Pixel Intensity Values Research Articles

Optimizing time-of-flight of PET/CT image quality via penalty β value in Bayesian penalized likelihood reconstruction algorithm.

Optimizing the image quality of Positron Emission Tomography/Computed Tomography (PET/CT) systems is crucial for effective monitoring, diagnosis, and treatment planning in oncology. This study evaluates the impact of time-of-flight (TOF) on PET/CT performance, focusing on varying penalty β values within Q. Clear reconstruction algorithm. The study measured signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) using the Discovery MI PET/CT scanner and NEMA IQ phantom filled with the radiotracer fluorodeoxyglucose (18F-FDG). PET/CT scans were performed with and without TOF using β values of 100, 500, 1000, 1500, 2000, and 3000. Pixel intensity values were measured using ImageJ software, and SNR and CNR were calculated. Results indicated that increasing β values improved SNR and CNR for both non-TOF and TOF images. At a β value of 100, SNR and CNR increased across all sphere sizes (10mm, 13mm, 17mm, 22mm, 28mm, 37mm) when comparing non-TOF and TOF images. However, β values of 500 or higher led to decreased SNR and CNR, particularly in larger spheres (22mm, 28mm, 37mm), when TOF was utilized. These findings underscore the importance of optimizing β values and employing TOF reconstruction in PET/CT scans to achieve the highest possible image quality. In clinical practice, practitioners should adjust β values in accordance with routine protocols, considering the size of the target region and the use of TOF reconstruction.

A selective chaos-driven encryption technique for protecting medical images

Abstract Smart devices, embedded in daily life, have limited memory, power, and processing capabilities, making traditional cryptography impractical and driving the development of lightweight cryptography. Selective encryption of medical images has gained significant attention for its lightweight performance. Nevertheless, existing methods face security challenges, such cannot resist chosen-plaintext attacks, that limit their practical use. To overcome these challenges, this paper introduces a novel selective encryption scheme based on chaos theory. The approach identifies regions of interest in medical images using an adaptive statistical threshold based on pixel intensity values, forming a sub-image block for encryption. The scheme employs a permutation-diffusion structure, utilizing bit-level circular shifts and pixel shuffling to modify both pixel positions and values. A randomized encryption operation in the diffusion phase ensures security against chosen-plaintext attacks. The final encrypted image integrates the encrypted sub-blocks with unencrypted regions, achieving a balance between efficiency and security. The comprehensive evaluation corroborates that our solutions outperform the existing state-of-the-art schemes regarding security and performance. Therefore, our proposed scheme is a practical solution for for lightweight medical image protection in resource-constrained applications.

Functional assessment of major salivary glands using scintigraphy

To demonstrate a methodology of scintigraphy imaging interpretation considering pixel intensity values in groups of patients presenting lupus erythematosus, Sjögren’s Syndrome (SS), SS associated to systemic lupus erythematosus, parotiditis, drug-induced sialorrhea and salivary glands disease-free. Material and methods: A total of 36 salivary gland scintigraphy images that were from patients with lupus erythematosus, SS, SS combined lupus, parotiditis, and drug-induced sialorrhea were assessed. The pixel intensity of the scintigrams was also evaluated using the standardized grayscale at 8 bits, Images were analyzed under a region of interest (ROI) of 2 cm2 at maximum uptake using ImageJ. Results: Significant differences between the groups were obtained both for parotid (p=0.026) and submandibular glands (p=0.0952). Statistical significant differences were observed in post-hoc tests between Lupus combined with SS patients, for parotid and submandibular glands, when compared to normal group (p=0.04 and p=0.03 respectively). Pixel values were higher for Lupus combined with SS patients, representing a lower uptake. Conclusion: The pixel intensity assessment was able to differentiate and point to lower salivary flow rates for the systemic lupus erythematosus combined with SS patients when compared to other disorders affecting the salivary gland function.

Alveolar bone healing patterns in chronic kidney failure and kidney transplant recipients: A pixel intensity and fractal analyses.

To assess and compare radiographically the alveolar bone after tooth extractions in individuals with chronic kidney failure undergoing hemodialysis (CKFh), those submitted to kidney transplantation (KT), and those without kidney disease (CG) by using fractal analysis (FA) and pixel intensity (PI). Periapical radiographs of 48 CKFh individuals (87 extracted teeth), 12 KT individuals (26 extracted teeth and 29 control individuals [76 extracted teeth] were analyzed at 7 and 60 days after tooth extraction. Fractal dimension (FD) and PI were assessed to evaluate the alveolar trabecular bone structural complexity and mineral content. The difference in FD values between the 7th and 60th postoperative days in KT individuals (0.03±0.08) was significantly lower compared to those of CKFh individuals (0.09±0.10) and controls (0.15±0.06). As for the difference in PI values, KT (4.55±10.24) and CKFh groups (9.88±15.90) showed significantly lower values compared to those of the control group (17.93±11.86) in the same period. These results indicate a lower gain in the trabecular bone complexity and bone density in the alveolus of KT individuals compared to the other groups. Overall mineral content and thickness of the bone in the plane of the x-ray beam were lower in KT and CKFh individuals compared to controls, reflecting the need for careful consideration in recommending rehabilitation with dental implants for these patients. Particular attention should be given to the potential challenges in oral rehabilitation of KT patients.

Molecular and cellular level analysis of the mechanism of nutritional intervention in preventing epidemic virus infection

Molecular nutrition encompasses a wider range of investigations than nutritional genomics, which can be considered a scientific investigation of how different nutrients and dietary components influence the cellular and molecular mechanisms of the body and health. In effect, increasing antioxidant elements in daily diets can assist with combating the inflammatory response caused by cytokines in the human body. Antioxidants can impede the oxidation process and hence avoid the creation of free radicals in the cytoplasm that can damage the cells via chain reactions. Contamination sequences, batch effects, uneven sampling, unreported taxa, technological biases, and heteroscedasticity are all significant issues in molecular microbial biology. Artificial Intelligence (AI) methodologies to uncover hidden patterns, connections, and interactions within metabolomics data, allowing them to provide personalized food recommendations based on individual health profiles. A multi-scale convolutional neural network (MCNN) classifies cellular images into phenotypes in a single coherent step utilizing the image’s pixel intensity values. Hence, the proposed AI-MCNN has been an essential nutrient that assists the immune system in various ways, including acting as an antioxidant to protect healthy cells, promoting immune cell development and function, and creating antibodies. According to epidemiological research, people who are undernourished are more likely to get bacterial, viral, and other diseases. Nutritional epidemiology investigates dietary or nutritional parameters concerning illness prevalence in communities. Nutritional epidemiology results often add to the evidence that provides dietary recommendations for preventing disease and related disorders.

KLASIFIKASI HASIL MRI TUMOR OTAK DENGAN EKTRAKSI FITUR GRAY LEVEL CO-OCCURANCE MATRIX (GLCM)

An important part of the body is the brain which is the source of all the body's organs in the skull cavity. Brain tumors are one of the diseases that can attack it. Detection of brain tumors is one aspect that is considered important in medical diagnosis. This research aims to implement GLCM (Gray Level Co-occurrence Matrix) feature extraction on MRI images of brain tumors and to find the best algorithm performance for detecting brain tumors using these MRI images. The data used in this research is public data originating from kaggle.com. The feature extraction process in pictures used in this research is GLCM, which has the function of calculating the frequency of pixel intensity values ​​that are spaced between images using parameters 0o, 45o, 90o, and 135o. The next stage in this research is to carry out preprocessing steps and then look for classification values ​​from the MRI results using the Naïve Bayes, C4.5, and Neural Network algorithms. The results obtained show that Naïve Bayes has the best algorithm performance compared to C4.5 and Neural Network, namely with an accuracy of the Naïve Bayes algorithm of 96.8%, while for the C4.5 algorithm it is 41.5% and the Neural Network is 38.25%. Apart from this, this study proves that GLCM feature extraction has proven effective in capturing texture information from MRI images which is very important in brain tumor classification.

Seismic modeling using pseudo-impedance derived from physical models

Building accurate numerical models of the earth for simulation is both challenging and time consuming. The subsurface complexity must be captured in sufficient detail for the results to be of practical use for geophysical analysis. Physical models provide an efficient way to add realistic detail to numerical models. Physical models, for example, are scaled simulations of large-scale geologic systems that provide great insight into understanding the interplay between sedimentation, salt tectonics, and faulting. The integration of geophysical workflows with sandbox models has been the subject of previous research, primarily to create synthetic data to compare with observed field data. However, capturing the detail from the physical model is challenging. A novel workflow is presented that uses pixel intensity values from photographic images of the analogue model to create a pseudo-impedance perturbation, mimicking the acoustic impedance contrasts that are encountered in the earth. This solution enables the detailed sedimentary architecture from the sandbox to be transferred to the digital earth model. Acoustic wave equation forward modeling and reverse time migration imaging have been applied using the generated pseudo-impedance model for a Gulf of Mexico-style salt canopy model. The images produced show clear definition of the salt/sediment interface and capture the sedimentary stratigraphy and faulting observed in the original sandbox model.

HDetect-VS: Tiny Human Object Enhancement and Detection Based on Visual Saliency for Maritime Search and Rescue

Strong sun glint noise is an inevitable obstruction for tiny human object detection in maritime search and rescue (SAR) tasks, which can significantly deteriorate the performance of local contrast method (LCM)-based algorithms and cause high false alarm rates. For SAR tasks in noisy environments, it is more important to find tiny objects than localize them. Hence, considering background clutter and strong glint noise, in this study, a noise suppression methodology for maritime scenarios (HDetect-VS) is established to achieve tiny human object enhancement and detection based on visual saliency. To this end, the pixel intensity value distributions, color characteristics, and spatial distributions are thoroughly analyzed to separate objects from background and glint noise. Using unmanned aerial vehicles (UAVs), visible images with rich details, rather than infrared images, are applied to detect tiny objects in noisy environments. In this study, a grayscale model mapped from the HSV model (HSV-gray) is used to suppress glint noise based on color characteristic analysis, and large-scale Gaussian Convolution is utilized to obtain the pixel intensity surface and suppress background noise based on pixel intensity value distributions. Moreover, based on a thorough analysis of the spatial distribution of objects and noise, two-step clustering is employed to separate objects from noise in a salient point map. Experiments are conducted on the SeaDronesSee dataset; the results illustrate that HDetect-VS has more robust and effective performance in tiny object detection in noisy environments than other pixel-level algorithms. In particular, the performance of existing deep learning-based object detection algorithms can be significantly improved by taking the results of HDetect-VS as input.

Noninvasive quantitative ultrasound fatty liver evaluation of hepato-renal index in pediatric patients using 3D-slicer

AimHepato-renal index (HRI) calculated by ultrasound images has been shown to be an effective, noninvasive tool to screen patients with steatosis. The aim of this study was to non-invasively explore a new method for the calculation, directly on DICOM images, of HRI in pediatric patients using 3D Slicer, a free and open-source software for medical image analysis, especially used for artificial intelligence data annotation. Previous studies in literature were based on non-medical image format (such as png and tiff) and analyzed by using ImageJ, a popular image analysis software.Materials and methodsDICOM images were collected retrospectively between November 2022 and December 2023 at a tertiary institution on any patient under 18 years referred to US assessment of suspected steatosis. The HRI was measured on sagittal images with a clear visualization of both the liver and the kidney by 3D Slicer. The HRI was calculated as the ratio of average pixel intensity values between the two ROIs. Also, we correlated the index with the qualitative operator assessment grade of steatosis made by two expert radiologists with more than 15 years of experience.Results49 patients (59% male, age 11.6 ± 2.6 year) were recruited. Of these, 29 (59%) had qualitative ultrasound confirmation of the diagnosis. The Bland–Altman plots showed a good agreement between the HRI indexes calculated with the standard tool ImageJ and 3D Slicer. Furthermore, the quantitative HRI calculated by the two software showed a correlation (Spearman’s coefficient = 0.52, P < 0.0001) with the qualitative operator measurement.ConclusionsFor the first time, an estimation of HRI directly on DICOM images was executed by using 3D Slicer, obtained quantitative information directly from clinically approved image format.

Does the Outcome of Graft Materials at Dental Implant Sites Differ Between Patients With Normal and Compromised Bone Health?

The objective of this paper was to assess the outcome of bone graft material at alveolar bone augmentation sites combined with dental implants in postmenopausal women with compromised bone health by evaluating cone beam computerized tomography (CBCT) scans at multiple time points.CBCT scans were analyzed on 55 postmenopausal women with compromised bone health status to determine the fate of alveolar bone augmentation. CBCT scans were taken immediately after surgery and 9 and 24 months postoperatively. The patient's medication regimens and durations were recorded, and the pixel intensity value (PIV) was measured and standardized using scoring criteria and visual assessment. Statistical analyses included 2-sample t tests for continuous variables and Fisher's exact tests for categorical variables.Among the normal patients, 73% received a grade 2 visual score, and 27% received a grade 1 visual score. After 24 months, 45% of patients received a grade 2 score, and 27% received a grade 3 score. In the osteoporotic group receiving medication, 77% of participants received a grade 1 visual score at the 9-month postoperative evaluation, while 23% received a grade 2 score. At the 24-month assessment, 55% of patients received a grade 1 score, 41% received a grade 2 score, and only 5% received a grade 3 score. Notably, although the graft material did not remodel into native bone, it was a scaffold for implants in controlled osteoporotic patients. The study's results show that the pixel intensity values of particulate graft materials are similar across the three different time points, suggesting that the graft material's pixel intensity value remains constant in postmenopausal women with osteoporosis. The study's limitations include a small sample size and a restricted 24-month follow-up period. This limited time frame may need to capture long-term changes or variations in graft materials adequately. Future research should include a larger sample size and have a longer follow-up duration to provide a more comprehensive understanding of the change in graft materials between patients with normal and compromised bone health.

Clinical validation of a novel digital twin framework for ventricular functional substrate simulation in post-infarction patients

Abstract Background Catheter ablation is a cornerstone treatment for scar related post-infarction ventricular arrhythmias. Functional substrate driven ablation strategies guided by local activation time (LAT) mapping have been proven as efficient and effective approaches, especially when dealing with large scar areas. In-silico electrophysiological modeling is emerging as a potential tool for procedural planning and guidance. Purpose To clinically validate the feasibility, diagnostic performance, and accuracy of a novel late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) based digital twin framework for simulated LAT map generation in post-infarction patients and their integration with CARTO3 EAM suite. Methods Five ischemic subjects who underwent CMR-aided scar-related ventricular tachycardia ablation at our referral center were retrospectively enrolled. Their CMR derived 3D pixel-signal-intensity (PSI) maps generated with ADAS3D were processed with novel in-house software to obtain patient-specific ventricular geometry, tissue characterization, and to generate a model of Purkinje system and myocyte fiber orientation. According to local normalized pixel intensity (NPI) values, myocardial regions were marked as healthy, scar, or border-zone. Electrophysiological properties of border-zone (BZ) were modulated according to local NPI. Continuous and 8-steps isochronal endo-epicardial LAT maps were generated and imported in CARTO3 system, aligned with electroanatomical mapping (EAM), and compared at an ASE 17-segments level, in terms of sensitivity, specificity, predictive values, and accuracy to actual high-density LAT maps obtained with a multipolar catheter. Deceleration Zones (DZ) were defined as previously described (&amp;gt;3 isochrones within 1 cm radius). Results A total of 85 ASE segments (34 epicardial) were analyzed. 24 EAM segments (28%) held DZs, 40 (47%) segments harbored bipolar scar or BZ. Thirty-seven (44%) CMR segments held scar core/BZ. Thirty (35%) digital model segments harbored DZs. Generated LAT maps were successfully imported and aligned with CARTO3 EAM suite for validation. In terms of DZ localization prediction, our LAT model showed 83% sensitivity (95% CI 63%-95%), 90% specificity (95% CI 80%-96%), 77% positive predictive value (PPV) (95% CI 56%-91%), 93% negative predictive value (NPV) (95% CI 83%-98%), 88% accuracy (95% CI 79%-94%). Conclusion Our newly developed framework for LGE-CMR derived functional substrate simulation in post-infarction patients holds high sensitivity, specificity, predictive values, and accuracy for DZ localization. Further validation, with a larger sample size, is required for evaluating potential implications in clinical practice.

Patch-based Reversible Steganography for Secured Communication over Wireless Channels

Securing the perceptual quality of the cover image (CI) and acquiring higher security for hidden information in stego images (STIs) are two sides of the same coin. There is always a trade-off between perceptual quality and level of security when secret bits (SBs) of the secret image (SI) are embedded in a CI. Non-reversible techniques are adopted where a higher level of security is required as in communication, while reversible schemes are preferred to maintain the visual quality of the CI. This article proposes a novel Patch-Based LSB Embedding (LSBE) Data Hiding (PB-LSB-EDH) scheme that provides better security to SBs and maintains stego quality. The scheme embeds a secret byte in a 3x3 patch of the CI. The starting byte in the neighborhood where the SBs are hidden is computed from the center pixels of the 3x3 patch window and continues to embed pixels clockwise. The PB-LSB-DH scheme is highly immune to external noise or attacks when the intensity value of the center pixels is equal to or greater than 12 since the starting index of bit embedding is computed using a natural logarithm. Experimental analysis of four different CIs and SIs showed that the proposed PB-LSB-DH scheme maintains the better perceptual quality of the CI and a higher peak signal-to-noise ratio (PSNR) above 50.

Reflectance characterization of Starlink-like satellite with HELIOS brightness testing facility

The HELIOS (High Efficiency Light Intensity Observation System) project addresses the issue of excessive brightness from LEO satellite constellations. The system aims to develop a reflectance model of a satellite prior to launch, enabling the validation of compliance with astronomer guidelines, which suggest a minimum magnitude of 7. This ensures that the constellation is not visible to the naked eye and does not excessively interfere with astronomical observations. Additionally, the reflectance model obtained can be used for attitude determination by comparing the light curves with those obtained from observations. This application extends to Space Traffic Management, debris reentry prediction, and active debris removal. The system utilizes a light source consisting of 14 high-power LEDs with different wavelengths that replicate the solar spectrum. The light is positioned on an arc and can slide along a rail, allowing sampling at various angles. The arc itself can rotate on its axis, enabling the placement of the light source at any point on the hemisphere. At the center of the hemisphere, a scaled 3D printed model of the satellite under study is placed, with surface finishes resembling the actual satellite. Creating models with varying levels of detail permits to assess their impact on the reflectance model. Finally, the robotic arm Arm4NDO (Arm For Near Distance Observations) permits the movement of a high-efficiency quantum camera mounted at its end across the entire hemisphere’s surface for data acquisition. The camera records a video, stopping at points of interest for capturing frames. To strike a balance between continuous data acquisition and reasonable testing times, both the light source and capture points are positioned every 15° in elevation and azimuth. The initial test campaign aimed to determine optimal camera settings (exposure, aperture, and ISO) to achieve good model visibility and a dark background. Preliminary tests focused on Starlink’s chassis and the most significant observation configurations. Frames of interest were extracted from the videos, and their luminous flux (sum of pixel intensity values) was derived. With the obtained data, curves normalized relative to the maximum were plotted, allowing for a comparison of flux variations among different configurations.

Ultrasound-based assessment of the expression of inflammatory markers in the rectus femoris muscle of rats.

Ultrasonographic characteristics of skeletal muscles are related to their health status and functional capacity, but they still provide limited information on muscle composition during the inflammatory process. It has been demonstrated that an alteration in muscle composition or structure can have disparate effects on different ranges of ultrasonogram pixel intensities. Therefore, monitoring specific clusters or bands of pixel intensity values could help detect echotextural changes in skeletal muscles associated with neurogenic inflammation. Here we compare two methods of ultrasonographic image analysis, namely, the echointensity (EI) segmentation approach (EI banding method) and detection of selective pixel intensity ranges correlated with the expression of inflammatory regulators using an in-house developed computer algorithm (r-Algo). This study utilized an experimental model of neurogenic inflammation in segmentally linked myotomes (i.e., rectus femoris (RF) muscle) of rats subjected to lumbar facet injury. Our results show that there were no significant differences in RF echotextural variables for different EI bands (with 50- or 25-pixel intervals) between surgery and sham-operated rats, and no significant correlations among individual EI band pixel characteristics and protein expression of inflammatory regulators studied. However, mean numerical pixel values for the pixel intensity ranges identified with the proprietary r-Algo computer program correlated with protein expression of ERK1/2 and substance P (both 86-101-pixel ranges) and CaMKII (86-103-pixel range) in RF, and were greater (p < 0.05) in surgery rats compared with their sham-operated counterparts. Our findings indicate that computer-aided identification of specific pixel intensity ranges was critical for ultrasonographic detection of changes in the expression of inflammatory mediators in neurosegmentally-linked skeletal muscles of rats after facet injury.

Quantitative Approach for Anemia Detection Using Regression Analysis

Anemia, generally termed as deficiency of hemoglobin or red blood cells in the blood is significant global health concern for the population in underdeveloped as well as in developing nations specially, for children and young women in rural areas. This paper proposes a quantitative approach for anemia detection by regression analysis technique which predicts hemoglobin level in the blood. To achieve this, the image dataset of microscopic blood sample is collected from 70 individuals. The data collection requires proper procedure as it plays vital part in system implementation. The statistical feature utilizing mean pixel intensity values from the red, green, and blue color planes of the images are given as input to the regression model. For the proposed system, we have employed multiple regression analysis model using machine learning approach with both three and four regression coefficients to establish relation between features obtained from blood samples and the hemoglobin level in the blood to achieve the specified task of anemia detection in an individual. Performance analysis show promising results for the proposed system with co-efficient of determination (R2) and root mean square error (RMSE) found out be 0.923 and 1.682 respectively. Overall, this paper presents valuable system for anemia detection based on hemoglobin estimation which can be implemented in areas with limited medical resources and gives another supportive technological solution for current healthcare problems.

Liver tumour detection and classification using partial differential technique algorithm with enhanced convolutional classifier

The image of liver which is the area of interest in this work is obtained from abdominal CT scan. It also contains details of other abdominal organs such as pancreas, spleen, stomach, gall bladder, intestine etc. Since all these organs are of soft tissues, the pixel intensity values differ marginally in the CT scan output and the organs overlap each other at their boundaries. Hence it is very difficult to trace out the exact contour of liver and liver tumor. The overlapping and obscure boundaries are to be avoided for proper diagnosis. Image segmentation process helps to meet this requirement. The normal perception of the CT image can be improved by suitable segmentation techniques. This will help the physician to extract more information from the image and give an accurate diagnosis and better treatment. The projected images are processed using the Partial Differential Technique (PDT) to isolate the liver from the other organs. The Level Set Methodology (LSM) is then used to separate the cancerous tissue from the healthy tissue around it. The classification of stages may be done with the assistance of an Enhanced Convolutional Classifier. The classification of LSM is evaluated by producing many metrics of accuracy, sensitivity, and specificity using an Improved Convolutional classifier. Compared to the two current algorithms, the proposed technique has a sensitivity and specificity of 96% and 93%, respectively, with 95% confidence intervals of [0.7513 1.0000] and [0.7126 1.0000] for sensitivity, and specificity respectively.

Optimality of analysing smart tourism destination management based on media convergence algorithms

Abstract This paper uses a local path fusion method of medium to simulate the angular deviation between the end direction of the trajectory and the target direction according to a specific evaluation function. The media fusion algorithm is guided to achieve global optimality of the path by fusing global path planning information and avoiding local dynamic obstacles. The smart tourism and tourism management systems are fused to balance the intensity loss constraint weights and perform Gaussian filtering to derive the tourism management situation. By decomposing the highest level of tourism information and normalizing the pixel intensity values and tourism characteristic information, it was found that the smart tourism penetration rate increased by 3.6%, the total tourism revenue increased by 88.87% over the previous year, and the working variance of tourism project effectiveness was 62.430.

Levy Flight and Chaos Theory-Based Gravitational Search Algorithm for Image Segmentation

Image segmentation is one of the pivotal steps in image processing due to its enormous application potential in medical image analysis, data mining, and pattern recognition. In fact, image segmentation is the process of splitting an image into multiple parts in order to provide detailed information on different aspects of the image. Traditional image segmentation techniques suffer from local minima and premature convergence issues when exploring complex search spaces. Additionally, these techniques also take considerable runtime to find the optimal pixels as the threshold levels are increased. Therefore, in order to overcome the computational overhead and convergence problems of the multilevel thresholding process, a robust optimizer, namely the Levy flight and Chaos theory-based Gravitational Search Algorithm (LCGSA), is employed to perform the segmentation of the COVID-19 chest CT scan images. In LCGSA, exploration is carried out by Levy flight, while chaotic maps guarantee the exploitation of the search space. Meanwhile, Kapur’s entropy method is utilized for segmenting the image into various regions based on the pixel intensity values. To investigate the segmentation performance of ten chaotic versions of LCGSA, firstly, several benchmark images from the USC-SIPI database are considered for the numerical analysis. Secondly, the applicability of LCGSA for solving real-world image processing problems is examined by using various COVID-19 chest CT scan imaging datasets from the Kaggle database. Further, an ablation study is carried out on different chest CT scan images by considering ground truth images. Moreover, various qualitative and quantitative metrics are used for the performance evaluation. The overall analysis of the experimental results indicated the efficient performance of LCGSA over other peer algorithms in terms of taking less computational time and providing optimal values for image quality metrics.

Ability of artificial intelligence to identify self-reported race in chest x-ray using pixel intensity counts.

Prior studies show convolutional neural networks predicting self-reported race using x-rays of chest, hand and spine, chest computed tomography, and mammogram. We seek an understanding of the mechanism that reveals race within x-ray images, investigating the possibility that race is not predicted using the physical structure in x-ray images but is embedded in the grayscale pixel intensities. Retrospective full year 2021, 298,827 AP/PA chest x-ray images from 3 academic health centers across the United States and MIMIC-CXR, labeled by self-reported race, were used in this study. The image structure is removed by summing the number of each grayscale value and scaling to percent per image (PPI). The resulting data are tested using multivariate analysis of variance (MANOVA) with Bonferroni multiple-comparison adjustment and class-balanced MANOVA. Machine learning (ML) feed-forward networks (FFN) and decision trees were built to predict race (binary Black or White and binary Black or other) using only grayscale value counts. Stratified analysis by body mass index, age, sex, gender, patient type, make/model of scanner, exposure, and kilovoltage peak setting was run to study the impact of these factors on race prediction following the same methodology. MANOVA rejects the null hypothesis that classes are the same with 95% confidence ( 7.38, ) and balanced MANOVA ( 2.02, ). The best FFN performance is limited [area under the receiver operating characteristic (AUROC) of 69.18%]. Gradient boosted trees predict self-reported race using grayscale PPI (AUROC 77.24%). Within chest x-rays, pixel intensity value counts alone are statistically significant indicators and enough for ML classification tasks of patient self-reported race.

Identifikasi Karakteristik Accumulator Menggunakan Citra Termal Berbasis Pengolahan Citra

Batteries are an important part of the power generation system, both solar power plants and motorized vehicle electrical systems. Battery capacity is something that must be considered for these various activities, because a decrease in battery capacity results in disruption of power distribution to users. The battery in this study is a battery or accumulator. The sample image is obtained using a thermal camera to determine the characteristics of the battery based on color. The basis for identifying characteristics is obtained by separating the RGB color components in the thermal image. Each color component will calculate the average pixel intensity value and see the difference in the resulting value. The results showed that the distinguishing characteristic between the sampling conditions was that the green pixel intensity mean value when the battery was being charged was higher than the condition of the battery before being charged and the condition of the battery when it was loaded. The average value when the battery is on the power side is 107 pixels green, while the average value when the battery is before charging is 81 pixels green and when the battery is loaded the average green value is 82 pixels.