Enhancement Techniques Research Articles

Low-light image enhancement guided by multi-domain features for detail and texture enhancement

Low-light image enhancement holds significant value in the fields of computer vision and image processing, such as in applications like surveillance photography and medical imaging. Images captured in low-light environments typically suffer from significant noise levels, low contrast, and color distortion. Although existing low-light image enhancement techniques can improve image brightness and contrast to some extent, they often introduce noise or result in over-enhancement, leading to the loss of detail and texture. This paper introduces an innovative approach to low-light image enhancement by fusing spatial and frequency domain features while optimizing them with multiple loss functions. The core of the algorithm lies in its multi-branch feature extraction, multi-loss function constraints, and a carefully designed model structure. In particular, the model employs an encoder-decoder architecture, where the encoder extracts spatial features from the image, the Fourier feature extraction module captures frequency domain information, and the histogram feature encoder-decoder module processes global brightness distribution. These extracted features are then fused and reconstructed in the decoder to produce the enhanced image. In terms of loss functions, the algorithm combines perceptual loss, structural similarity loss, Fourier loss, and histogram loss to ensure comprehensive and natural enhancement effects. The novelty of this algorithm lies not only in its multi-branch feature extraction design but also in its unique model structure, which synergistically improves image quality across different domains, effectively preventing over-enhancement, and ultimately achieving a balanced enhancement of brightness, details, and texture. Experimental results on multiple datasets, including SIDD, LOL, MIT-Adobe-FiveK, and LOL-v2-synthetic, demonstrate that the proposed method outperforms existing techniques in terms of image detail, texture, and brightness. Specifically, it achieves a PSNR of 27.52 dB on the LOL dataset, surpassing Wavelet Diffusion by 1.19 dB. Additionally, on the LOL-v2-synthetic dataset, it achieves a PSNR of 29.56 dB, exceeding Wavelet Diffusion by 3.06 dB. These results demonstrate a significant enhancement in the visual quality of low-light images.

Enhanced MRI brain tumor detection and classification via topological data analysis and low-rank tensor decomposition

The advent of artificial intelligence in medical imaging has paved the way for significant advancements in the diagnosis of brain tumors. This study presents a novel ensemble approach that uses magnetic resonance imaging (MRI) to identify and categorize common brain cancers, such as pituitary, meningioma, and glioma. The proposed workflow is composed of a two-fold approach: firstly, it employs non-trivial image enhancement techniques in data preprocessing, low-rank Tucker decomposition for dimensionality reduction, and machine learning (ML) classifiers to detect and predict the type of brain tumor. Secondly, persistent homology (PH), a topological data analysis (TDA) technique, is exploited to extract potential critical areas in MRI scans. When paired with the ML classifier output, this additional information can help domain experts to identify areas of interest that might contain tumor signatures, improving the interpretability of ML predictions. When compared to automated diagnoses, this transparency adds another level of confidence and is essential for clinical acceptance. The performance of the system was quantitatively evaluated on a well-known MRI dataset, with an overall classification accuracy of 97.28% using an extremely randomized trees model. The promising results show that the integration of TDA, ML, and low-rank approximation methods is a successful approach for brain tumor identification and categorization, providing a solid foundation for further study and clinical application.

An Integrated Approach using YOLOv8 and ResNet, SeResNet & Vision Transformer (ViT) Algorithms based on ROI Fracture Prediction in X-ray Images of the Elbow.

In this study, we harnessed three cutting-edge algorithms' capabilities to refine the elbow fracture prediction process through X-ray image analysis. Employing the YOLOv8 (You only look once) algorithm, we first identified Regions of Interest (ROI) within the X-ray images, significantly augmenting fracture prediction accuracy. Subsequently, we integrated and compared the ResNet, the SeResNet (Squeeze-and-Excitation Residual Network) ViT (Vision Transformer) algorithms to refine our predictive capabilities. Furthermore, to ensure optimal precision, we implemented a series of meticulous refinements. This included recalibrating ROI regions to enable finer-grained identification of diagnostically significant areas within the X-ray images. Additionally, advanced image enhancement techniques were applied to optimize the X-ray images' visual quality and structural clarity. These methodological enhancements synergistically contributed to a substantial improvement in the overall accuracy of our fracture predictions. The dataset utilized for training, testing & validation, and comprehensive evaluation exclusively comprised elbow X-ray images, where predicting the fracture with three algorithms: Resnet50; accuracy 0.97, precision 1, recall 0.95, SeResnet50; accuracy 0.97, precision 1, recall 0.95 & ViTB- 16 with high accuracy of 0.99, precision same as the other two algorithms, with a recall of 0.95. This approach has the potential to increase the precision of diagnoses, lessen the burden of radiologists, easily integrate into current medical imaging systems, and assist clinical decision-making, all of which could lead to better patient care and health outcomes overall.

SR-Forest: A Genetic Programming-Based Heterogeneous Ensemble Learning Method

Ensemble learning methods have been widely used in machine learning in recent years due to their high predictive performance. With the development of genetic programming-based symbolic regression methods, many papers begin to choose a popular ensemble learning method, random forests, as the baseline competitor. Instead of considering them as competitors, an alternative idea might be to consider symbolic regression as an enhancement technique for random forest. Genetic programming-based symbolic regression methods which fit a smooth function are complementary to the piecewise nature of decision trees, as the smooth variation is common in regression problems. In this article, we propose to form an ensemble model with symbolic regression-based decision trees to address this issue. Furthermore, we design a guided mutation operator to speed up the search on high-dimensional problems, a multi-fidelity evaluation strategy to reduce the computational cost and an ensemble selection mechanism to improve predictive performance. Finally, experimental results on a regression benchmark with 120 datasets show that the proposed ensemble model outperforms 25 existing symbolic regression and ensemble learning methods. Moreover, the proposed method can provide notable insights on an XGBoost hyperparameter performance prediction task, which is an important application area of ensemble learning methods.

Advanced Filtering and Enhancement Techniques for Diabetic Retinopathy Image Analysis

Diabetic retinopathy is a leading cause of visual impairment and blindness in diabetes sufferers. Early detection is crucial to prevent severe outcomes. This study presents an image processing method for retinal images to aid early detection. The method involves four steps: image enlargement, preprocessing, enhancement, and convolution. First, an algorithm enlarges the retinal image to increase resolution and reveal finer details. Preprocessing uses a min-max filtering algorithm to reduce noise and improve image quality. Next, specific pixel range enhancement techniques further refine the image and highlight relevant features. Finally, convolution with customized kernels detects and emphasizes areas indicating diabetic retinopathy, such as aneurysms and hemorrhages. Experimental results show improvement in image clarity and detail, enabling more accurate detection of diabetic retinopathy features. The correlation results are as follows: Filtering (0.35275, 0.20157, 0.4345), Enhancement (0.3214, 0.15823 0.34674), and Convolution (0.33542, 0.15758, 0.36826). The proposed algorithm enhances early detection and diagnosis by improving retinal image quality. Future work can optimize the algorithm and validate results with larger datasets, aiming to refine the determination of areas or pixel values relevant to diabetic retinopathy.

Ti3C2Tx MXene deposition: A simple surface engineering technique for dual enhancement of biological functions for nonbearing applications

Implant-associated complications, such as infection and poor osseointegration, present significant challenges in the field of biomedical implants. To address these issues, it is crucial to develop implant surfaces that possess both bacteriostatic and osteoconductive properties. In recent years, the field of surface modification for metallic substrates using two-dimensional materials has emerged as a highly promising strategy to enhance their biological properties. Among these materials, MXenes stand out as an excellent candidate for surface modifications due to their unique properties, such as biocompatibility, high specific surface area, and tunable chemical composition. In the present study, we introduce a simple deposition method of Ti3C2Tx MXene films on SS316L substrates to improve surface-cell interactions. The differentiation study demonstrated the alkaline phosphatase (ALP) enzyme activity on Ti3C2Tx-MXene-coated samples without osteogenic medium compared to uncoated samples in both, basic and osteogenic media. Moreover, the bacteriostatic character of the deposited MXene-coatings was confirmed against Gram-positive Staphylococcus aureus as well as Gram-negative Escherichia coli bacteria. The improved stimulation of both cell osteogenic differentiation and distinctive antimicrobial features triggered by Ti3C2Tx-MXene-coatings emphasizes their great potential as implant surface modifiers to improve integration and reduce the risk of infection in various biomedical applications.

High efficiency regulation method to generate an illumination source by adopting the micromirror array in DUV lithography

Source and mask optimization (SMO) is an important lithography resolution enhancement technique for 22 nm technology nodes and beyond in lithography. This technique generates freeform sources by adjusting the inclination angle of the micromirror array (MMA). In this paper, a high efficiency regulation method to generate an illumination source by adopting the micromirror array in DUV lithography is proposed. The number and inclination angles of micromirrors required for adjustment to convert the initial source into any illumination source are quickly and accurately obtained by using the proposed method. The illumination source is obtained on the pupil plane by adjusting the inclination angles of some micromirrors. The simulation results show that the initial source is converted into another illumination source with different complexities by adjusting some micromirrors. Compared with the traditional MMA allocation method, when the initial source is the freeform source, the regulation efficiency of micromirrors has been improved by at least 20%. The method reduces the regulation time of micromirrors and the number of micromirrors required for adjustment. Moreover, the number of micromirrors required for adjustment is positively correlated with the coherence coefficient. The results illustrate that this method is effective and has significant engineering implications.

End-to-end AI pipeline optimization: Benchmarking and performance enhancement techniques for recommendation systems

End-to-end AI pipeline optimization is critical for improving the efficiency and performance of recommendation systems, which play a pivotal role in personalizing user experiences across various domains. This review explores benchmarking and performance enhancement techniques tailored to recommendation systems within AI pipelines. The objective is to streamline the processes involved in data ingestion, feature engineering, model training, and deployment to achieve optimal system performance and user satisfaction. Recommendation systems typically involve complex workflows that require continuous optimization. Benchmarking serves as a foundational step, enabling the identification of bottlenecks and inefficiencies within the pipeline. By establishing clear performance metrics, such as precision, recall, and latency, benchmarking allows for the comparative analysis of different algorithms, data processing methods, and system configurations. These metrics guide the selection of the most suitable models and techniques, thereby enhancing overall system effectiveness. Performance enhancement techniques are then applied to various stages of the AI pipeline. Advanced methods in feature engineering, such as automated feature selection and dimensionality reduction, can significantly improve model accuracy while reducing computational overhead. In the model training phase, techniques like hyperparameter tuning, gradient-based optimization, and distributed training are employed to accelerate convergence and improve model generalization. Additionally, optimization strategies at the deployment stage, including model compression, quantization, and the use of specialized hardware, are crucial for minimizing latency and resource consumption. This review also highlights the importance of continuous monitoring and feedback loops to maintain the effectiveness of recommendation systems in dynamic environments. By integrating real-time analytics and adaptive algorithms, systems can adjust to changing user behaviors and preferences, ensuring sustained performance improvements. In conclusion, optimizing end-to-end AI pipelines for recommendation systems involves a multifaceted approach that includes benchmarking, feature engineering, model training, and deployment enhancements. These efforts collectively contribute to more efficient, scalable, and accurate recommendation systems, ultimately leading to better user experiences and operational efficiencies. This paper will focus on optimizing AI pipelines for recommendation systems, covering the entire process from data extraction and feature engineering to model deployment and performance benchmarking. It will discuss techniques for identifying and mitigating performance bottlenecks in different computing environments, providing valuable insights for enhancing the efficiency of recommendation systems, which are crucial for various applications.

Fruit and vegetable leaf disease recognition based on a novel custom convolutional neural network and shallow classifier.

Fruits and vegetables are among the most nutrient-dense cash crops worldwide. Diagnosing diseases in fruits and vegetables is a key challenge in maintaining agricultural products. Due to the similarity in disease colour, texture, and shape, it is difficult to recognize manually. Also, this process is time-consuming and requires an expert person. We proposed a novel deep learning and optimization framework for apple and cucumber leaf disease classification to consider the above challenges. In the proposed framework, a hybrid contrast enhancement technique is proposed based on the Bi-LSTM and Haze reduction to highlight the diseased part in the image. After that, two custom models named Bottleneck Residual with Self-Attention (BRwSA) and Inverted Bottleneck Residual with Self-Attention (IBRwSA) are proposed and trained on the selected datasets. After the training, testing images are employed, and deep features are extracted from the self-attention layer. Deep extracted features are fused using a concatenation approach that is further optimized in the next step using an improved human learning optimization algorithm. The purpose of this algorithm was to improve the classification accuracy and reduce the testing time. The selected features are finally classified using a shallow wide neural network (SWNN) classifier. In addition to that, both trained models are interpreted using an explainable AI technique such as LIME. Based on this approach, it is easy to interpret the inside strength of both models for apple and cucumber leaf disease classification and identification. A detailed experimental process was conducted on both datasets, Apple and Cucumber. On both datasets, the proposed framework obtained an accuracy of 94.8% and 94.9%, respectively. A comparison was also conducted using a few state-of-the-art techniques, and the proposed framework showed improved performance.

A Systematic Investigation Based on BCI and EEG Implemented using Machine Learning Algorithms

BCI is a strong tool that improves human-system communication. It improves the brain's ability to interact with its surroundings. Recent decades have seen substantial advances in neuroscience and computer science. This has made BCI a leader in computational neuroscience and intelligence research. Recent technological advances including wearable sensing devices, real-time data streaming, machine learning, and deep learning have raised the need for electroencephalographic (EEG)-based brain-computer interface (BCI) in clinical and translational applications. EEG-based Brain-Computer Interfaces (BCIs) detect cognitive state variations throughout laborious tasks, making them advantageous for individuals. To fill in the gaps in the wide overview of the past five years (2019-2024), we surveyed the newest research on EEG signal detection and computational intelligence in brain-computer interfaces. To provide a more accurate account, we will begin by reviewing Brain-Computer Interface (BCI) technology and its main challenges. Modern signal detection and enhancement techniques for EEG signal collection and refinement follow. We also provide advanced computational intelligence methods for tracking, maintaining, and monitoring human cognitive and operational performance in everyday applications. Combinations, interpretable fuzzy models, transfer learning, and deep learning are used. We conclude with a sample of cutting-edge BCI-driven healthcare applications and explore future EEG-based BCI research.

UICE-MIRNet guided image enhancement for underwater object detection

Underwater object detection is a crucial aspect of monitoring the aquaculture resources to preserve the marine ecosystem. In most cases, Low-light and scattered lighting conditions create challenges for computer vision-based underwater object detection. To address these issues, low-colorfulness and low-light image enhancement techniques are explored. This work proposes an underwater image enhancement technique called Underwater Image Colorfulness Enhancement MIRNet (UICE-MIRNet) to increase the visibility of small, multiple, dense objects followed by underwater object detection using YOLOv4. UICE-MIRNet is a specialized version of classical MIRNet, which handles random increments of brightness features to address the visibility problem. The proposed UICE-MIRNET restrict brightness and also works on the improvement of the colourfulness of underwater images. UICE-MIRNet consists of an Underwater Image-Colorfulness Enhancement Block (UI-CEB). This block enables the extraction of low-colourful areas from underwater images and performs colour correction without affecting contextual information. The primary characteristics of UICE-MIRNet are the extraction of multiple features using a convolutional stream, feature fusion to facilitate the flow of information, preservation of contextual information by discarding irrelevant features and increasing colourfulness through proper feature selection. Enhanced images are then trained using the YOLOv4 object detection model. The performance of the proposed UICE-MIRNet method is quantitatively evaluated using standard metrics such as UIQM, UCIQE, entropy, and PSNR. The proposed work is compared with many existing image enhancement and restoration techniques. Also, the performance of object detection is assessed using precision, recall, and mAP. Extensive experiments are conducted on two standard datasets, Brackish and Trash-ICRA19, to demonstrate the performance of the proposed work compared to existing methods. The results show that the proposed model outperforms many state-of-the-art techniques.

Predictive process monitoring: concepts, challenges, and future research directions

Predictive Process Monitoring (PPM) extends classical process mining techniques by providing predictive models that can be applied at runtime during the execution of a business process, for example, to predict the sequence of the next event(s) in a case, its outcomes, or performance-related aspects such as the remaining processing time. These predictive models go beyond process mining’s inherent descriptive nature that is offered by typical process discovery, conformance checking, and model enhancement techniques. The growing interest in PPM is driven by its additional value proposition, i.e., delivering real-time information regarding the future execution of business process instances, thus allowing for better informed operational decision making and performance analysis. The rapid growth of PPM during the last ten years has left the field lacking a cohesive taxonomy and an explicit recognition of the prevailing challenges. This paper aims at closing this gap, by comprehensively defining PPM using a unified approach to the key terms and by discussing challenges and opportunities in the field. Specifically, we propose three overarching research challenges and nine research directions, which have been validated through a survey with PPM researchers.

Gold prospectivity mapping using “SWARA” model on geophysical datasets in parts of Ilesa Schist belt, Southwestern Nigeria

This study employed a knowledge–driven model (stepwise weight assessment ratio analysis (SWARA)) for the prospectivity mapping of gold in parts of Ilesa Schist belt, Southwestern Nigeria. Aeromagnetic, aero-radiometric and remote sensing (Atmospheric Spaceborne Thermal Emission and reflection Radiometer (ASTER) data) datasets were utilized for this study. Data enhancement techniques were performed on the aeromagnetic data to produce the lineament map of the study area. Also, analyses of the aeroradiometric and ASTER datasets were used in delineating hydrothermally altered zones in the study area. Lithology, lineament density, hydrothermal alteration and slope were the factors considered to produce the gold potential map of the study area using the SWARA model for weight assignment. The study showed that NE–SW trending structures aid the transportation of hydrothermal and mineralizing fluids in the study area. Furthermore, gold mineralisation is observed to occur majorly on the granitoids. From the SWARA model, weight assignment results showed that the factors influencing gold mineralisation in descending order of importance are hydrothermal alteration, lithology, lineament density and slope. The produced gold mineralisation map based on the weight assignment classified the study area into five classes: background, low, moderate, high and very high with the southern, western and northwestern axis of the study area having moderate to very high potential of gold mineralisation. Qualitative validation using mining pits showed 73 % success rate while quantitative validation utilizing linear regression model showed a success rate of 74 % substantiating the reliability of the model.

Research on Defect Detection Method of Fusion Reactor Vacuum Chamber Based on Photometric Stereo Vision.

This paper addresses image enhancement and 3D reconstruction techniques for dim scenes inside the vacuum chamber of a nuclear fusion reactor. First, an improved multi-scale Retinex low-light image enhancement algorithm with adaptive weights is designed. It can recover image detail information that is not visible in low-light environments, maintaining image clarity and contrast for easy observation. Second, according to the actual needs of target plate defect detection and 3D reconstruction inside the vacuum chamber, a defect reconstruction algorithm based on photometric stereo vision is proposed. To optimize the position of the light source, a light source illumination profile simulation system is designed in this paper to provide an optimized light array for crack detection inside vacuum chambers without the need for extensive experimental testing. Finally, a robotic platform mounted with a binocular stereo-vision camera is constructed and image enhancement and defect reconstruction experiments are performed separately. The results show that the above method can broaden the gray level of low-illumination images and improve the brightness value and contrast. The maximum depth error is less than 24.0% and the maximum width error is less than 15.3%, which achieves the goal of detecting and reconstructing the defects inside the vacuum chamber.

Issues and Challenges in Small-Signal Low-Power Amplifiers: A Review

Background: Contemporary linear electronic circuit designs frequently include small-signal low-power amplifiers as a fundamental building block. These amplifiers are widely used as LNAs (Low Noise Amplifiers) in the pre-amplifier stages of both low-frequency and high-frequency featured electronic circuits. Objectives: To review the recent advances in the design of small-signal low-power amplifiers based on device configuration of BJTs, JFETs and MOSFETs for low (≤1KHz) and high frequencies (≥1MHz) at smaller input voltage (<1 Volt). Methods: The articles published between 2010 to 2024 are shortlisted from IEEE Xplore, Springer, Science Direct Elsevier, Google Scholar, and MDPI databases and the outcomes of the different techniques are compared on various parameters. Findings: It is found that four-stage CMOS amplifier at TSMC 40nm process technology emerges with highest 84.59dB gain, InP (Indium Phosphide) Distributed Amplifier Using 3-D Interdigital Capacitors carries widest bandwidth of 160 GHz, two stage darlington pair amplifier at 0.18μm under dual input and dual output topologies and four stage CMOS amplifier at 40nm technology realizes lower power consumption of 0.5mW and 0.00086 mW respectively. Small Signal Amplifier based on single stage BJT-JFET Sziklai pair operates at lowest frequency of 11.36 Hz, single stage LNA at 180nm CMOS technology using inductive degenerate topology works at very low supply voltage at +0.5V and, recently reported complementary sziklai based small signal amplifier under CC mode works at lowest -15V supply voltage. Novelty: The review proposed on ‘Small Signal Low Power Amplifier’ is first time reported in this paper. Moreover, it discusses low power small signal amplifiers at both low (≤1KHz) and high (≥MHz) frequencies considering gain enhancement technique, power dissipation reduction technique, and noise reduction technique whereas other review papers emphasize on the general discussion of different topologies only at high frequencies. Keywords: Small-Signal Amplifiers, Low Power Amplifiers, BJTs, JFETs, MOSFETs

An Experimental Methodology for Automated Detection of Surface Turbulence Features in Tidal Stream Environments

Tidal stream environments are important areas of marine habitat for the development of marine renewable energy (MRE) sources and as foraging hotspots for megafaunal species (seabirds and marine mammals). Hydrodynamic features can promote prey availability and foraging efficiency that influences megafaunal foraging success and behaviour, with the potential for animal interactions with MRE devices. Uncrewed aerial vehicles (UAVs) offer a novel tool for the fine-scale data collection of surface turbulence features and animals, which is not possible through other techniques, to provide information on the potential environmental impacts of anthropogenic developments. However, large imagery datasets are time-consuming to manually review and analyse. This study demonstrates an experimental methodology for the automated detection of turbulence features within UAV imagery. A deep learning architecture, specifically a Faster R-CNN model, was used to autonomously detect kolk-boils within UAV imagery of a tidal stream environment. The model was trained on pre-existing, labelled images of kolk-boils that were pre-treated using a suite of image enhancement techniques based on the environmental conditions present within each image. A 75-epoch model variant provided the highest average recall and precision values; however, it appeared to be limited by sub-optimal detections of false positive values. Although further development is required, including the creation of standardised image data pools, increased model benchmarking and the advancement of tailored pre-processing techniques, this work demonstrates the viability of utilising deep learning to automate the detection of surface turbulence features within a tidal stream environment.

LesionMix data enhancement and entropy minimization for semi-supervised lesion segmentation of lung cancer

Determining the location and contour of the lesion is a crucial prerequisite for medical diagnosis, subsequent personalized treatment plan and prognostic prediction of lung cancer. Semi-supervised learning and data augmentation methods facilitate deep learning to be used in many fields of medical imaging. In this paper, we introduce a novel data enhancement technique called LesionMix. This method involves extracting and reusing lesions from a limited amount of labeled CT data, thereby enhancing the efficiency of utilizing those labeled data. Meanwhile, we propose a two-stage semi-supervised training strategy called Entropy Minimization LesionMix (EMLM). In the first stage, features containing lesion contour information are rapidly learned through LesionMix data augmentation. Entropy minimization strategy optimizes the model parameters to alleviate overfitting as much as possible in the second stage and improves prediction confidence. Our proposed method is validated on the public dataset LIDC-IDRI and the in-house dataset GDPHLUAD. Extensive experiments demonstrate that our method achieves promising performance and outperforms seven state-of-the-art semi-supervised models; Moreover, ablation experiments validate the effectiveness of various aspects of our approach.

A 28/56 Gb/s NRZ/PAM-4 Dual-Mode Transmitter with Eye-Opening Enhancement in 28 nm CMOS

This paper presents a non-return-to-zero (NRZ)/4-level pulse amplitude modulation (PAM-4) dual-mode wireline transmitter with an eye-opening enhancement technique to improve horizontal eye-opening. With the eye-enhancement pulse generator and the auxiliary pull-up device in the tail-less current-mode driver, the worst-case horizontal eye-opening increased by 30% in the PAM-4 eye diagram. The power efficiency of the NRZ mode was also improved by completely turning off the LSB path in the differential data path, resulting in only a 31% power efficiency degradation, which is far lower than that of the prior dual-mode transmitters. Fabricated in 28 nm CMOS, the transmitter achieves power efficiency of 1.4 pJ/bit at 56 Gb/s in PAM-4 mode and 1.84 pJ/bit at 28 Gb/s in NRZ mode, respectively.

RDAG U-Net: An Advanced AI Model for Efficient and Accurate CT Scan Analysis of SARS-CoV-2 Pneumonia Lesions.

Background/Objective: This study aims to utilize advanced artificial intelligence (AI) image recog-nition technologies to establish a robust system for identifying features in lung computed tomog-raphy (CT) scans, thereby detecting respiratory infections such as SARS-CoV-2 pneumonia. Spe-cifically, the research focuses on developing a new model called Residual-Dense-Attention Gates U-Net (RDAG U-Net) to improve accuracy and efficiency in identification. Methods: This study employed Attention U-Net, Attention Res U-Net, and the newly developed RDAG U-Net model. RDAG U-Net extends the U-Net architecture by incorporating ResBlock and DenseBlock modules in the encoder to retain training parameters and reduce computation time. The training dataset in-cludes 3,520 CT scans from an open database, augmented to 10,560 samples through data en-hancement techniques. The research also focused on optimizing convolutional architectures, image preprocessing, interpolation methods, data management, and extensive fine-tuning of training parameters and neural network modules. Result: The RDAG U-Net model achieved an outstanding accuracy of 93.29% in identifying pulmonary lesions, with a 45% reduction in computation time compared to other models. The study demonstrated that RDAG U-Net performed stably during training and exhibited good generalization capability by evaluating loss values, model-predicted lesion annotations, and validation-epoch curves. Furthermore, using ITK-Snap to convert 2D pre-dictions into 3D lung and lesion segmentation models, the results delineated lesion contours, en-hancing interpretability. Conclusion: The RDAG U-Net model showed significant improvements in accuracy and efficiency in the analysis of CT images for SARS-CoV-2 pneumonia, achieving a 93.29% recognition accuracy and reducing computation time by 45% compared to other models. These results indicate the potential of the RDAG U-Net model in clinical applications, as it can accelerate the detection of pulmonary lesions and effectively enhance diagnostic accuracy. Additionally, the 2D and 3D visualization results allow physicians to understand lesions' morphology and distribution better, strengthening decision support capabilities and providing valuable medical diagnosis and treatment planning tools.

Zero-CSC: Low-light image enhancement with zero-reference color self-calibration

Zero-Reference Low-Light Image Enhancement (LLIE) techniques mainly focus on grey-scale inhomogeneities, and few methods consider how to explicitly recover a dark scene to achieve enhancements in color and overall illumination. In this paper, we introduce a novel Zero-Reference Color Self-Calibration framework for enhancing low-light images, termed as Zero-CSC. It effectively emphasizes channel-wise representations that contain fine-grained color information, achieving a natural result in a progressive manner. Furthermore, we propose a Light Up (LU) module with large-kernel convolutional blocks to improve overall illumination, which is implemented with a simple U-Net and further simplified with a light-weight structure. Experiments on representative datasets show that our model consistently achieves state-of-the-art performance in image signal-to-noise ratio, structural similarity, and color accuracy, setting new records on the challenging SICE dataset with improvements of 23.7% in image signal-to-noise ratio and 5.3% in structural similarity compared to the most advanced methods.