Pseudo-color Map Research Articles

Non-Destructive Detection and Visualization of Chlorophyll Content in Cherry Tomatoes Based on Hyperspectral Technology and Machine Learning

The cherry tomato has an important economic value and an increasingly broad market, and the chlorophyll content of cherry tomato leaves can directly reflect the plant’s photosynthetic ability, thus indirectly reflecting its growth status. Therefore, this paper proposes a regression detection method for chlorophyll in cherry tomato leaves by combining machine learning and hyperspectral technology to realize non-destructive, fast, and more accurate detection. Firstly, Moving-Average (MA) preprocessing was chosen as the pretreatment method for this paper, and three regression models of principal component regression (PCR), random forest (RF), and partial least squares regression (PLSR) were established with leaf chlorophyll under different nitrogen concentrations. The CARS_PLSR algorithm has the highest prediction accuracy with accuracy, precision, RMSEC, and RMSEP of 0.8790, 0.9187, 2.9581, and 2.5578, respectively. The study examined the impact of various nitrogen concentrations on the chlorophyll content of cherry tomato leaves, and it was found that the high concentration of nitrogen inhibited the SPAD value of cherry tomato leaves more than that of the low concentration, and the optimal concentration of nitrogen fertilization for tomatoes was 300 mg·L−1. Finally, a regression model was established by using CARS-PLSR combined with the pseudo-color map technology, and a distribution map of chlorophyll content in different SPAD value gradients of cherry tomato leaves was obtained, which could visualize the distribution of chlorophyll and its distribution sites in the leaves and understand the growth status of cherry tomatoes. The distribution of chlorophyll content in different SPAD values of cherry tomato leaves was obtained by using the CARS-PLSR regression model combined with pseudo-color map technology, which can visualize the distribution of chlorophyll in the leaves and the parts of distribution and understand the growth condition of cherry tomatoes. Finally, the optimal model is applied in conjunction with a sprayer to automate fertilizer application.

Research on a Method for Measuring the Pile Height of Materials in Agricultural Product Transport Vehicles Based on Binocular Vision.

The advancement of unloading technology in combine harvesting is crucial for the intelligent development of agricultural machinery. Accurately measuring material pile height in transport vehicles is essential, as uneven accumulation can lead to spillage and voids, reducing loading efficiency. Relying solely on manual observation for measuring stack height can decrease harvesting efficiency and pose safety risks due to driver distraction. This research applies binocular vision to agricultural harvesting, proposing a novel method that uses a stereo matching algorithm to measure material pile height during harvesting. By comparing distance measurements taken in both empty and loaded states, the method determines stack height. A linear regression model processes the stack height data, enhancing measurement accuracy. A binocular vision system was established, applying Zhang's calibration method on the MATLAB (R2019a) platform to correct camera parameters, achieving a calibration error of 0.15 pixels. The study implemented block matching (BM) and semi-global block matching (SGBM) algorithms using the OpenCV (4.8.1) library on the PyCharm (2020.3.5) platform for stereo matching, generating disparity, and pseudo-color maps. Three-dimensional coordinates of key points on the piled material were calculated to measure distances from the vehicle container bottom and material surface to the binocular camera, allowing for the calculation of material pile height. Furthermore, a linear regression model was applied to correct the data, enhancing the accuracy of the measured pile height. The results indicate that by employing binocular stereo vision and stereo matching algorithms, followed by linear regression, this method can accurately calculate material pile height. The average relative error for the BM algorithm was 3.70%, and for the SGBM algorithm, it was 3.35%, both within the acceptable precision range. While the SGBM algorithm was, on average, 46 ms slower than the BM algorithm, both maintained errors under 7% and computation times under 100 ms, meeting the real-time measurement requirements for combine harvesting. In practical operations, this method can effectively measure material pile height in transport vehicles. The choice of matching algorithm should consider container size, material properties, and the balance between measurement time, accuracy, and disparity map completeness. This approach aids in manual adjustment of machinery posture and provides data support for future autonomous master-slave collaborative operations in combine harvesting.

Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images.

Fluorescence in situ hybridization (FISH) is widely regarded as the gold standard for evaluating human epidermal growth factor receptor 2 (HER2) status in breast cancer; however, it poses challenges such as the need for specialized training and issues related to signal degradation from dye quenching. Silver-enhanced in situ hybridization (SISH) serves as an automated alternative, employing permanent staining suitable for bright-field microscopy. Determining HER2 status involves distinguishing between "Amplified" and "Non-Amplified" regions by assessing HER2 and centromere 17 (CEN17) signals in SISH-stained slides. This study is the first to leverage deep learning for classifying Normal, Amplified, and Non-Amplified regions within HER2-SISH whole slide images (WSIs), which are notably more complex to analyze compared to hematoxylin and eosin (H&E)-stained slides. Our proposed approach consists of a two-stage process: first, we evaluate deep-learning models on annotated image regions, and then we apply the most effective model to WSIs for regional identification and localization. Subsequently, pseudo-color maps representing each class are overlaid, and the WSIs are reconstructed with these mapped regions. Using a private dataset of HER2-SISH breast cancer slides digitized at 40× magnification, we achieved a patch-level classification accuracy of 99.9% and a generalization accuracy of 78.8% by applying transfer learning with a Vision Transformer (ViT) model. The robustness of the model was further evaluated through k-fold cross-validation, yielding an average performance accuracy of 98%, with metrics reported alongside 95% confidence intervals to ensure statistical reliability. This method shows significant promise for clinical applications, particularly in assessing HER2 expression status in HER2-SISH histopathology images. It provides an automated solution that can aid pathologists in efficiently identifying HER2-amplified regions, thus enhancing diagnostic outcomes for breast cancer treatment.

Diffusion-Weighted Imaging in Minimal Hepatic Encephalopathy Using Mono-, Bi-, and Stretched Exponential Models

Background: Currently, there is no gold standard for diagnosing minimal hepatic encephalopathy (MHE). Diffusion-weighted imaging (DWI) can non-invasively evaluate changes in brain volume and damage to brain function. Objectives: The current study aims to evaluate changes in cerebral blood flow and brain function as predictors of MHE using DWI. Patients and Methods: Participants from October 2016 to October 2021 were scanned using a 3.0T superconductive MR machine (Discovery MR750, GE Medical Systems). Intravoxel incoherent motion DWI (IVIM-DWI) images of 30 patients with MHE and 30 controls were analyzed in a retrospective case-control study. The parameters of mono-, bi-, and stretched exponential models of the regions of interest, delineated from cerebral perfusion pseudo-color maps, were measured. The significance of the differences in parameter values between the groups was assessed using an independent t-test. Furthermore, the receiver operating characteristic curve was used to analyze the predictive efficiency of each parameter for MHE. Results: Compared to the control group, the distributed diffusion coefficient (DDC) of the bilateral frontal lobe, temporal lobe, occipital lobe, parietal lobe, cingulate gyrus, and thalamus in the MHE group was statistically different (P < 0.05). The pseudo-diffusion coefficient (D*) and DDC demonstrated good diagnostic efficacy for MHE. D* had the highest area under the curve (AUC) in the bilateral parietal lobe, bilateral cingulate gyrus, and left occipital lobe. In contrast, DDC had the highest AUC in the right occipital and bilateral temporal lobes. Conclusion: Intravoxel incoherent motion DWI is an imaging method that can detect MHE. In addition, D* and DDC are better diagnostic parameters for screening MHE. Intravoxel incoherent motion DWI will be helpful in uncovering deeper intrinsic pathophysiological mechanisms and improving predictive efficiency.

Assessment of food safety risk using machine learning-assisted hyperspectral imaging: Classification of fungal contamination levels in rice grain

A rapid and nondestructive assessment of food safety risk using machine learning-assisted hyperspectral imaging was developed for classification of fungal contamination in brown rice grain. Brown rice was inoculated with Penicillium. The fungal infected rice was then mixed with healthy rice to obtain 0 %, 5 %, 25 %, 50 % and 100 % (w/w) contamination of infected rice. Volatile compounds including pentamethyl-heptane, decane, dodecane, 3-octanone, and 1-octen-3-ol were found in fungal infected rice, as analyzed using gas chromatography-mass spectrometry. The HSI system was used to collect spectral reflectance and spatial data of the samples covering the wavelength range of 400–1000 nm. The hypercubed data were analyzed using machine learning algorithms, including principal component analysis (PCA), discriminant factor analysis (DFA) and support vector machine (SVM). Using PCA for data reduction, 3 principal components were extracted with a cumulative variance of 90.53 %. DFA (linear and quadratic algorithms) and SVM (linear, quadratic, cubic, and Gaussian algorithms) were then used to classify the samples. HSI integrated with Gaussian SVM gave 93.4% accuracy which was best for classifying rice with different percentages of contamination. The image analysis gave a pseudo-color distribution map which facilitated the visualization of the contaminated rice by presenting data in an uncomplicated image. The machine learning-assisted HSI can be used as a rapid, nondestructive and chemical-free tool for an assessment of food safety risk for rice grain.

Multi-Dimensional Fusion of Spectral and Polarimetric Images Followed by Pseudo-Color Algorithm Integration and Mapping in HSI Space

Spectral–polarization imaging technology plays a crucial role in remote sensing detection, enhancing target identification and tracking capabilities by capturing both spectral and polarization information reflected from object surfaces. However, the acquisition of multi-dimensional data often leads to extensive datasets that necessitate comprehensive analysis, thereby impeding the convenience and efficiency of remote sensing detection. To address this challenge, we propose a fusion algorithm based on spectral–polarization characteristics, incorporating principal component analysis (PCA) and energy weighting. This algorithm effectively consolidates multi-dimensional features within the scene into a single image, enhancing object details and enriching edge features. The robustness and universality of our proposed algorithm are demonstrated through experimentally obtained datasets and verified with publicly available datasets. Additionally, to meet the requirements of remote sensing tracking, we meticulously designed a pseudo-color mapping scheme consistent with human vision. This scheme maps polarization degree to color saturation, polarization angle to hue, and the fused image to intensity, resulting in a visual display aligned with human visual perception. We also discuss the application of this technique in processing data generated by the Channel-modulated static birefringent Fourier transform imaging spectropolarimeter (CSBFTIS). Experimental results demonstrate a significant enhancement in the information entropy and average gradient of the fused image compared to the optimal image before fusion, achieving maximum increases of 88% and 94%, respectively. This provides a solid foundation for target recognition and tracking in airborne remote sensing detection.

Macro-micro exploration on dynamic interaction between aflatoxigenic Aspergillus flavus and maize kernels using Vis/NIR hyperspectral imaging and SEM technology

Aspergillus flavus and its toxic metabolites-aflatoxins infect and contaminate maize kernels, posing a threat to grain safety and human health. Due to the complexity of microbial growth and metabolic processes, dynamic mechanisms among fungal growth, nutrient depletion of maize kernels and aflatoxin production is still unclear. In this study, visible/near infrared (Vis/NIR) hyperspectral imaging (HSI) combined with the scanning electron microscope (SEM) was used to elucidate the critical organismal interaction at kernel (macro-) and microscopic levels. As kernel damage is the main entrance for fungal invasion, maize kernels with gradually aggravated damages from intact to pierced to halved kernels with A. flavus were cultured for 0–120 h. The spectral fingerprints of the A. flavus-maize kernel complex over time were analyzed with principal components analysis (PCA) of hyperspectral images, where the pseudo-color score maps and the loading plots of the first three PCs were used to investigate the dynamic process of fungal infection and to capture the subtle changes in the complex with different hardness of the maize matrix. The dynamic growth process of A. flavus and the interactions of fungus-maize complexes were explained on a microscopic level using SEM. Specifically, fungus morphology, e.g., hyphae, conidia, and conidiophore (stipe) was accurately captured on the microscopic level, and the interaction process between A. flavus and nutrient loss from the maize kernel tissues (i.e., embryo, and endosperm) was described. Furthermore, the growth stage discrimination models based on PLSDA with the results of CCRC = 100 %, CCRV = 97 %, CCRIV = 93 %, and the prediction models of AFB1 based on PLSR with satisfactory performance (R2C = 0.96, R2V = 0.95, R2IV = 0.93 and RPD = 3.58) were both achieved. In conclusion, the results from both macro-level (Vis/NIR-HSI) and micro-level (SEM) assessments revealed the dynamic organismal interactions in A. flavus-maize kernel complex, and the detailed data could be used for modeling, and quantitative prediction of aflatoxin, which would establish a theoretical foundation for the early detection of fungal or toxin contaminated grains to ensure food security.

Translucency measurement system based on a polarized camera.

This paper proposes a measurement system capable of estimating the transmittance and haze values of a composite object. The system, comprising a polarized camera, linear polarizer, and backlight, was calibrated to obtain four phase polarization images. Forty-one samples, which covered a wide range of transmittance and haze values, were manufactured to assist in correlating the polarization images and the referenced ground truth from the BKY-Gardner instrument. After the data regression, two linear equations were selected to estimate the transmittance and haze values of transparent objects. The verification experiment for 52 samples demonstrated that the proposed method accurately estimated the transmittance of the samples with a coefficient of determination (R 2) as high as 0.96 and an average error of less than 4.1%. The haze estimation had an R 2 of 0.94 and an average error of 5.08%. Pseudo color maps were used to present the different transmittance and haze values of a single object. The proposed system can perform image-based translucency measurements and obtain individual values of a composite object.

Prediction of moisture content of Agaricus bisporus slices as affected by vacuum freeze drying using hyperspectral imaging

Moisture content (MC) is a crucial indicator used for assessing the degree of freeze-drying (FD) of Agaricus bisporus. This study illustrated a novel approach to quickly and visually detect MC in A. bisporus during FD using hyperspectral imaging (HSI) system along with several spectral preprocessing methods and models. The proposed approach employs a support vector machine (SVM) to establish a quantitative function between the physical indicator and the spectra obtained from the acquired hyperspectral images in the full mean spectral range. In the study stability competitive adaptive reweighted sampling (SCARS) was also used to choose key wavelengths most relevant to MC. Multiplicative scattering correction (MSC) was used to improve the precision and robustness of models. Moreover, SCARS-MSC-SVM was selected as the most appropriate model whereby, the values of RC2, RCV2, RP2 and RPD were 0.9281, 0.9025, 0.8026, and 2.08, respectively. Furthermore, pseudo-color maps were developed to illustrate color changes, and gradual MC decrease from the edge of the mushroom to the core during the FD process, enabling monitoring of the processing progress. Results demonstrated the potential of HSI to rapidly, accurately, non-destructively, and visually display the MC of A. bisporus during the FD process.

Visual detection of microplastics using Raman spectroscopic imaging.

As a new type of pollutant in the marine environment and terrestrial ecosystems, microplastics have attracted widespread attention. Assessing the ecological risk of microplastics relies on accurately detecting small-sized particles in the environment. Microplastics exhibit unique "fingerprint" characteristics in Raman spectroscopy, making them suitable for rapid identification. In this study, we achieved visualization of microplastics through pseudo-color images generated by Raman spectroscopy imaging. Pseudo-color imaging maps were generated by selecting characteristic peaks and the classical least-squares fitting method was used to visually represent the distribution of different microplastics. The study explored the potential of Raman spectroscopy and its mapping mode in distinguishing various types of mixed microplastics and demonstrated that this approach can identify microplastics in complex environmental samples. Specifically, a cloud-point extraction followed by membrane filtration method was successfully applied to identifying mixed-component microplastics. In summary, the category, quantity, location, and differentiation of microplastics can be accurately analyzed by Raman spectroscopy, which provides a basis for assessing their ecological risk.

Analysis of the posterior cerebral perfusion status and clinical prognostic value in chronic unilateral middle cerebral artery occlusion using SWAN combined with 3D-ASL.

To investigate the predictive value of T2 star-weighted angiography (SWAN) combined with 3-dimensional (3D) arterial spin labeling (3D-ASL) to assess cerebral perfusion status and clinical prognosis in chronic unilateral middle cerebral artery (MCA) M1 occlusion. This study included 55 patients diagnosed with chronic unilateral MCA M1 occlusion using 3D time-of-flight magnetic resonance angiography between January 2018 and July 2022. Based on the prominent vessel sign (PVS) shown in the SWAN sequence, the patients were divided into PVS-positive (n = 26) and PVS-negative (n = 29) groups. Cerebral blood flow (CBF) was selected in the affected regions of the frontal, parietal, and temporal lobes (regions of interest = 200 ± 20 mm2) using pseudo-color maps in the 3D-ASL sequence. Each patient was followed up for ischemic cerebrovascular disease within 12 months of diagnosis. The collected data were statistically analyzed to evaluate the predictive value of SWAN and 3D-ASL for the clinical prognosis of patients with chronic unilateral MCA M1 occlusion. Patients were divided into 2 groups based on the occurrence of an ischemic cerebrovascular event within 12 months (ischemic cerebrovascular event [acute ischemic stroke + transient ischemic attack] and non-ischemic cerebrovascular event groups, including 30 and 25 cases, respectively). The incidence of ischemic cerebrovascular events within 12 months was significantly higher in the PVS-positive group than in the PVS-negative group (92.31% vs 20.69%). Furthermore, the CBF values of the affected frontal, parietal, and temporal lobes were significantly lower in the ischemic cerebrovascular event group than in the non-ischemic cerebrovascular event group (P < .05). According to the receiver operating characteristic curve, the CBF values of the affected frontal, parietal, and temporal lobes in patients with chronic unilateral MCA M1 occlusion strongly correlated with ischemic cerebrovascular disease within 12 months. PVS-negative display and good collateral circulation were closely related to clinical prognosis in patients with chronic unilateral MCA M1 occlusion.

The montage method improves the classification of suspected acute ischemic stroke using the convolution neural network and brain MRI.

This study investigated the usefulness of the montage method that combines four different magnetic resonance images into one images for automatic acute ischemic stroke (AIS) diagnosis with deep learning method. The montage image was consisted from diffusion weighted image (DWI), fluid attenuated inversion recovery (FLAIR), arterial spin labeling (ASL), and apparent diffusion coefficient (ASL). The montage method was compared with pseudo color map (pCM) which was consisted from FLAIR, ASL and ADC. 473 AIS patients were classified into four categories: mechanical thrombectomy, conservative therapy, hemorrhage, and other diseases. The results showed that the montage image significantly outperformed pCM in terms of accuracy (montage image = 0.76 ± 0.01, pCM = 0.54 ± 0.05) and the area under the curve (AUC) (montage image = 0.94 ± 0.01, pCM = 0.76 ± 0.01). This study demonstrates the usefulness of the montage method and its potential for overcoming the limitations of pCM.

Quantitative Analysis of the Concentration of Trifluridine in Tumor Hypoxic Regions Using a Novel Platform Combining Functional Endoscopy and Mass Spectrometry.

Hypoxic regions in solid tumors are highly resistant to drugs and thus represents an obstacle in drug discovery. Currently, however, there are technical barriers in sampling human hypoxic tumors and examining drug delivery with high sensitivity and accuracy. Herein, we present a new platform combining functional endoscopy and highly sensitive liquid chromatography-mass spectrometry (LC-MS) to assess drug delivery to hypoxic regions. Because oxygen saturation endoscopic imaging (OXEI), a functional endoscopy, can evaluate lesions and hypoxia in real-time by simultaneously acquiring a pseudocolor map of oxygen saturation and conventional endoscopic images, this platform can be used to evaluate drug delivery with human samples from hypoxic regions. As the first clinical application of this platform, the relationship between hypoxic regions and the concentration of trifluridine (FTD) incorporated into DNA was evaluated in patients with advanced gastric cancer treated with FTD/tipiracil (FTD/TPI; n = 13) by obtaining and analysis of tissue samples by OXEI and LC-MS and vascular maturity index by CD31/α-SMA staining ex vivo. The results showed that the concentration of FTD was significantly higher in the normoxic region than in the hypoxic region (P < 0.05) and there were significantly more immature vessels in hypoxic regions than in normoxic regions (P < 0.05). These results indicate that the platform was sufficiently sensitive to evaluate differences in drug anabolism in different oxygenic regions of human tumor tissue. This new platform allows quantitative drug analysis in hypoxic regions and is expected to initiate a new era of drug discovery and development.

Using satellite multi-angle polarization measurements to characterize atmospheric aerosol above Bohai Bay

The paper analyzes data from the PARASOL optical multi-angle polarization radiometer over the waters of Bohai Bay under various atmospheric conditions and different seawater optical types. The study considered cases of clear atmosphere, haze, dust aerosol, and cloud coverage. The waters of Bohai Bay were categorized into areas heavily influenced by river inflows and relatively clear waters. By utilizing PARASOL data, the degree of polarization (DoP) values of optical radiation at scattering angles of about 90° between incident solar radiation and recorded radiation were determined. Appropriate scatterplots were created using measurements from the 490, 670, and 865 nm bands. Polarimetric pseudo-color maps were presented to classify various atmospheric states. The scatterplots successfully identified atmospheric dust, dust in clouds, haze, and water areas with high levels of suspended particles. The results obtained are consistent with the experience of using the Umov effect to study dust aerosol, which consists in the negative correlation between the maximum polarization of radiation and geometric albedo. The presence of suspended particles in water led to decrease in correlation coefficients between analyzed DoP at different wavelengths within the investigated sea area. The strong influence of river inflows on Bohai Bay in polarimetric data was observed only under clean atmospheric conditions.

Image recognition model of pipeline magnetic flux leakage detection based on deep learning

Abstract Deep learning algorithm has a wide range of applications and excellent performance in the field of engineering image recognition. At present, the detection and recognition of buried metal pipeline defects still mainly rely on manual work, which is inefficient. In order to realize the intelligent and efficient recognition of pipeline magnetic flux leakage (MFL) inspection images, based on the actual demand of MFL inspection, this paper proposes a new object detection framework based on YOLOv5 and CNN models in deep learning. The framework first uses object detection to classify the targets in MFL images and then inputs the features containing defects into a regression model based on CNN according to the classification results. The framework integrates object detection and image regression model to realize the target classification of MFL pseudo color map and the synchronous recognition of metal loss depth. The results show that the target recognition ability of the model is good, its precision reaches 0.96, and the mean absolute error of the metal loss depth recognition result is 1.14. The framework has more efficient identification ability and adaptability and makes up for the quantification of damage depth, which can be used for further monitoring and maintenance strategies.

Multi-parameter optical performance monitoring based on single-channel convolutional neural network

For the first time, a combination of grayscale maps and single-channel convolutional neural networks (CNN) is used in the direct detection optical performance monitoring (OPM) technique. Due to the faster monitoring speed of the direct detection OPM technique, it is very suitable for intermediate nodes of optical networks. The OPM technique proposed in this paper is an improvement based on the previous asynchronous delay-tap plot (ADTP) techniques. By reducing the redundant color channel information, the training process of the ADTP feature-based monitoring model is improved. In the simulation stage, three high-order modulated signals, 16quadrature amplitude modulation (QAM), 32QAM and 64QAM, are used as sample signals. The ADTP color maps, ADTP pseudo-color maps and ADTP grayscale maps generated by these three modulated signals with different signal-to-noise ratios and cumulative dispersion (CD) are collected. The accuracy of the monitoring model based on these three feature maps is close to 100% for both cumulative dispersion identification and signal modulation formats identification (MFI). However, the monitoring models based on grayscale maps and pseudo-color maps perform slightly better in estimating optical signal-to-noise ratio (OSNR) compared to the monitoring models based on color maps. And the grayscale map-based model slightly outperforms the other two models in terms of training complexity and monitoring speed. The superiority of grayscale maps and single-channel convolutional neural networks compared to previous ADTP-based OPM techniques is demonstrated.

Nondestructive detection of lipid oxidation in frozen pork using hyperspectral imaging technology

Lipid oxidation is an important cause of pork quality degradation during freezing. Traditional chemical methods are time-consuming and destructive. In this paper, two hyperspectral imaging (HSI) techniques, including visible near-infrared (vis-NIR HSI) (400–1002 nm) and fluorescence (F-HSI) (400–1002 nm), were tested for non-destructive detection of lipid oxidation in pork. Two types of hyperspectral image data were collected from pork samples with 0–9 freeze-thaw cycles. The model performance based on the two spectra data was then tested by three multivariate analysis methods of partial least squares regression, support vector regression and Gaussian process regression (GPR). It was found that the GPR models using vis-NIR HSI and F-HSI acquired optimal prediction results of R2p = 0.9697, RMSEP= 0.0184 mg/kg and R2p = 0.9726, RMSEP= 0.0182 mg/kg, respectively. The results showed that the two techniques have shown reliable performance in predicting TBARS, and the performance of F-HSI was slightly superior to vis-NIR HSI. A pseudo-color map of TBARS was drawn using the F-HSI model to provide a visual screening method for lipid oxidation in pork. Moreover, another batch of pork with different freeze-thaw cycles (0–5 cycles) was successfully quantified and visualized for TBARS content using the F-HSI model. It demonstrated the feasibility of using F-HSI for quantitative monitoring of lipid oxidation in pork.

Towards quantitative in vivo dosimetry using x-ray acoustic computed tomography.

Radiation dosimetry is essential for radiation therapy (RT) to ensure that radiation dose is accurately delivered to the tumor. Despite its wide use in clinical intervention, the delivered radiation dose can only be planned and verified via simulation. This makes precision radiotherapy challenging while in-line verification of the delivered dose is still absent in the clinic. X-ray-induced acoustic computed tomography (XACT) has recently been proposed as an imaging tool for in vivo dosimetry. Most of the XACT studies focus on localizing the radiation beam. However, it has not been studied for its potential for quantitative dosimetry. The aim of this study was to investigate the feasibility of using XACT for quantitative in vivo dose reconstruction during radiotherapy. Varian Eclipse system was used to generate simulated uniform and wedged 3D radiation field with a size of 4 cm 4 cm. In order to use XACT for quantitative dosimetry measurements, we have deconvoluted the effects of both the x-ray pulse shape and the finite frequency response of the ultrasound detector. We developed a model-based image reconstruction algorithm to quantify radiation dose in vivo using XACT imaging, and universal back-projection (UBP) reconstruction is used as comparison. The reconstructed dose was calibrated before comparing it to the percent depth dose (PDD) profile. Structural similarity index matrix (SSIM) and root mean squared error (RMSE) are used for numeric evaluation. Experimental signals were acquired from 4 cm 4 cm radiation field created by Linear Accelerator (LINAC) at depths of 6, 8, and 10 cm beneath the water surface. The acquired signals were processed before reconstruction to achieve accurate results. Applying model-based reconstruction algorithm with non-negative constraints successfully reconstructed accurate radiation dose in 3D simulation study. The reconstructed dose matches well with the PDD profile after calibration in experiments. The SSIMs between the model-based reconstructions and initial doses are over 85%, and the RMSEs of model-based reconstructions are eight times lower than the UBP reconstructions. We have also shown that XACT images can be displayed as pseudo-color maps of acoustic intensity, which correspond to different radiation doses in the clinic. Our results show that the XACT imaging by model-based reconstruction algorithm is considerably more accurate than the dose reconstructed by UBP algorithm. With proper calibration, XACT is potentially applicable to the clinic for quantitative in vivo dosimetry across a wide range of radiation modalities. In addition, XACT's capability of real-time, volumetric dose imaging seems well-suited for the emerging field of ultrahigh dose rate "FLASH" radiotherapy.

ACCURATE CELL SEGMENTATION IN BLOOD SMEAR IMAGES BASED ON COLOR ANALYSIS AND CNN MODELS

Abstract. Nowadays, automated blood cell evaluation play a major role in the classification and diagnosis of diseases. Despite the many possible ways to segment blood cells, the recognition efficiency remains insufficient, especially when different cell types overlap. Also, one should not forget about the cells structure complexity. Image segmentation and image classification are the main stages of this problem. At the same time, segmentation of blood smear images is considered the most important stage in automated disease detection systems. Often cell segmentation in blood smear images is performed as a separate mapping for white blood cells and red blood cells. We propose another problem statement that uses the capabilities of supervised and unsupervised CNNs for the semantic segmentation of objects of different sizes and shapes. CNN has encoder-decoder architecture and builds a pseudo-color map. We tested several CNN models using different color spaces converting initial images from RGB to Lab, HSV and CMYK color spaces and obtained promising experimental results for several microscopic datasets such as CellaVision DM96, All-IDB and Blood Cell Detection.

Nondestructive detection of nutritional parameters of pork based on NIR hyperspectral imaging technique

Nondestructive detection of the nutritional parameters of pork is of great importance. This study aimed to investigate the feasibility of applying hyperspectral image technology to detect the nutrient content and distribution of pork nondestructively. Hyperspectral cubes of 100 pork samples were collected using a line-scan hyperspectral system, the effects of different preprocessing methods on the modeling effects were compared and analyzed, the feature wavelengths of fat and protein were extracted, and the full-wavelength model was optimized using the regressor chains (RC) algorithm. Finally, pork's fat, protein, and energy value distributions were visualized using the best prediction model. The results showed that standard normal variate was more effective than other preprocessing methods, the feature wavelengths extracted by the competitive adaptive reweighted sampling algorithm had better prediction performance, and the protein model prediction performance was optimized after using the RC algorithm. The best prediction models were developed, with the correlation coefficient of prediction (RP) = 0.929, the root mean square error in prediction (RMSEP) = 0.699% and residual prediction deviation (RPD) = 2.669 for fat, and RP = 0.934, RMSEP = 0.603% and RPD = 2.586 for protein. The pseudo-color maps were helpful for the analysis of nutrient distribution in pork. Hyperspectral image technology can be a fast, nondestructive, and accurate tool for quantifying the composition and assessing the distribution of nutrients in pork.