Efficient Image Research Articles

Wavelet-based Filter Bank Approach for Image Compression and Enhancement in Alzheimer\'s Disease Diagnosis Using Medical Imaging

Abstract: This research presents a wavelet-based filter bank approach for image compression and enhancement in the context of Alzheimer's disease diagnosis using medical imaging. The proposed system leverages the PyWavelets and OpenCV libraries in Python to implement Discrete Wavelet Transform (DWT) and Inverse Discrete Wavelet Transform (IDWT) algorithms. The primary objective is to develop an efficient image compression technique while preserving visual quality and enhancing relevant features for improved diagnostic accuracy. The system utilizes filter banks to process wavelet coefficients, enabling selective enhancement of patterns or biomarkers associated with Alzheimer's disease. Results show that the decompressed images closely resemble the originals, with low Mean Squared Error (MSE) and high Peak Signal-to-Noise Ratio (PSNR) values. Visual inspection and quantitative metrics confirm the successful preservation of image quality and structural details. The wavelet coefficients visualization highlights the captured significant features crucial for reconstruction

Fast and efficient hard X-ray projection imaging below 10 nm resolution

Fast and efficient hard X-ray projection imaging below 10 nm resolution

Neural Substrates for Early Data Reduction in Fast Vision: A Psychophysical Investigation.

To ensure survival, the visual system must rapidly extract the most important elements from a large stream of information. This necessity clashes with the computational limitations of the human brain, so a strong early data reduction is required to efficiently process information in fast vision. A theoretical early vision model, recently developed to preserve maximum information using minimal computational resources, allows efficient image data reduction by extracting simplified sketches containing only optimally informative, salient features. Here, we investigate the neural substrates of this mechanism for optimal encoding of information, possibly located in early visual structures. We adopted a flicker adaptation paradigm, which has been demonstrated to specifically impair the contrast sensitivity of the magnocellular pathway. We compared flicker-induced contrast threshold changes in three different tasks. The results indicate that, after adapting to a uniform flickering field, thresholds for image discrimination using briefly presented sketches increase. Similar threshold elevations occur for motion discrimination, a task typically targeting the magnocellular system. Instead, contrast thresholds for orientation discrimination, a task typically targeting the parvocellular system, do not change with flicker adaptation. The computation performed by this early data reduction mechanism seems thus consistent with magnocellular processing.

Analyze the Impact, Reasons, and Optimization Strategies of the Image of AI Anchors on Consumer Purchase Intention in Live Streaming E-commerce

The importance of live streaming e-commerce in online shopping is increasing with the continuous development of live streaming technology. Artificial intelligence (AI), as a disruptive force, has introduced virtual anchors in the live streaming field, replacing live anchors for product introduction and interaction. The virtual anchor image, with its anthropomorphic appearance, interacts with the audience in real-time and is gradually being applied in various fields such as e-commerce, advertising, and social platforms. This study reviews how the image of AI anchors in live streaming e-commerce affects consumer trust and personalized experience, and further explores its impact on consumer purchase intention. Research has found that virtual anchor images can be divided into human and animal images based on their appearance, and different images have different impacts on consumer purchasing intentions. Humanized virtual anchors establish trust relationships and stimulate purchase intentions through rich expressions and actions; Personalized and customized design enhances the attractiveness and sense of identity of virtual anchors. Finally, regarding the application of enterprises in the field of virtual anchors, this article proposes anthropomorphic design, personalized image, and cultural adaptability strategies to improve the commercial efficiency and brand image of virtual anchors.

Multi-layer adaptive spatial-temporal feature fusion network for efficient food image recognition

Numerous deep learning methods have been developed to tackle the challenges of recognizing food images, including convolutional neural networks, deep feature extraction, and deep feature fusion methods. This research proposes a new architecture called ASTFF-Net that uses deep feature fusion to tackle various challenges in food recognition, including similarity patterns between two categories, multi-object problems, light conditions, camera position, noise objects, and blurred images. ASTFF-Net is a robust and adaptive spatial–temporal fusion network designed to address these challenges effectively. The ASTFF-Net architecture consisted of three networks. In the spatial feature extraction network, the ResNet50 architecture was used to extract robust spatial features, and the reduction operation was utilized to minimize parameter size. Subsequently, the spatial features were passed through a 1D convolution (Conv1D) to fit the features into the recurrent neural networks. In the temporal feature extraction network, the spatial features were given to the long short-term memory, allowing the network to learn from various long sequence patterns. In the adaptive feature fusion network, the robust spatial and temporal features were fused and assigned to the Conv1D, followed by the softmax function. The ASTFF-Net architecture is also intended to decrease the number of network parameters and prevent overfitting problems. Experimental results on four benchmark food image datasets: Food11, UEC Food-100, UEC Food-256, and ETH Food-101, demonstrate that the proposed ASTFF-Nets, particularly ASTFF-NetB3, were more competitive compared with other existing methods.

Phthalocyanine J-aggregate nanoparticles with enormous-redshifted and intense absorption: Potential structure-J-aggregation relationships and application in tumor-associated macrophages-targeted phototheranostics

Phthalocyanines (Pcs) are considered promising in cancer phototherapy. However, their maximum absorption wavelengths are only around 700 nm, which cannot allow deep tissue penetration and leads to poor therapeutic efficacy. To expand their clinical application, significantly shifting their absorption to longer wavelengths is urgently required. Dye J-aggregates exhibit a redshifted absorption relative to its monomer. However, Pc J-aggregates with enormous-redshifted and intense absorption is rarely reported, and little is known about the relationships between Pc structure and J-aggregation. Herein, such Pc J-aggregates are ingeniously conceived. With a yeast β-D-glucan-ursodeoxycholic acid conjugate as a potential tumor-associated macrophages (TAMs)-targeting carrier and 1-(4-carboxyethylphenoxy) zinc (II) phthalocyanine (Pc1) as a model, Pc1 J-aggregate nanoparticle (NanoPc1) is obtained via ultrasonication-aided emulsification-solvent evaporation technique. NanoPc1 displays strong absorption at 830 nm, with a 156 nm redshift. Further investigation on another twenty-four Pcs demonstrates that unsubstituted zinc (II) or magnesium (II) Pc and hydrophobic mono-substituted zinc (II) or magnesium (II) Pcs with mono-substituted phenoxy or phenylthio or naphthoxy as a substituent can readily form desired Pc J-aggregates with significant redshifts (140–165 nm). The other Pcs fail to form expected J-aggregates probably due to absence of central metals, steric hindrance on central metals (atoms), forming axial coordination on central metals, disorder tendency during self-assembly or hydrophilicity. The theoretical calculation indicates that Pc1 in its J-aggregates exhibits a spiral-like arrangement, and the reduction in the energy gap between HOMO and LUMO and variation of intermolecular π-π interaction caused by J-aggregate formation are responsible for the huge redshift. Additionally, using NanoPc1 as an exemplar, such Pc J-aggregate nanoparticles are substantiated to afford TAMs-targeted and efficient tri-modal imaging and photothermal therapy in a H22 mouse model.

Delivering Consistent and Efficient Imaging for SPA with HexAuFoil® Sample Supports

Delivering Consistent and Efficient Imaging for SPA with HexAuFoil® Sample Supports

An efficient ultrasonic wavenumber-domain plane wave imaging method towards the inspection of curved structures

Ultrasonic phased array testing is commonly employed for inspecting curved structures. Conventional plane wave imaging techniques, based on delay-and-sum in the time-domain, offer high image quality and inspection accuracy but suffer from low frame rates due to their high computational complexity. In this work, an efficient wavenumber-domain imaging method that combines non-stationary wavefield extrapolation and f-k migration is proposed for curved structure inspection. Special emission focal laws are designed to generate a sequence of steered plane waves through the curved interface. The raw data is then extrapolated to the top boundary of the region of interest, followed by f-k migration to reconstruct images with high time efficiency. Simulation and experimental evaluations demonstrate a time reduction by a factor of up to 32.24 compared to conventional time-domain plane wave image reconstruction with equivalent image quality, highlighting its potential for monitoring flaws in real-time.

Temperature-Responsive "Nano-to-Micro" Transformed Polymersomes for Enhanced Ultrasound/Fluorescence Dual Imaging-Guided Tumor Phototherapy.

The perfect integration of microbubbles for efficient ultrasound imaging and nanocarriers for intelligent tumor-targeting delivery remains a challenge in precise tumor theranostics. Herein, we exquisitely fabricated laser-activated and targeted polymersomes (abbreviated as FIP-NPs) for simultaneously encapsulating the photosensitizer indocyanine green (ICG) and the phase change agent perfluorohexane (PFH). The formulated FIP-NPs were nanosize and effectively accumulated into tumors as observed by ICG fluorescence imaging. When the temperature rose above 56 °C, the encapsulated PFH transformed from liquid to gas and the FIP-NPs underwent balloon-like enlargement without structure destruction. Impressively, the enlarged FIP-NPs fused with adjacent polymersomes to form even larger microparticles. This temperature-responsive "nano-to-micro" transformation and fusion process was clearly demonstrated, and FIP-NPs showed greatly improved ultrasound signals. More importantly, FIP-NPs achieved dramatic antitumor efficacy through ICG-mediated phototherapy. Taken together, the novel polymersomes achieved excellent ultrasound/fluorescence dual imaging-guided tumor phototherapy, providing an optimistic candidate for the application of tumor theranostics.

Hybrid design scheme for enabling large-aperture diffractive achromat imaging

Diffractive achromats (DAs) combined with image processing algorithms offer a promising lens solution for high-performance ultra-thin imagers. However, the design of large-aperture DAs that align seamlessly with image processing algorithms remains challenging. Existing sequential methods, which prioritize focusing efficiency in DAs before selecting an algorithm, may not achieve a satisfactory match due to an ambiguous relationship between efficiency and final imaging quality. Conversely, image-quality-oriented end-to-end design often entails high computational complexity for both front-end optics and back-end algorithms, impeding the development of large-aperture designs. To address these issues, we present a hybrid design scheme that begins with end-to-end optimization of the DA with the simplest image processing algorithm, i.e., Wiener filter, significantly reducing the back-end complexity. Subsequently, we apply complex algorithm fine-tuning to further enhance image quality. We validate this hybrid design scheme through extensive investigations on several DA imagers. Our results demonstrate a reduction in memory requirement by approximately 50% while maintaining a high imaging quality with a reasonably large aperture. As a case in point, we simulated a DA imager with a 25 mm diameter aperture. Furthermore, our hybrid design scheme provides two crucial insights. Firstly, we find no strong linear correlation between focusing efficiency and imaging quality, which challenges the conventional understanding. Secondly, we establish a prediction formula for imaging quality, benefiting from the hybrid design scheme.

A Versatile One-Step Enzymatic Strategy for Efficient Imaging and Mapping of Tumor-Associated Tn Antigen.

Tn antigen (CD175), recognized as the precursor monosaccharide (α-GalNAc) of mucin O-glycan, is a well-known tumor-associated carbohydrate antigen (TACA). It has emerged as a potential biomarker for cancer diagnosis and prognosis. However, the role it plays in cancer biology remains elusive due to the absence of a sensitive and selective detection method. In this study, we synthesized two new probes based on a unique uridine-5'-diphospho-α-d-galactose (UDP-Gal) derivative, each functionalized with either a fluorescence or a cleavable biotin tag, to develop an innovative one-step enzymatic labeling strategy, enabling the visualization, enrichment, and site-specific mapping of the Tn antigen with unparalleled sensitivity and specificity. Our versatile strategy has been successfully applied to detect and image Tn antigen across various samples, including the complex cell lysates, live cells, serum, and tissue samples. Compared to the traditional lectin method, this one-step enzymatic method is simpler and more efficient (>10/100-fold in sensitivity). Furthermore, it allowed us to map 454 Tn-glycoproteins and 624 Tn-glycosylation sites from HEK293FTn+ and Jurkat cells. Therefore, our strategy provides an exceptionally promising tool for revealing the biological functions of the Tn antigen and advancing cancer diagnostics.

Autonomous three-dimensional oscillator with two and four wings attractors embedded in the microcontroller: analysis, amplitude controls, random number generator, and image encryption application

Robust chaotic systems offer unpredictability, complex dynamics, noise-like properties, efficient bifurcation behavior, and the ability to model real-world phenomena, making them valuable in diverse scientific and engineering applications. This paper details on the dynamical appraisal, amplitude controls, microcontroller execution, Random number generator (RNG) of an autonomous three-dimensional (3D) oscillator with two and four wings attractors (ATDOTFWA), and its image encryption application. Thanks to the Routh-Hurwitz criteria, five steady states found in the ATDOTFWA are classified as stable or unstable, depending on its two control parameters. During the numerical simulations employing the Runge–Kutta scheme, the ATDOTFWA exhibit a wide range of dynamic behaviors, including no oscillations, Hopf bifurcation, limit cycle, five distinct presentations of two wings chaotic structures, monostable and bistable two wings chaotic structures, bistable and monostable regular oscillations, chaotic bursting characteristics, coexistence of period-2-oscillations and four wings chaotic structure, and four wings chaotic attractor which were validated experimentally by the microcontroller implementation. The total and partial controls of the amplitude are achieved in the ATDOTFWA. A RNG is designed based on the ATDOTFWA, and the generated random numbers are successfully tested using the ENT and NIST 800–22 statistical test suites, demonstrating the reliability of the ATDOTFWA-based RNG. This reliability is further confirmed through the application of the ATDOTFWA-based RNG in an efficient and secure image encryption process, where the generated random numbers are used as the encryption key. The effectiveness of the image encryption process is validated through comprehensive cryptanalysis, with an encryption time of 0.1923 s for a 512×512 image, an average normalized pixel change rate (NPCR) of 99.6126%, an average unified average changing intensity (UACI) of 33.4578%, and an average information entropy of 7.9994.

An Overview onEffectiveness of Activation Functions in Processing Medical Images

This study studies the impact of activation functions in the field of machine learning and deep learning in general and especially on medical images for different aims such as classification, clustering, feature engineering. Important components that add nonlinearity and allow networks to learn intricate patterns are activation extraction, training and etc. The study first starts by explaining various activation function types that are commonly used in NN applications and fields. Subsequently, a comprehensive comparative analysis is conducted, to evaluate how activation functions perform in terms of accuracy and their impact on speed convergence. Understanding how activation functions impact the categorization of medical imagery is crucial to the study's findings. In additions, the study illustrates overview of which activation functions yield optimal results. The Main results contribute how to select best activation functions that suits most accurate and efficient medical image classification basedon this overview, any researcher can choose best activation function after reading this overview.

Dual path features interaction network for efficient image super-resolution

Image super-resolution (SR) is a crucial task in computer vision that involves reconstructing a low-resolution (LR) image into its high-resolution (HR) counterpart. Transformer-based methods excel at establishing long-range dependency but face challenges with high-complexity computations and capturing fine-grained features. Conversely, CNN-based methods are advantageous in capturing fine-grained features but are limited by fixed receptive fields. Additionally, most SR methods suffer from channel redundancy, leading to higher computational overhead. In this paper, we propose a Dual Path Features Interaction Network (DPFINet) to achieve efficient image SR, which consists of two components: a) To alleviate the issue of feature channel redundancy, a Local–Global Features Modeling (LGFM) method is newly proposed, which concurrently models global and local features by splitting features along different channels. In LGFM, a Shift Window Linear Attention (SWLA) layer is adopted to effectively capture global information through a large shift window based on the split features. Meanwhile, a Multi-Scale Detail Enhancement (MSDE) layer is designed, where the split other features are encoded to facilitate detail reconstruction through an interactive fusion of semantic and local information, thereby addressing the limitations of SWLA in capturing fine-grained features. b) A Cross-Level Features Interaction (CLFI) method is proposed to fuse global and local features modeled by different network structures (SWLA and MSDE), where a novel residual fusion mechanism is designed to preserve both global and local information while complementing each other. Extensive experiments demonstrate that our method outperforms most state-of-the-art SR methods on five benchmark datasets. Notably, during inference, our approach improves performance by 0.41 dB and reduces memory consumption by approximately 79% compared to DiVANet (Behjati et al., 2023) on the Manga109 (×4) dataset.

Design and Analysis of a Novel Fractional-Order System with Hidden Dynamics, Hyperchaotic Behavior and Multi-Scroll Attractors

The design of chaotic systems with complex dynamic behaviors has always been a key aspect of chaos theory in engineering applications. This study introduces a novel fractional-order system characterized by hidden dynamics, hyperchaotic behavior, and multi-scroll attractors. By employing fractional calculus, the system’s order is extended beyond integer values, providing a richer dynamic behavior. The system’s hidden dynamics are revealed through detailed numerical simulations and theoretical analysis, demonstrating complex attractors and bifurcations. The hyperchaotic nature of the system is verified through Lyapunov exponents and phase portraits, showing multiple positive exponents that indicate a higher degree of unpredictability and complexity. Additionally, the system’s multi-scroll attractors are analyzed, showcasing their potential for secure communication and encryption applications. The fractional-order approach enhances the system’s flexibility and adaptability, making it suitable for a wide range of practical uses, including secure data transmission, image encryption, and complex signal processing. Finally, based on the proposed fractional-order system, we designed a simple and efficient medical image encryption scheme and analyzed its security performance. Experimental results validate the theoretical findings, confirming the system’s robustness and effectiveness in generating complex chaotic behaviors.

Secure and efficient content-based image retrieval using dominant local patterns and watermark encryption in cloud computing

Secure and efficient content-based image retrieval using dominant local patterns and watermark encryption in cloud computing

Monocular Vision Sensor-Based Indoor Road and Stair Detection

Road detection is an essential component of indoor robot navigation. Vision sensors have great advantages in road detection as they can provide rich information in terms of environmental perception. In this paper, a monocular vision sensor-based method for indoor road and stair detection is proposed, which detects feasible areas in indoor environments very fast without paying attention to detailed features of walls or other obstacles. More specifically, for a given indoor road image captured by an on-board vision sensor, the simple linear iterative clustering (SLIC) algorithm-based approach for efficient image segmentation is introduced. Then, according to the DBSCAN algorithm, the generated superpixels are clustered to form large areas of view. The initial road area is obtained through a safe window on the middle bottom of the image. In order to achieve a more accurate road segmentation, the initial image is processed by the binary search, edge detection based on the Canny operator and straight-line detection and location based on the Hough transform, which integrates edge and stair information into road detection. Several experiments are performed to evaluate the performance of the proposed method. The experimental results demonstrate that the proposed method could accurately detect road information and staircase information in images and succeeds in addressing the indoor road-detection problem.

An efficient image classification and segmentation method for crime investigation applications

AbstractThe field of forensic science is experiencing significant growth, largely driven by the increasing integration of holographic and immersive technologies, along with their associated head-mounted displays. These immersive systems have become increasingly vital in resolving critical crimes as they facilitate communication, interaction, and collaboration. Given the sensitive nature of their work, crime investigators require substantial technical support. There is a pressing need for accurate documentation and archiving of crime scenes, which can be addressed by leveraging 3D scanned scenes to accurately represent evidence and expected scenarios. This study aims to develop an enhanced AR. system that can be deployed on hologram facilities such as the Microsoft HoloLens. The proposed system encompasses two main approaches, namely image classification and image segmentation. Image classification utilizes various deep learning models, including lightweight convolutional neural networks (CNNs) and convolutional Long-Short Term Memory (ConvLSTM). Additionally, the image segmentation approach is based on the fuzzy active contour model (FACM). The effectiveness of the proposed system was evaluated for both classification and segmentation tasks, utilizing metrics such as accuracy, sensitivity, precision, and F1 score. The simulation results indicate that the proposed system achieved a 99% accuracy rate in classification and segmentation tasks, positioning it as an effective solution for detecting bloodstain patterns in AR applications.

Efficient Blind Image Deblurring Network Based on Frequency Decomposition

Efficient Blind Image Deblurring Network Based on Frequency Decomposition

Integrating Clinical Data and Medical Imaging in Lung Cancer: Feasibility Study Using the Observational Medical Outcomes Partnership Common Data Model Extension.

Digital transformation, particularly the integration of medical imaging with clinical data, is vital in personalized medicine. The Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) standardizes health data. However, integrating medical imaging remains a challenge. This study proposes a method for combining medical imaging data with the OMOP CDM to improve multimodal research. Our approach included the analysis and selection of digital imaging and communications in medicine header tags, validation of data formats, and alignment according to the OMOP CDM framework. The Fast Healthcare Interoperability Resources ImagingStudy profile guided our consistency in column naming and definitions. Imaging Common Data Model (I-CDM), constructed using the entity-attribute-value model, facilitates scalable and efficient medical imaging data management. For patients with lung cancer diagnosed between 2010 and 2017, we introduced 4 new tables-IMAGING_STUDY, IMAGING_SERIES, IMAGING_ANNOTATION, and FILEPATH-to standardize various imaging-related data and link to clinical data. This framework underscores the effectiveness of I-CDM in enhancing our understanding of lung cancer diagnostics and treatment strategies. The implementation of the I-CDM tables enabled the structured organization of a comprehensive data set, including 282,098 IMAGING_STUDY, 5,674,425 IMAGING_SERIES, and 48,536 IMAGING_ANNOTATION records, illustrating the extensive scope and depth of the approach. A scenario-based analysis using actual data from patients with lung cancer underscored the feasibility of our approach. A data quality check applying 44 specific rules confirmed the high integrity of the constructed data set, with all checks successfully passed, underscoring the reliability of our findings. These findings indicate that I-CDM can improve the integration and analysis of medical imaging and clinical data. By addressing the challenges in data standardization and management, our approach contributes toward enhancing diagnostics and treatment strategies. Future research should expand the application of I-CDM to diverse disease populations and explore its wide-ranging utility for medical conditions.