatter correction in cone-beam CT image

Purpose:Cone-beam computed tomography (CBCT) is widely utilized in modern radiotherapy; however, CBCT images exhibit increased scatter artifacts compared to planning CT (pCT), compromising image quality and limiting further applications. Scatter correction is thus crucial for improving CBCT image quality. Methods:In this study, we proposed an unsupervised contrastive learning method for CBCT scatter correction. Initially, we transformed low-quality CBCT into high-quality synthetic pCT (spCT) and generated forward projections of CBCT and spCT. By computing the difference between these projections, we obtained a residual image containing image details and scatter artifacts. Image details primarily comprise high-frequency signals, while scatter artifacts consist mainly of low-frequency signals. We extracted the scatter projection signal by applying a low-pass filter to remove image details. The corrected CBCT (cCBCT) projection signal was obtained by subtracting the scatter artifacts projection signal from the original CBCT projection. Finally, we employed the FDK reconstruction algorithm to generate the cCBCT image. Results:To evaluate cCBCT image quality, we aligned the CBCT and pCT of six patients. In comparison to CBCT, cCBCT maintains anatomical consistency and significantly enhances CT number, spatial homogeneity, and artifact suppression. The mean absolute error (MAE) of the test data decreased from 88.0623 ± 26.6700 HU to 17.5086 ± 3.1785 HU. The MAE of fat regions of interest (ROIs) declined from 370.2980 ± 64.9730 HU to 8.5149 ± 1.8265 HU, and the error between their maximum and minimum CT numbers decreased from 572.7528 HU to 132.4648 HU. The MAE of muscle ROIs reduced from 354.7689 ± 25.0139 HU to 16.4475 ± 3.6812 HU. We also compared our proposed method with several conventional unsupervised synthetic image generation techniques, demonstrating superior performance. Conclusions:Our approach effectively enhances CBCT image quality and shows promising potential for future clinical adoption.

Sorting of navel orange soluble solids content based on online near infrared spectroscopy

Abstract A rapid, nondestructive, and online detection of the internal quality of navel orange cannot only reduce the labor intensity, but also improve the economic benefits of the navel orange. In this paper, an online detection and sorting equipment is designed for navel orange. The transmission spectrum data of 1697 navel oranges are divided into the calibration, prediction, and validation sets, with a ratio of 14:3:3. Pre-processing methods such as first derivative (FD), second derivative (SD), standard normal variate transform (SNV), and multiplicative scatter correction (MSC) were chosen to process the spectra. Accordingly, the soluble solids content prediction model for navel oranges is established using standard normal variable transformation (SNV) and partial least squares (PLS). The determination coefficients (R 2) of the calibration set, prediction set, and validation set are 0.8476, 0.8326, and 0.8025, respectively. Moreover, the corresponding root mean square errors are 0.5097°Brix, 0.5590°Brix, and 0.6048°Brix, respectively. The residual predictive deviation (RPD) value is 2.4510 (i.e., greater than 2.0), indicating that the model performs accurate predictive simulations, and has high reliability. In addition, two classification methods based on the national standard method and the normal probability graph of the soluble solids content of navel oranges were used to classify navel oranges into three classes for online validation. 185 navel oranges were selected for online validation, in which the classification method based on the normal probability graph of the soluble solids content of navel oranges was more effective and its average sorting accuracy was 81.13 %. Likewise, the mean absolute error (MAE) is 0.4613°Brix. The experimental results show that the online sorting equipment possesses high sorting accuracy and can be practically used for actual postharvest processing.

Generative adversarial network-based attenuation correction for 99mTc-TRODAT-1 brain SPECT.

Attenuation correction (AC) is an important correction method to improve the quantification accuracy of dopamine transporter (DAT) single photon emission computed tomography (SPECT). Chang's method was developed for AC (Chang-AC) when CT-based AC was not available, assuming uniform attenuation coefficients inside the body contour. This study aims to evaluate Chang-AC and different deep learning (DL)-based AC approaches on 99mTc-TRODAT-1 brain SPECT using clinical patient data on two different scanners. Two hundred and sixty patients who underwent 99mTc-TRODAT-1 SPECT/CT scans from two different scanners (scanner A and scanner B) were retrospectively recruited. The ordered-subset expectation-maximization (OS-EM) method reconstructed 120 projections with dual-energy scatter correction, with or without CT-AC. We implemented a 3D conditional generative adversarial network (cGAN) for the indirect deep learning-based attenuation correction (DL-ACμ) and direct deep learning-based attenuation correction (DL-AC) methods, estimating attenuation maps (μ-maps) and attenuation-corrected SPECT images from non-attenuation-corrected (NAC) SPECT, respectively. We further applied cross-scanner training (cross-scanner indirect deep learning-based attenuation correction [cull-ACμ] and cross-scanner direct deep learning-based attenuation correction [call-AC]) and merged the datasets from two scanners for ensemble training (ensemble indirect deep learning-based attenuation correction [eDL-ACμ] and ensemble direct deep learning-based attenuation correction [eDL-AC]). The estimated μ-maps from (c/e)DL-ACμ were then used in reconstruction for AC purposes. Chang's method was also implemented for comparison. Normalized mean square error (NMSE), structural similarity index (SSIM), specific uptake ratio (SUR), and asymmetry index (%ASI) of the striatum were calculated for different AC methods. The NMSE for Chang's method, DL-ACμ, DL-AC, cDL-ACμ, cDL-AC, eDL-ACμ, and eDL-AC is 0.0406 ± 0.0445, 0.0059 ± 0.0035, 0.0099 ± 0.0066, 0.0253 ± 0.0102, 0.0369 ± 0.0124, 0.0098 ± 0.0035, and 0.0162 ± 0.0118 for scanner A and 0.0579 ± 0.0146, 0.0055 ± 0.0034, 0.0063 ± 0.0028, 0.0235 ± 0.0085, 0.0349 ± 0.0086, 0.0115 ± 0.0062, and 0.0117 ± 0.0038 for scanner B, respectively. The SUR and %ASI results for DL-ACμ are closer to CT-AC, Followed by DL-AC, eDL-ACμ, cDL-ACμ, cDL-AC, eDL-AC, Chang's method, and NAC. All DL-based AC methods are superior to Chang-AC. DL-ACμ is superior to DL-AC. Scanner-specific training is superior to cross-scanner and ensemble training. DL-based AC methods are feasible and robust for 99mTc-TRODAT-1 brain SPECT.

A Pilot Study of the Striatal Dopamine Transporter Levels in Kratom-Dependent and Normal Subjects Using 99mTc-TRODAT-1 Single Photon Emission Computed Tomography-Computed Tomography (SPECT-CT).

The study aims to elucidate the effects of kratom addiction on dopamine transporter (DAT) using[2-[[2-[[[3-(4-chlorophenyl)-8-methyl-8-azabicyclo[3.2.1]oct-2-yl]methyl](2-mercaptoethyl)amino]ethyl]amino]ethanethiolato(3-)-N2,N20,S2,S20]oxo-[1R-(exo-exo)]-[99mTc] technetium (99mTc-TRODAT-1) brain single photon emission computed tomography-computed tomography (SPECT-CT) in kratom-dependent and healthy subjects. We recruited 12 kratom-dependent subjects and 13 healthy men to participate in this study. Addiction, craving, depression, and cognitive scores were assessed. All subjects received a single bolus injection of 99mTc-TRODAT-1 with 914.1 MBq ± 65.5 of activity (mean ± SD). The brain SPECT-CT images were reconstructed using 3D ordered subset expectation maximization (3D-OSEM) along with attenuation correction (AC), scatter correction (SC), and resolution recovery (RR) with an iteration number of four and a subset of 10. The Cohen's Kappa interrater-reliability between two raters, the standardized uptake value of body weight (SUVBW), and the asymmetrical index percentage (AI%) were evaluated. Kappa statistics showed a fine agreement of abnormal 99mTc-TRODAT-1 uptake in the striatum region for the kratom-dependent group with the κ value of 0.69 (p = 0.0001), and the percentage of agreement for rater 1 and rater 2 was 56% and 64%, respectively. There was a reduction in average SUV in kratom-dependent subjects compared to healthy control subjects in the left caudate and left striatum (0.938 vs. 1.251, p = 0.014, and 1.055 vs. 1.29, p = 0.036, respectively). There was a significant difference in the AI% of the caudate region between the kratom-dependent group and the normal group (33% vs. 14%, p = 0.019). Our findings signify that kratom addiction, may cause a change in DAT level and the results can be confirmed using 99mTc-TRODAT-1 SPECT-CT.

Unsupervised deep learning framework for data-driven gating in positron emission tomography.

Physiological motion, such as respiratory motion, has become a limiting factor in the spatial resolution of positron emission tomography (PET) imaging as the resolution of PET detectors continue to improve. Motion-induced misregistration between PET and CT images can also cause attenuation correction artifacts. Respiratory gating can be used to freeze the motion and to reduce motion induced artifacts. In this study, we propose a robust data-driven approach using an unsupervised deep clustering network that employs an autoencoder (AE) to extract latent features for respiratory gating. We first divide list-mode PET data into short-time frames. The short-time frame images are reconstructed without attenuation, scatter, or randoms correction to avoid attenuation mismatch artifacts and to reduce image reconstruction time. The deep AE is then trained using reconstructed short-time frame images to extract latent features for respiratory gating. No additional data are required for the AE training. K-means clustering is subsequently used to perform respiratory gating based on the latent features extracted by the deep AE. The effectiveness of our proposed Deep Clustering method was evaluated using physical phantom and real patient datasets. The performance was compared against phase gating based on an external signal (External) and image based principal component analysis (PCA) with K-means clustering (Image PCA). The proposed method produced gated images with higher contrast and sharper myocardium boundaries than those obtained using the External gating method and Image PCA. Quantitatively, the gated images generated by the proposed Deep Clustering method showed larger center of mass (COM) displacement and higher lesion contrast than those obtained using the other two methods. The effectiveness of our proposed method was validated using physical phantom and real patient data. The results showed our proposed framework could provide superior gating than the conventional External method and Image PCA.