Search

This paper presents an in-pixel contrast enhancement circuit that performs image processing directly within the pixel circuit. The circuit leverages HyperFET, a hybrid device combining a MOSFET and a phase transition material (PTM), to enhance performance. It can be tuned for different modes of operation. In foreground enhancement mode, it suppresses low-intensity background pixels to nearly zero, isolating the foreground for better object visibility. In contrast enhancement mode, it improves overall image contrast. The contrast enhancement function is customizable both during the design phase and in real-time, allowing the circuit to adapt to specific applications and varying lighting conditions. A model of the designed pixel circuit is developed and applied to a full pixel array, demonstrating significant improvements in image quality. Simulations performed in HSPICE show a nearly 6x increase in Michelson Contrast Ratio (CR) in the foreground enhancement mode. Furthermore, process variation and Signal-to-Noise Ratio (SNR) analysis has been conducted to evaluate the robustness of the design under manufacturing variations. The simulation results indicate its potential for real-time, adaptive contrast enhancement across various imaging environments. [ABSTRACT FROM AUTHOR]

Objective: To perform a systematic review and meta-analysis of the diagnostic performance of contrast enhancement to differentiate benign and malignant renal lesions using CT and MRI. Material and Methods: A systematic literature search of databases was performed between January 1, 1980 and September 26, 2022. We included studies reporting the accuracy of CE thresholds on CT and MRI indeterminate renal lesions, with pathologic examination and follow-up as the reference standard. Studies meeting the inclusion criteria underwent quality assessment with the Cochrane recommendation for diagnostic accuracy study Quality Assessment 2. We excluded studies with high risk of bias. Summary estimates of diagnostic performance were obtained with the bivariate Bayesian model for CT and MRI. Effects of different thresholds and index test modalities were investigated through subgroup analysis. Results: Eleven studies (1372 patients) using CT and six studies (218 patients) using MRI were included. Of the eleven studies, 15 parts from 9 studies were considered for the CT meta-analysis, and 6 parts from 3 studies for the MRI meta-analysis. Diagnostic performance meta-analysis on enhancement found a 96% summary sensitivity (95% CI 92, 98) and a 92% summary specificity (95% CI 85, 96) in 2056 renal lesions for CT; and 82% summary sensitivity (95% CI 65, 89) and an 89% summary specificity (95% CI 77, 95) in 634 lesions for MRI. Conclusion: CT and MRI have high accuracy to determine enhancement and classify renal lesions, and both modalities can be used with confidence for this purpose. There are still some controversies about the optimal thresholds. Future research should evaluate outcomes and decision-making pathways to determine whether basing clinical decisions on a specific threshold on CT and MRI would do more harm than good. [ABSTRACT FROM AUTHOR]

Anatomical structure preservation throughout the denoising process is a challenge in the domain of medical imaging. The Rician noise introduced through the acquisition procedure by the Magnetic Resonance Imaging (MRI) scanner distorts the images. In this study, denoising using Wavelet-based Non-Local Median Filter (WBNLMF) and a novel contrast-enhancement method termed Improved Minimum Intensity Error Intuitionistic Fuzzy Contrast Enhancement (IMIEIFCET) is suggested. This methodology gives superior results while maintaining the edges and the brightness of the original image. An Attention Module-based Convolution Neural Network (AM-CNN) is suggested in the research as a methodology for skull stripping from MRI data. With a mean Dice coefficient of 0.998, a Sensitivity of 0.9975, and a Specificity of 0.9985, the proposed network exhibits result that are comparable to those of the specified Deep Learning (DL)-based technique. [ABSTRACT FROM AUTHOR]

Background: Diabetic Retinopathy (DR) is a leading cause of blindness among individuals aged 18 to 65 with diabetes, affecting 35–60% of this population, according to the International Diabetes Federation. Early diagnosis is critical for preventing vision loss, yet processing raw fundus images using machine learning faces significant challenges, particularly in accurately identifying microaneurysm lesions, which are crucial for diagnosis. Methods: This study proposes a novel pre-processing technique utilizing the Modified Fuzzy C-means Clustering approach combined with a Support Vector Machine classifier. The method includes converting RGB images to HSI colour space, applying median filtering to reduce noise, enhancing contrast through Intensity Histogram Equalization, and identifying false microaneurysm candidates using connected components. Additionally, morphological operations are performed to remove the optic disc from the enhanced images due to its similarity to microaneurysms. Results: The proposed method was evaluated using publicly available datasets, demonstrating superior performance compared to existing state-of-the-art algorithms. The approach achieved an accuracy rate of 99.31%, significantly improving the detection of microaneurysms and reducing false detections. Conclusions: The findings indicate that the proposed pre-processing technique effectively enhances diabetic retinopathy classification by addressing the challenges of false microaneurysm detection. The comparative analysis against state-of-the-art algorithms highlights the effectiveness of the proposed method, particularly in addressing the challenges associated with false microaneurysms. [ABSTRACT FROM AUTHOR]

Image enhancement is a technique for improving the quality of an image so that it can be viewed by both humans and machines. The primary purpose of picture contrast enhancement is to improve the image's visual quality. Histogram equalisation (HE) is one way to increase contrast. One disadvantage of He is that it does not sustain brightness while increasing contrast since a sdden mean shift occurs during the equalisation process. A new image enhancement method is established with weighted histogram equalisation with Oppositional-based Customised Monarch Butterfly Optimisation (OCMBO), for better visual perception and improving image quality. The collected input image is in RGB format. This image is then converted into YCbCr format for contrast stretching. In digital image processing, the YCbCr colour space is often used to take advantage of the lower resolution capability of the human visual system for colour concerning luminosity. The weighted histogram equalisation with Oppositional-based Customised Monarch Butterfly Optimisation (OCMBO) is applied to the converted image's Y component, and then the Cr, Cb and modified Y components are combined back into RGB format. [ABSTRACT FROM AUTHOR]

Images and videos collected in an underwater environment often have low contrast, blur, and colour cast due to two significant sources of distortion; light scattering and absorption. In an underwater image/video, suspended particles attenuate red and blue components more than green channels. This article presents two adaptive weight allocation strategies based on rule assignment for red, green, and blue channels. Firstly, an improved balanced contrast enhancement technique (IBCET) is proposed using an adaptive contrast enhancement scheme based on colour component weight assignment. Secondly, a modified fuzzy contrast enhancement technique which obtains the intensification factor based on the weight of each component is developed. Finally, principal component analysis fusion is employed to improve the overall colour and contrast of the output video frames. Qualitative and quantitative evaluations on the standard underwater video dataset are demonstrated to validate the improved performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Low-light images are challenging for both human observation and computer vision algorithms due to low visibility. To address this issue, various image enhancement techniques such as dehazing, histogram equalization, and neural network-based methods have been proposed. However, most existing methods often suffer from the problems of insufficient contrast and over-enhancement while enhancing the brightness, which not only affects the visual quality of images but also adversely impacts their subsequent analysis and processing. To tackle these problems, this paper proposes a low-light image enhancement method called LEFB. Specifically, the low-light image is first transformed into the LAB color space, and the L channel controlling brightness is enhanced using a local contrast enhancement algorithm. Then, the enhanced image is further enhanced using an exposure fusion-based contrast enhancement algorithm, and finally, a bilateral filtering function is applied to reduce image edge blurriness. Experimental evaluations are conducted on real datasets with four comparison algorithms. The results demonstrate that the proposed method has superior performance in enhancing low-light images, effectively addressing problems of insufficient contrast and over-enhancement, while preserving fine details and texture information, resulting in more natural and realistic enhanced images. [ABSTRACT FROM AUTHOR]

Objectives: It is difficult to solve the matching problem between heterogeneous remote sensing images caused by nonlinear radiometric distortions. Methods: This paper proposes a nonlinear scale-space enhanced automatic matching method for optical and synthetic aperture radar (SAR) images. First, by modifying the calculation of color pixel contrast, the contrast information of images is effectively enhanced. As a result, the repeatability of corresponding points between optical and SAR images can be improved. Second, a nonlinear diffusion equation is employed to describe the image diffusion characteristics, avoiding the issue of boundary blurring in the Gaussian scale-space. Third, the multi-scale ratio of exponentially weighted averages operator and the Sobel operator are utilized to compute the gradient information of SAR and optical images, respectively, followed by the stable extraction of Harris feature points. Finally, log-polar de‑ scriptor framework is employed to compute a high discriminate feature vector, and the outliers are eliminat‑ ed by Euclidean distance and fast sample consensus algorithm. Results: The experimental results demonstrate that the proposed method can get more matching points and achieve higher matching accuracy, compared Objectives: It is difficult to solve the matching problem between heterogeneous remote sensing images caused by nonlinear radiometric distortions. Methods: This paper proposes a nonlinear scale-space enhanced automatic matching method for optical and synthetic aperture radar (SAR) images. First, by modifying the calculation of color pixel contrast, the contrast information of images is effectively enhanced. As a result, the repeatability of corresponding points between optical and SAR images can be improved. Second, a nonlinear diffusion equation is employed to describe the image diffusion characteristics, avoiding the issue of boundary blurring in the Gaussian scale-space. Third, the multi-scale ratio of exponentially weighted averages operator and the Sobel operator are utilized to compute the gradient information of SAR and optical images, respectively, followed by the stable extraction of Harris feature points. Finally, log-polar de‑ scriptor framework is employed to compute a high discriminate feature vector, and the outliers are eliminat‑ ed by Euclidean distance and fast sample consensus algorithm. Results: The experimental results demonstrate that the proposed method can get more matching points and achieve higher matching accuracy, compared with other classic methods. Conclusions: The proposed method can realize automatic and robust matching for SAR and optical images. [ABSTRACT FROM AUTHOR]

Background: This study aims to investigate the efficacy of multifactorial MRI in diagnosing breast cancer, specifically in the context of predicting lymphovascular invasion (LVI). Materials & methods: The patients were stratified into two groups: the primary group (100 patients) and the validation group (100 patients), based on essential characteristics. Multifactorial MRI, encompassing tumor size evaluation, diffusion coefficient assessment and dynamic contrast enhancement, was employed for patient examination. Results: Statistically significant differences were observed in tumor size, diffusion coefficient and dynamic contrast enhancement between groups with LVI (LVI+) and those without (LVI-). Key parameters were identified for predicting the degree of invasion. Conclusion: The results affirm the effectiveness of multifactorial MRI in forecasting LVI. Article highlights Innovative approach: Successfully tested the methodology of using multiparametric MRI for identifying lymphovascular invasion (LVI) indicators, offering a novel advancement in breast cancer (BC) diagnostics. Enhanced accuracy: Multiparametric MRI demonstrates superior effectiveness compared with traditional methods in predicting LVI, providing a critical tool for clinicians. Key MRI parameters: Identified three significant MRI parameters – tumor size, diffusion coefficient and dynamic contrast enhancement – that are crucial for accurately predicting LVI. Clinical Implications: Emphasizes the importance of integrating multiparametric MRI into clinical practice to enable more precise diagnostics and personalized treatment strategies for BC patients. Research recommendations: Highlights the need for further research, including larger patient cohorts and multicenter studies, to validate and refine the application of multiparametric MRI in BC diagnostics. Impact on care: The study underscores the potential of multiparametric MRI to significantly enhance the quality of care and improve prognoses for patients with BC. Study validation: The findings confirm the robustness of multiparametric MRI in comparison to traditional methods, reinforcing its value in clinical settings. Personalized treatment: Advocates for the use of MRI-derived parameters to tailor treatment strategies, improving the accuracy of treatment planning and patient outcomes. Future directions: Calls for expanded research to strengthen conclusions and explore further applications of multiparametric MRI in the oncology field. Clinical relevance: Provides compelling evidence for the integration of advanced MRI techniques into routine diagnostic protocols to better manage LVI in BC. [ABSTRACT FROM AUTHOR]

Integrating fractional calculus into image processing techniques offers a useful and robust approach. In this study, we proposed contrast enhancement filters using Prabhakar fractional integral operator based on Grunwald–Letnikov and forward Euler. We evaluated the performance of the proposed enhancement methods on both high and low contrast images and compared them with fractional and non-fractional contrast enhancement methods. To demonstrate the superiority of our methods, we employed five different image quality metrics: PSNR, MSE, SSIM, FSIM, and entropy. For low contrast images, our methods not only achieved acceptable results for each metric—PSNR values above 25, SSIM values above 0.9, MSE values below 200, FSIM values above 0.97, and entropy values above 7—but also demonstrated better performance compared to other methods. In high contrast images, despite an overall decline in metric scores, the Grunwald–Letnikov based method remains the leading approach among both fractional and non-fractional methods. Additionally, empirical results provide evidence that the proposed methods are more effective in enhancing low contrast images compared to high contrast images. [ABSTRACT FROM AUTHOR]

BACKGROUND: Resection of the contrast-enhancing (CE) tumor represents the standard of care in newly diagnosed glioblastoma. However, some tumors ultimately diagnosed as glioblastoma lack contrast enhancement and have a low-grade appearance on imaging (non-CE glioblastoma). We aimed to (a) volumetrically define the value of non-CE tumor resection in the absence of contrast enhancement, and to (b) delineate outcome differences between glioblastoma patients with and without contrast enhancement. METHODS: The RANO resect group retrospectively compiled a global, eight-center cohort of patients with newly diagnosed glioblastoma per WHO 2021 classification. The associations between postoperative tumor volumes and outcome were analyzed. Propensity score-matched analyses were constructed to compare glioblastomas with and without contrast enhancement. RESULTS: Among 1323 newly diagnosed IDH-wildtype glioblastomas, we identified 98 patients (7.4%) without contrast enhancement. In such patients, smaller postoperative tumor volumes were associated with more favorable outcome. There was an exponential increase in risk for death with larger residual non-CE tumor. Accordingly, extensive resection was associated with improved survival compared to lesion biopsy. These findings were retained on a multivariable analysis adjusting for demographic and clinical markers. Compared to CE glioblastoma, patients with non-CE glioblastoma had a more favorable clinical profile and superior outcome as confirmed in propensity score analyses by matching the patients with non-CE glioblastoma to patients with CE glioblastoma using a large set of clinical variables. CONCLUSIONS: The absence of contrast enhancement characterizes a less aggressive clinical phenotype of IDH-wildtype glioblastomas. Maximal resection of non-CE tumors has prognostic implications and translates into favorable outcome.

The histogram equalization method, used to improve images, minimizes the amount of pixel intensities, which results in the loss of detail and an unnatural appearance. This study presents an approach for enhancing low contrast images based on their inherent characteristics. The statistical parameter skewness is derived from the photographs to facilitate the classification process into dark and bright images. Based on the classification, appropriate dark and bright pass filters are applied on the multi-level decomposed images to extract the significant edge details. The level of decomposition is optimized using particle swarm optimization. The extracted edge details are utilized by the two-dimensional histogram equalization technique. It leverages the combined presence of edge information and pixel intensities in the low contrast image. The algorithm's efficacy is assessed on three databases, namely CCID, LOL, and DRESDEN, through the utilization of standard deviation (SD), contrast improvement index (CII), discrete entropy (DE), the natural image quality evaluator (NIQE), and Kullback–Leibler distance (KL). Based on the empirical findings, it can be observed that the suggested methodology exhibits better performance compared to alternative methods, including deep learning architectures, in terms of high CII, SD, DE, and low NIQE, KL values. [ABSTRACT FROM AUTHOR]

Digital radiography in medicine is a widely used imaging method for obtaining visual information about the inside of a body. To prepare the acquired raw image for diagnostic evaluation, the contrast must be adjusted depending on the examined part of the body and the reason of acquisition. The contrast enhancement of an image can be considered as a style transfer or an image-to-image translation which is an important field in deep learning. Based on common methods like the pix2pix network that only translate from one domain into one other, we propose a method (cc-pix2pix) for translating into multiple domains in one training. We provide additional information about the examination to the network for a specific contrast adjustment. Compared to the pix2pix network, the ccpix2pix reduces the mean squared error by a factor of six and achieves an improvement of approximately seven percentage points based on the histogram intersection of source and target images.

Aim. To evaluate the possibilities of post-processing of multidetector computed tomography (CT) results in the non-invasive diagnosis of pancreatic fibrosis (PF). Materials and methods. The study included 165 patients aged 57.91±13.5 years who underwent preoperative CT during surgical treatment for chronic pancreatitis and pancreatic cancer from April 2022 to February 2024. The normalized contrast ratios of pancreatic tissue in the pancreatic (NCPP) and venous (NCVP) phases, as well as the contrast ratio (CR) were measured. Pathomorphological assessment of PF performed in tissues outside neoplasm or desmoplastic reaction by the Kloppel and Maillet scale. Results. The values of post-processing CT results were compared in groups with different degrees of PF. Mean CR values were significantly higher (p=0.001) in patients with severe PF (CR 1.16±0.65 HU) than in patients with mild PF (CR 0.78±0.31 HU). CR value significant increase (p=0.03) was found in patients with signs of inflammatory changes in the pancreas tissue (CR 1.14±0.6 HU) than in those without them (CR 0.81±0.3 HU). There were no significant differences between the values of NCPP and NCVP, and the degree of PF. Conclusion. The CR value increased in patients with severe degree of PF. There was a relationship between CR value increase and the radiological density of pancreatic tissue in non-contrast phase and presence of early signs of pancreatic inflammatory changes. Thus, there was a relationship between CT postprocessing results and morphological signs of PF, which can be used for pancreatic fibrosis non-invasive diagnosis and identification of additional signs of early chronic pancreatitis.

Medical images provide a visual representation of the internal structure of the human body. Injecting a contrast agent can increase the contrast of diseased tissues and assist in the accurate identification and assessment of conditions. Considering the adverse reactions and side effects caused by contrast agents, previous methods synthesized post-contrast images with pre-contrast images to bypass the administration process. However, existing methods pay inadequate attention to reasonable mapping of the lesion area and ignore gaps between post-contrast and real images in the frequency domain. Thus, in this paper, we propose an interactive frequency generative adversarial network (IFGAN) to solve the above problems and synthesize post-contrast images from pre-contrast images. We first designed an enhanced interaction module that is embedded in the generator to focus on the contrast enhancement region. Within it, target and reconstruction branch features interact to control the local contrast enhancement region feature and maintain the anatomical structure. We propose focal frequency loss to ensure the consistency of post-contrast and real images in the frequency domain. The experimental results demonstrated that IFGAN outperforms other sophisticated approaches in terms of preserving the accurate contrast enhancement of lesion regions and anatomical structures. Specifically, our method produces substantial improvements of 7.9% in structural similarity (SSIM), 36.3% in the peak signal-to-noise ratio (PSNR), and 8.5% in multiscale structural similarity (MSIM) compared with recent state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This study presents a multi-exposed fusion algorithm aimed at enhancing the quality of retinal images captured under variable illumination conditions. Retinal imaging devices frequently struggle with inconsistent lighting, which can lead to low-contrast images where critical vascular details may be lost. The proposed algorithm combines multiple exposures, preserving the best features from each - improving both clarity and detail. Using the database of 40 retinal images, the method evaluates image quality through the structural similarity index measure (SSIM). Results indicate high structural similarity between fused images and input images across different illumination levels, with SSIM values above 0.9 for medium and high exposure. Furthermore, incorporating Contrast-Limited Adaptive Histogram Equalization (CLAHE) enhances contrast, facilitating clearer vessel visualization against the background. The improved contrast and detail retention achieved by the algorithm support accurate retinal vessel analysis, which is crucial in diagnosing conditions like diabetic retinopathy and glaucoma. This approach provides a robust, enhanced imaging solution for medical diagnostics, significantly improving readability and reliability in retinal assessments. [ABSTRACT FROM AUTHOR]

The underwater imaging environment is very different from land, and some common land image enhancement methods are often not applicable to the underwater environment. This paper proposes a two-step underwater image enhancement method. White balance is a commonly used color correction method. In underwater environments, the traditional white balance method has certain limitations and results in severe color bias. This is caused by the faster attenuation of red light in underwater environments. We develop a new white balance method based on the assumption of the gray world method. A red correction module is embedded in the method, which is more suitable for underwater environments. For contrast correction, we design an illuminance correction method based on the Retinex model. The method significantly reduces the computational burden compared to traditional methods, while enhancing the brightness and contrast of the images. In addition, most of the current underwater image enhancement methods deal with color and contrast issues separately. However, these two factors influence each other, and processing them separately may lead to suboptimal results. Therefore, we investigate the relationship between color and contrast and propose a trade-off method. Our method integrates color and contrast within a histogram framework, achieving a balanced enhancement of both aspects. To avoid chance, we utilized four datasets, each containing 800 randomly selected images for metric testing. On the five non-referential metrics, three firsts and two seconds were ranked. Our method ranked second on two referenced metrics. Superior results were also achieved in runtime comparisons. Finally, we further demonstrate the superiority of our method through detailed demonstrations and ablation experiments. [ABSTRACT FROM AUTHOR]

The article introduces a special issue on "Recent Trends in Multimedia Forensics," categorizing articles into three main areas: Adversarial Attacks, Security Preservation, and Deepfake Detection. Various methods are proposed to protect privacy, detect deepfakes, and enhance copyright protection in multimedia content. The research aims to address challenges in detecting deepfakes, identifying sources, maintaining generalization, and implementing proactive defense mechanisms. The special issue also includes a comprehensive survey on methods for image integrity, offering insights into the prevention and identification of counterfeit images. [Extracted from the article]

In autonomous driving, capturing high-quality images with visual sensors in adverse weather conditions presents a significant challenge for object detection. This paper introduces a candid and effective preprocessing method called Contrast Enhancement through Mutual Entropy (CEME) to improve the visual quality of images. Unlike previous methods such as traditional image processing, image restoration, and deep learning techniques, CEME enhances image quality using simple filtering operations. CEME works by adjusting gray levels appropriately through the calculation of mutual entropy between adjacent gray levels in each plane of a color image. Experimental simulations were conducted on various images taken in weather conditions like snow, fog, sand, and rain. To evaluate performance, this study used two natural image quality assessment metrics: Novel Blind Image Quality Assessment (NBIQA) and Natural Image Quality Evaluator (NIQE). The proposed method achieved an average NBIQA for sandy, snowy, rainy, and foggy images of 28.1576, 35.7233, 29.8796, and 36.1944 respectively. [ABSTRACT FROM AUTHOR]

Image improvement is essential in various computer vision and image analysis applications. These include healthcare, automotive, security and surveillance, retail and E-commerce, agriculture, manufacturing, entertainment, media, sports activity, and documents and text analysis. Ophthalmologists commonly use fundus images to detect and identify frequent fundus disorders and diseases. Few retinal images are clinically unacceptable due to improper imaging processes and movement of the eyes. The proposed method suggested a new approach for enhancing the contrast and luminosity of fundus pictures. The Luminance Gain Matrix (LGM) is first acquired using the Moth Swarm Algorithm (MSA) of the Value channel (V), which corresponds to the HSV color model. LGM is imposed to improve the RGB channels, respectively. Second, the Contrast-Limited Adaptive Histogram Equalization (CLAHE) enhances the contrast of the Luminosity channel (L) in the L*a*b* color model. The execution of the suggested technique is primarily validated using two datasets: a STARE large dataset of approximately 400 images and a small dataset of 23 high-resolution photos representing the diseases fibrosis and glaucoma, respectively. The proposed approach outshines other state-of-the-art techniques concerning both subjective and objective assessment. As a result, the proposed method may aid ophthalmologists in more effective retinal disease research. [ABSTRACT FROM AUTHOR]

Stroke is one of the leading causes of death worldwide, accounting for five of all deaths in Malaysia. It happens when an infarct from a blocked blood artery results in brain necrosis. Diagnoses involving brain diseases and injuries can be made with the help of CT scans, which create axial images by using exact X-ray measurements. These scans offer vital information on the anatomy and physiology of the brain. For an appropriate diagnosis, early infarct brain CT scan contrast can be improved. The two main types of histogram equalization (HE) approaches used for this purpose are Global Histogram Equalization (GHE) and Local Histogram Equalization (LHE), which is also referred to as adaptive histogram equalization (AHE). Locally, LHE uses the block overlapped method to improve photos. Additional sophisticated methods include Dualistic Sub Image Histogram Equalization (DSIHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Recursive Sub Image Histogram Equalization (RSIHE), Gamma Correction Adaptive Extreme Level Eliminating With Weighting Distribution (GCAELEWD), and Brightness Preserving Bi Histogram Equalization (BBHE). The contrast of brain images is greatly improved by these techniques. Nevertheless, a number of these methods have issues with blur, noise, and preserving local image brightness. According to our research, CLAHE and DSIHE are especially good to improve image contrast and yield better outcomes than other techniques. These methods lessen frequent problems, which makes them better suited to create precise and comprehensive brain images--an essential component of successful stroke diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Contrast enhancement is a crucial aspect of image processing, as it improves visual quality by adjusting the brightness and contrast of an image. This paper comprehensively explores contrast enhancement techniques, classified into three categories: Image Processing (IP) based methods Deep Learning (DL) based approaches, and Generative Adversarial Network (GAN) methods. The paper also details various quality evaluation methods for enhanced images and compares different algorithms. The performance of the presented algorithms is evaluated using metrics such as Structural Similarity Index Measurement (SSIM), Absolute Mean Brightness Error (AMBE), Average Information Content (AIC), Contrast Improvement Index (CII), Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Universal Quality Index (UQI), and Color Enhancement Factor (CEF). The comparative analysis aims to provide insights into improving image quality, information content and error production within each category, facilitating informed decision-making in selecting contrast enhancement techniques for diverse applications. [ABSTRACT FROM AUTHOR]

Image enhancement is a fundamental prerequisite for every computer vision program that intends to process an image further. When applied to practically undetectable photos, one of the most common limitations of most existing approaches is the loss of color information throughout the improvement process. In this work, a method based on the enhancement of base as well as detail images using the concept of global and local enhancement for highly degraded images has been proposed which improves the highly degraded image along with preserving its color as well as naturalness. In this novel method, a global–local technique is proposed that breaks the image into smoother and sharper regions called base and detail images. The base image consists of the smoother regions in the input image whereas the detail image contains the sharp edges. The global approach is applied for improving the base image and the local technique is applied for the enhancement of the detail image, containing the sharper edges. The base and detail images are estimated using the median and weighted least squares (WLS) filters respectively. The base image is enhanced using the global approach using the modified form of AGC based on the cumulative histogram. The value of gamma is derived from the image parameters, which makes the proposed method adaptive and applicable to a wide range of images with different contrast degradations. The detail image is enhanced using the newly introduced parameter RoE, which ensures that the enhancement of the detail image is in fine tune with the base image. The enhanced base and detail images are combined and scaled to bring the intensity levels to the permitted range. Finally, mean adjustment is applied to develop the final improved image. The approach improves visual contrast while preserving naturalness. The simulation results on typical datasets show that the suggested technique outperforms numerous state-of-the-art as well as traditional algorithms for extremely degraded images. [ABSTRACT FROM AUTHOR]

ABSTRACT Aim Materials and Methods Results Conclusion To develop and evaluate a novel multi‐method micro‐computed tomography (μCT) imaging protocol for enhanced visualization of both hard and soft tissues in murine mandibles, addressing the limitations of traditional imaging techniques in dental research.We employed a contrast‐enhanced (CE) μCT imaging technique using Lugol's iodine as a contrast agent to visualize the intricate structures of murine mandibles. The protocol involved the combination of conventional μCT imaging as well as CE‐μCT, including decalcification with EDTA, allowing for simultaneous assessment of hard and soft tissues. The method is compared with standard imaging modalities, and the ability to visualize detailed anatomical features is discussed.The CE‐μCT imaging technique provided superior visualization of murine mandibular structures, including dental pulp, periodontal ligaments and the surrounding soft tissues, along with conventional μCT imaging of alveolar bone and teeth. This method revealed detailed anatomical features with high specificity and contrast, surpassing traditional imaging approaches.Our findings demonstrate the potential of CE‐μCT imaging with Lugol's iodine as a powerful tool for dental research. This technique offers a comprehensive view of the murine mandible, facilitating advanced studies in tissue engineering, dental pathology and the development of dental materials. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) creates detailed images by combining a powerful magnetic field with high-frequency radio waves. MRI images need to increase brightness and contrast to facilitate distinguishing diseases. This study aims to improve the MRI images depending on the suggested algorithm, including three main stages. The first is to divide the image into three main areas using Multilevel image thresholds and then improve using CLAHE for each area separately. Finally, these images combine to form one image and improve it again. By analyzing the results and calculating non-referenced quality measures, the proposed method obtained the best quality results compared to the rest of the methods with quality rates of EN(6.14), AG(6.79), and CEM(0.84), which indicates excellent success in increasing clarity in those images. [ABSTRACT FROM AUTHOR]

Passive millimeter-wave (MMW) and TeraHertz (THz) imaging systems have become increasingly popular in recent years due to their cost-effectiveness and non-invasive characteristics compared to active systems, prompting a surge in research interest. Evaluating the quality of reconstructed images used in these systems is essential for revealing the fine details. General image quality metrics such as the structural similarity index (SSIM) and the peak signal-to-noise ratio (PSNR) require a reference image in order to compare the reconstructed image. However, there is a notable gap in the literature regarding the evaluation of reconstruction or deconvolution algorithms with a reference image in the passive MMW/THz bands. This study proposes a reference image generation technique for passive MMW/THz imaging systems using an infrared imaging system that shares a similar physical background. Then, passive MMW/THz images were evaluated using the reference images at varying target distances and spatial resolutions. Besides these, the assessment of passive MMW/THz images with the SSIM and PSNR metrics after the reconstruction algorithms were performed. The metrics SSIM and PSNR, are inadequate in the evaluation of reconstruction algorithms alone in terms of concealed object (CO) detection. Because of this reason, the contrast level (CL) method was proposed to address the application-based shortcomings of PSNR and SSIM metrics. Hence, the image quality metric, CL, indicates that the Richardson–Lucy (RL) algorithm yielded superior results in variable optical configurations and target distances with the aid of CL metric. Finally, contrast enhancement techniques were developed in order to increase the contrast level of the CO. As a result, the introduction of these novel methods—the reference image generation technique using an infrared imaging system in passive MMW/THz bands, the evaluation of the reconstructed images with the application-based CL metric, and contrast enhancement techniques for single-band or multi-band imaging methods—holds the potential for the development of innovative techniques. These advancements may contribute to the creation of new applications within the passive MMW/THz bands, particularly focusing on the improvement of detection methods in the future. [ABSTRACT FROM AUTHOR]

For a better understanding of living tissues and materials, it is essential to study the intricate spatial relationship between cells and their surrounding tissue on the nanoscale, with a need for 3D, high‐resolution imaging techniques. In the case of bone, focused ion beam‐scanning electron microscopy (FIB‐SEM) operated in the backscattered electron (BSE) mode proves to be a suitable method to image mineralized areas with a nominal resolution of 5 nm. However, as clinically relevant samples are often resin‐embedded, the lack of atomic number (Z) contrast makes it difficult to distinguish the embedding material from unmineralized parts of the tissue, such as osteoid, in BSE images. Staining embedded samples with iodine vapor has been shown to be effective in revealing osteoid microstructure by 2D BSE imaging. Based on this idea, an iodine (Z = 53) staining protocol is developed for 3D imaging with FIB‐SEM, investigating how the amount of iodine and exposure time influences the imaging outcome. Bone samples stained with this protocol also remain compatible with confocal laser scanning microscopy to visualize the lacunocanalicular network. The proposed protocol can be applied for 3D imaging of tissues exhibiting mineralized and nonmineralized regions to study physiological and pathological biomineralization. [ABSTRACT FROM AUTHOR]

Sensor limitations in capturing devices and environmental factors can result in radiance artifacts in rendered images. This paper presents an entropy-driven exposure interpolation framework in the context of large exposure-ratio fusion. The proposed framework generates intermediate exposure-corrected images through transmission map estimation to obtain initial radiance and illumination maps. Fusion weight maps, within a pyramidal framework, are derived from the transmission map and spatial entropy, thereby enhancing the visual quality of images while preventing color artifacts. Experiments demonstrate that the proposed framework outperforms several state-of-the-art multi-exposure fusion schemes. [ABSTRACT FROM AUTHOR]

One of the most challenging, interesting, and influential areas in image processing is image enhancement. Image enhancement techniques manipulate the existing image so as to ameliorate the quality as well as the visual appearance of the image to the viewer. Different types of image enhancement methods are utilized to tackle the complex problems of image visualization in medical imaging. Many imaging techniques are available, such as CT scans, magnetic resonance imaging, X-rays, and others. MRI is a kind of scan that uses strong magnetic fields and radio waves to capture images of the internal structure of the patient's body. Medical imaging is an exceptionally normal and fundamental medium for clinical experts to conclude illnesses with respect to unseen regions inside the body. In many situations, these images suffer from low contrast and bad illumination. To overcome these problems of low contrast and poor illumination, this paper presents an enhancement scheme using a modified type-2 fuzzy set for MRI images. The results of the proposed scheme are shown in terms of both qualitative and quantitative analysis. All the experiments are carried out for a fixed value of a parameter β = 0.7 . For qualitative analysis, results are visualized with state-of-the-art methods and for quantitative analysis, PSNR, SSIM, AMBE, REC and PL are used. Qualitative and quantitative analysis bear witness to the fact that the performance of the proposed scheme is better in many places in comparison to other existing methods. [ABSTRACT FROM AUTHOR]

Retinal imaging often falls short in image quality due to limitations in imaging conditions. Issues such as low contrast and inadequate brightness are frequently encountered. However, fundus pictures play a crucial role in diagnosing various retinal diseases within the field of ophthalmology. Nonetheless, specific ocular abnormalities and capturing environments result in low-grade fundus images, hampering the diagnostic abilities of both human experts and machines. Analyzing color fundus images to detect retinal abnormalities necessitates enhanced representation of image properties, including contrast, illumination, and precise edge points. The proposed method introduces a new technique for improving color fundus photos. The algorithm comprises three stages. Firstly, a feed-forward denoising convolutional neural network (DnCNN) removes noise. Subsequently, a contrast enhancement method, recursive separated weighted histogram equalization (RSWHE), addresses low contrast issues. Finally, adaptive Gamma correction (AGC) improves uneven luminosity. Experiments were conducted using the STARE benchmark datasets to evaluate the algorithm. The suggested algorithm's output is equated against state-of-the-art enhancement methods. Objective validation was performed using performance parameters such as NIQE, PCQI, CEIQ, MEME, and PSNR. It suggests that the algorithm has the potential to serve as an efficient method for enhancing retinal images, thereby improving diagnostic capabilities in the field of ophthalmology. [ABSTRACT FROM AUTHOR]

Background: Adequate image enhancement of organs and blood vessels of interest is an important aspect of image quality in contrast‐enhanced computed tomography (CT). There is a need for an objective method for evaluation of vessel contrast that can be automatically and systematically applied to large sets of CT exams. Purpose: The purpose of this work was to develop a method to automatically segment and measure attenuation Hounsfield Unit (HU) in the portal vein (PV) in contrast‐enhanced abdomen CT examinations. Methods: Input CT images were processed by a vessel enhancing filter to determine candidate PV segmentations. Multiple machine learning (ML) classifiers were evaluated for classifying a segmentation as corresponding to the PV based on segmentation shape, location, and intensity features. A public data set of 82 contrast‐enhanced abdomen CT examinations was used to train the method. An optimal ML classifier was selected by training and tuning on 66 out of the 82 exams (80% training split) in the public data set. The method was evaluated in terms of segmentation classification accuracy and PV attenuation measurement accuracy, compared to manually determined ground truth, on a test set of the remaining 16 exams (20% test split) held out from public data set. The method was further evaluated on a separate, independently collected test set of 21 examinations. Results: The best classifier was found to be a random forest, with a precision of 0.892 in the held‐out test set to correctly identify the PV from among the input candidate segmentations. The mean absolute error of the measured PV attenuation relative to ground truth manual measurement was 13.4 HU. On the independent test set, the overall precision decreased to 0.684. However, the PV attenuation measurement remained relatively accurate with a mean absolute error of 15.2 HU. Conclusions: The method was shown to accurately measure PV attenuation over a large range of attenuation values, and was validated in an independently collected dataset. The method did not require time‐consuming manual contouring to supervise training. The method may be applied to systematic quality control of contrast‐enhanced CT examinations. [ABSTRACT FROM AUTHOR]

Background: The best settings of deep learning image reconstruction (DLIR) algorithm for abdominal low-kiloelectron volt (keV) virtual monoenergetic imaging (VMI) have not been determined. Purpose: To determine the optimal settings of the DLIR algorithm for abdominal low-keV VMI. Material and Methods: The portal-venous phase computed tomography (CT) scans of 109 participants with 152 lesions were reconstructed into four image series: VMI at 50 keV using adaptive statistical iterative reconstruction (Asir-V) at 50% blending (AV-50); and VMI at 40 keV using AV-50 and DLIR at medium (DLIR-M) and high strength (DLIR-H). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of nine anatomical sites were calculated. Noise power spectrum (NPS) using homogenous region of liver, and edge rise slope (ERS) at five edges were measured. Five radiologists rated image quality and diagnostic acceptability, and evaluated the lesion conspicuity. Results: The SNR and CNR values, and noise and noise peak in NPS measurements, were significantly lower in DLIR images than AV-50 images in all anatomical sites (all P < 0.001). The ERS values were significantly higher in 40-keV images than 50-keV images at all edges (all P < 0.001). The differences of the peak and average spatial frequency among the four reconstruction algorithms were significant but relatively small. The 40-keV images were rated higher with DLIR-M than DLIR-H for diagnostic acceptance (P < 0.001) and lesion conspicuity (P = 0.010). Conclusion: DLIR provides lower noise, higher sharpness, and more natural texture to allow 40 keV to be a new standard for routine VMI reconstruction for the abdomen and DLIR-M gains higher diagnostic acceptance and lesion conspicuity rating than DLIR-H. [ABSTRACT FROM AUTHOR]

Diagnosing diabetic retinopathy (DR) based on features that appear on fundus images is currently conducted through an eye exam by an ophthalmologist. Tracking DR progression manually is time-consuming and keen for a high-skill person. As the technology offered in industrial revolution (IR) 4.0, namely artificial intelligence, is shown to help in the medical diagnosis process, this study proposes an image enhancement algorithm based on a hybrid of contrast enhancement (CE) and particle swarm optimization (PSO). The proposed method incorporates contrast adjustment on the bright and dark region of LAB color space where the bright and dark region is initially segmented using K-mean PSO. 100 retinal fundus images are used for training and testing purposes. The proposed method undergoes qualitative and quantitative evaluation with a comparison between the two methods. The result indicates that the performance of the proposed method is more acceptable as compared to another two methods. [ABSTRACT FROM AUTHOR]

Early detection of diabetic retinopathy (DR) is crucial as it allows for timely intervention, preventing vision loss and enabling effective management of diabetic complications. This research performs detection of DR and DME at an early stage through the proposed framework which includes three stages: preprocessing, segmentation, feature extraction, and classification. In the preprocessing stage, noise filtering is performed by fuzzy filtering, artefact removal is performed by non-linear diffusion filtering, and the contrast improvement is performed by a novel filter called Adaptive Variable Distance Speckle (AVDS) filter. The AVDS filter employs four distance calculation methods such as Euclidean, Bhattacharya, Manhattan, and Hamming. The filter adaptively chooses a distance method which produces the highest contrast value amongst all 3 methods. From the analysis, hamming distance method was found to achieve better results for contrast and Euclidean distance showing less error value with high PSNR. The segmentation stage is performed using Improved Mask-Regional Convolutional Neural Networks (Mask RCNN). In the final stage, feature extraction and classification using novel Self-Spatial Attention infused VGG-16 (SSA-VGG-16), which effectively captures both global contextual relationships and critical spatial regions within retinal images, thereby improving the accuracy and robustness of DR and DME detection and grading. The effectiveness of the proposed method is assessed using two distinct datasets: IDRiD and MESSIDOR. [ABSTRACT FROM AUTHOR]

Human gait is an essential biometric feature in the area of computer vision research. Over the past ten years, there has been a growing demand for a non-contact biometric approach to identify potential candidates, mainly since the global COVID-19 epidemic emerged. Gait recognition involves automatically capturing and extracting characteristics of human movement, which are subsequently utilized to verify the identity of a moving individual. Nevertheless, covariates like walking while carrying a bag, changing clothes, environmental conditions, and any unusual gait patterns all have an impact on the accuracy of gait recognition accuracy. This paper presents a new end-to-end deep learning framework for human gait recognition. The proposed framework contains a few important steps that help in the improvement of the recognition accuracy. A contrast enhancement technique named Enhancing Human Body Shape and Reducing Noise is proposed at the initial step and used for the dataset augmentation. The second step involves deep learning architecture development, such as the proposed GNET-23 model and a fine-tuned pre-trained AlexNet model. Both models are trained on selected datasets and later extract deep features from the average pooling layer. A novel parallel correlation fusion technique is proposed to fuse the richer information of both models that are further optimized using an improved Satin Bowerbird optimization algorithm. Finally, the most optimal features are classified using Neural Networks and nearest-neighbor classifiers. The experiment was conducted using four different angles of publicly accessible CASIA-B datasets, resulting in mean accuracy scores of 91.6%, 96.2%, 94.3%, and 96.8%, respectively. The proposed framework surpasses other deep learning networks and recently published techniques in both accuracy and processing speed. [ABSTRACT FROM AUTHOR]

Background and objectives: Contrast enhancement in glioblastoma, IDH-wildtype is common but not systematic. In the era of the WHO 2021 Classification of CNS Tumors, the prognostic impact of a contrast enhancement and the pattern of contrast enhancement is not clearly elucidated. Methods: We performed an observational, retrospective, single-centre cohort study at a tertiary neurosurgical oncology centre (January 2006 - December 2022). We screened adult patients with a newly-diagnosed glioblastoma, IDH-wildtype in order to assess the prognosis role of the contrast enhancement and the pattern of contrast enhancement. Results: We included 1149 glioblastomas, IDH-wildtype: 26 (2.3%) had a no contrast enhancement, 45 (4.0%) had a faint and patchy contrast enhancement, 118 (10.5%) had a nodular contrast enhancement, and 960 (85.5%) had a ring-like contrast enhancement. Overall survival was longer in non-contrast enhanced glioblastomas (26.7 months) than in contrast enhanced glioblastomas (10.9 months) (p < 0.001). In contrast enhanced glioblastomas, a ring-like pattern was associated with shorter overall survival than in faint and patchy and nodular patterns (10.0 months versus 13.0 months, respectively) (p = 0.033). Whatever the presence of a contrast enhancement and the pattern of contrast enhancement, surgical resection was an independent predictor of longer overall survival, while age ≥ 70 years, preoperative KPS score < 70, tumour volume ≥ 30cm3, and postoperative residual contrast enhancement were independent predictors of shorter overall survival. Conclusion: A contrast enhancement is present in the majority (97.7%) of glioblastomas, IDH-wildtype and, regardless of the pattern, is associated with a shorter overall survival. The ring-like pattern of contrast enhancement is typical in glioblastomas, IDH-wildtype (85.5%) and remains an independent predictor of shorter overall survival compared to other patterns (faint and patchy and nodular). [ABSTRACT FROM AUTHOR]

Anatomical structure preservation throughout the denoising process is a challenge in the domain of medical imaging. The Rician noise introduced through the acquisition procedure by the Magnetic Resonance Imaging (MRI) scanner distorts the images. In this study, denoising using Wavelet-based Non-Local Median Filter (WBNLMF) and a novel contrast-enhancement method termed Improved Minimum Intensity Error Intuitionistic Fuzzy Contrast Enhancement (IMIEIFCET) is suggested. This methodology gives superior results while maintaining the edges and the brightness of the original image. An Attention Module-based Convolution Neural Network (AM-CNN) is suggested in the research as a methodology for skull stripping from MRI data. With a mean Dice coefficient of 0.998, a Sensitivity of 0.9975, and a Specificity of 0.9985, the proposed network exhibits result that are comparable to those of the specified Deep Learning (DL)-based technique.

PURPOSES: To provide abdominal contrast-enhanced MR image synthesis, we developed an gradient regularized multi-modal multi-discrimination sparse attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. METHODS: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). A Turing test and experts contours evaluated the image synthesis quality. RESULTS: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values < 0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, which is close to random guessing, supporting the models effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90 compared to the inter-operator DICE of 0.91. CONCLUSION: We demonstrated the function of a novel multi-modal MR image synthesis neural network GRMM-GAN for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

Due to the complex underwater environment and the selective absorption and scattering effect of water on light waves, underwater images often suffer from issues such as low contrast, color distortion, and blurred details. This paper presents a stable and effective algorithm for enhancing underwater images to address these challenges. Firstly, an improved color correction algorithm based on the gray world and minimum information loss is employed to remove the blue-green bias present in the images. Secondly, a contrast enhancement algorithm is based on the guided filter and wavelet decomposition to make the texture details of the image clearer. Then, the normalized weight map of the image is obtained to carry out multi-scale fusion. Finally, the fused image is applied to perform the multi-scale decomposition. The experimental results show that the algorithm proposed in this paper can correct the image color deviation, improve the image contrast and enhance the image details. [ABSTRACT FROM AUTHOR]