Radiographic Research Articles

Variable structures in the stellar wind of the HMXB Vela X-1

Strong stellar winds are an important feature in wind-accreting high-mass X-ray binary (HMXB) systems. Exploring their structure provides valuable insights into stellar evolution and their influence on surrounding environments. However, the long-term evolution and temporal variability of these wind structures are not fully understood. This work probes the archetypal wind-accreting HMXB Vela X-1 using the Monitor of All-sky X-ray Image (MAXI) instrument to study the orbit-to-orbit absorption variability in the $2–10$ keV energy band across more than 14 years of observations. Additionally, the relationship between hardness ratio trends in different binary orbits and the spin state of the neutron star is investigated. We calculated X-ray hardness ratios to track absorption variability, comparing flux changes across various energy bands, as the effect of absorption on the flux is energy-dependent. We assessed variability by comparing the hardness ratio trends in our sample of binary orbits to the long-term averaged hardness ratio evolution derived from all available MAXI data. Consistent with prior research, the long-term averaged hardness ratio evolution shows a stable pattern. However, the examination of individual binary orbits reveals a different hardness ratio evolution between consecutive orbits with no evident periodicity within the observed time span. We find that fewer than half of the inspected binary orbits align with the long-term averaged hardness evolution. Moreover, neutron star spin-up episodes exhibit more harder-than-average hardness trends compared to spin-down episodes, although their distributions overlap considerably. The long-term averaged hardness ratio dispersion and evolution are consistent with absorption column densities reported in literature from short observations, indicating that a heterogeneous wind structure -- from accretion wakes to individual wind clumps -- likely drives these variations. The variability observed from orbit to orbit suggests that pointed X-ray observations provide limited insights into the overall behaviour of the wind structure. Furthermore, the link between the spin state of the neutron star and the variability in orbit-to-orbit hardness trends highlights the impact of accretion processes on absorption. This connection suggests varying accretion states influenced by fluctuations in stellar wind density.

Statistical-based modeling strategy for entrance skin dose estimation in patient undergoing body interventional radiology

Abstract Interventional radiology (IR) provides significant advancements in diagnostic and therapeutic procedures, yet concerns persist regarding radiological risks such as erythema, burns, and epilation. Direct dose measurements observed difficulties regarding the perturbation of the detector probe in X-ray images during fluoroscopy-guided procedures, high-cost expenses, and non-compliant patients. This study aims to develop a statistical-based model for estimating entrance skin dose (ESD) in body IR procedures using patient radiation-dose recording data. Models are categorized into vascular and non-vascular procedures. This study demonstrates that the simplified models are sufficient in estimating patient ESDs for both IR groups, with a 95% confidence interval. This user-friendly method enables radiologists to calculate doses without complex parameters such as the backscatter factor and mass-energy absorption coefficient, as required in conventional calculation methods. It not only does this support to radiologists in effectively refining treatment protocols, but also enables patients to monitor their received doses immediately after treatment ends.

TIA-UNet: transformer-enhanced deep learning for adolescent idiopathic scoliosis spinal x-ray image segmentation

Abstract Adolescent Idiopathic Scoliosis (AIS) is a common spinal deformity where precise diagnosis is crucial for developing effective treatment strategies. Traditional manual x-ray image analysis is time-consuming and highly dependent on the operator’s expertise, thus constraining diagnostic efficiency and accuracy. This study aimed to develop an automated thoracolumbar spine segmentation method utilizing deep learning to enhance the efficiency and accuracy of AIS diagnosis. We introduced TIA-UNet, an innovative network architecture that combines Convolutional Neural Networks (CNN) with Transformer models. By integrating the IR Block and DA Block, TIA-UNet was optimized for feature extraction and multi-scale information fusion. The model underwent training and validation using our established Adolescent Scoliosis Medical Dataset (ASMD). TIA-UNet attained a Dice similarity coefficient of 90. 02%, a Mean Intersection over Union (MIoU) of 81. 96%, and a Hausdorff Distance (HD) of 4. 09, significantly surpassing current state-of-the-art methods such as UNet and TransUNet. Moreover, TIA-UNet exhibited superior computational efficiency regarding parameter count, inference time, and floating-point operations (FLOPs). As an automated medical image segmentation algorithm, TIA-UNet enhanced segmentation accuracy while maintaining high computational efficiency, demonstrating significant potential for clinical diagnostic applications. This study provides compelling evidence supporting the utilization of deep learning techniques in medical image analysis.

Revolutionizing X-ray Imaging: A Leap toward Ultra-Low-Dose Detection with a Cascade-Engineered Approach

Revolutionizing X-ray Imaging: A Leap toward Ultra-Low-Dose Detection with a Cascade-Engineered Approach

KOC_Net: Impact of the Synthetic Minority Over-Sampling Technique with Deep Learning Models for Classification of Knee Osteoarthritis Using Kellgren–Lawrence X-Ray Grade

One of the most common diseases afflicting humans is knee osteoarthritis (KOA). KOA occurs when the knee joint cartilage breaks down, and knee bones start rubbing together. The diagnosis of KOA is a lengthy process, and missed diagnosis can have serious consequences. Therefore, the diagnosis of KOA at an initial stage is crucial which prevents the patients from Severe complications. KOA identification using deep learning (DL) algorithms has gained popularity during the past few years. By applying knee X-ray images and the Kellgren–Lawrence (KL) grading system, the objective of this study was to develop a DL model for detecting KOA. This study proposes a novel model based on CNN called knee osteoarthritis classification network (KOC_Net). The KOC_Net model contains 05 convolutional blocks, and each convolutional block has three components such as Convlotuioanl2D, ReLU, and MaxPooling 2D. The KOC_Net model is evaluated on two publicly available benchmark datasets which consist of X-ray images of KOA based on the KL grading system. Additionally, we applied contrast-limited adaptive histogram equalization (CLAHE) methods to enhance the contrast of the images and utilized SMOTE Tomek to deal with the problem of minority classes. For the diagnosis of KOA, the classification performance of the proposed KOC_Net model is compared with baseline deep networks, namely Dense Net-169, Vgg-19, Xception, and Inception-V3. The proposed KOC_Net was able to classify KOA into 5 distinct groups (including Moderate, Minimal, Severe, Doubtful, and Healthy), with an AUC of 96.71%, accuracy of 96.51%, recall of 91.95%, precision of 90.25%, and F1-Score of 96.70%. Dense Net-169, Vgg-19, Xception, and Inception-V3 have relative accuracy rates of 84.97%, 81.08%, 87.06%, and 83.62%. As demonstrated by the results, the KOC_Net model provides great assistance to orthopedics in making diagnoses of KOA.

Development of a Hybrid Medical Softbot for Enhanced Decision Making using AI-tools

Health is wealth. The maintenance of health is of paramount importance. Due to increasing environmental decay, human health is threatened and therefore requires maintenance. Healthcare providers are few in number and therefore may not be able to cater for everyone. They tend to get fatigued because of the volume of work required on daily basis. This terribly affects their decision making and may lead to death as a result of wrong diagnosis or recommendations. This is the motivation behind this work; design and implementation of a hybrid medical softbot for enhanced decision making. This work was designed with the aid of machine learning algorithms for image analysis and classification and a rule based system that accepts input in the form of symptoms from user to make expert diagnosis and recommendation. Object oriented analysis and design methodology was employed in the analysis and design phase. The result is a hybrid softbot capable of analyzing and classifying X-ray images and giving expert diagnosis for patients.

Automatic Defects Recognition of Lap Joint of Unequal Thickness Based on X-Ray Image Processing

It is difficult to automatically recognize defects using digital image processing methods in X-ray radiographs of lap joints made from plates of unequal thickness. The continuous change in the wall thickness of the lap joint workpiece causes very different gray levels in an X-ray background image. Furthermore, due to the shape and fixturing of the workpiece, the distribution of the weld seam in the radiograph is not vertical which results in an angle between the weld seam and the vertical direction. This makes automatic defect detection and localization difficult. In this paper, a method of X-ray image correction based on invariant moments is presented to solve the problem. In addition, a novel background removal method based on image processing is introduced to reduce the difficulty of defect recognition caused by variations in grayscale. At the same time, an automatic defect detection method combining image noise suppression, image segmentation, and mathematical morphology is adopted. The results show that the proposed method can effectively recognize the gas pores in an automatic welded lap joint of unequal thickness, making it suitable for automatic detection.

Enhanced Tuberculosis Detection in Chest X-Rays Using Optimal Feature Selection with Hybrid Binary Particle Swarm Optimization (HBPSO) and a Dual Classifier Framework Combining LSTM and Spiking Neural Networks

Tuberculosis (TB) remains a significant global health challenge, particularly in developing countries, where rapid and accurate diagnosis is crucial for effective treatment. Recent advancements in machine learning and image processing have shown promise in enhancing the detection of TB from chest X-ray images. This research introduces a novel approach that integrates a hybrid feature selection method with a dual classifier framework to improve the accuracy of tuberculosis detection. Feature extraction is conducted using Multi-Scale Local Binary Patterns (MSLBP), Speeded-Up Robust Features (SURF) with Bag of Words (BoW), and Cartoon Texture Features, combining them into a comprehensive feature vector. The Hybrid Binary Particle Swarm Optimization (HBPSO) is employed for optimal feature selection, reducing redundancy and improving classification efficiency. Classification is performed using a dual framework involving a Long Short-Term Memory (LSTM) network and a Spiking Neural Network (SNN), which work in tandem to provide robust predictions. Majority voting is utilized to finalize predictions, ensuring high accuracy and adaptability across varying TB presentations. Extensive evaluation on publicly available datasets shows that this hybrid approach significantly outperforms existing methods, achieving a highest accuracy of 99.73%, along with superior precision, recall, and F1 scores.

Thrombin Immobilized Hemocompatible Radiopaque Polyurethane Microspheres for Topical Blood Coagulation.

Over the past decade, there has been growing interest in developing microspheres for embolization procedures. However, the lack of noninvasive monitoring of the embolic agents and the occurrence of reflux phenomenon leading to unintentional occlusions has raised concerns regarding their compatibility/suitability for embolization therapy. Here we report the development of specialty microspheres having intrinsic radiopacity and surface functionality to tackle the existing complications that pave the way for more advanced solutions. To achieve the above goal, an iodinated monomer, termed "IBHV," capable of imparting radiopacity and functionality, was synthesized and used as a chain extender to make radiopaque polyurethane. Microspheres with a smooth surface and an average diameter of 474 ± 73 μm were fabricated from this polyurethane. The microspheres obtained were noncytotoxic, had a permissible hemolysis rate, and showed better traceability on x-ray imaging. Subsequent immobilization of thrombin onto microspheres improved their hemostatic effect. This study demonstrated that immobilization of thrombin would lead to microspheres with unique traits of radiopacity and hemostatic properties, which will undoubtedly enhance embolization efficiency.

Molecular Engineering for High-Performance X-ray Scintillators.

X-ray scintillators, materials that convert high-energy radiation into detectable light in the ultraviolet to visible spectrum, are widely used in industrial and medical applications. Organic and organic-inorganic hybrid systems have emerged as promising alternatives for X-ray detection and imaging due to their mechanical flexibility, lightweight, tunable excited states, and solution processability for large-scale fabrication. However, these systems often suffer from weak X-ray absorption and insufficient exciton utilization, which seriously affects their scintillation performance, limiting their potential for broader application and commercialization. This review highlights recent advances in molecular engineering for developing high-performance X-ray scintillators. Itfocuses on molecular design principles, such as the heavy atom effect, donor-acceptor/host-guest strategies, hydrogen/halogen bonding, molecular sensitization, and crystal packing, for enhancing scintillation performance. By leveraging these approaches, researchers have made significant strides in improving X-ray scintillation efficiency and advancing the potential of these materials for commercial applications.

NOVEL DEVICE FOR ENHANCING TUBERCULOSIS DIAGNOSIS FOR FASTER, MORE ACCURATE SCREENING RESULTS

Tuberculosis (TB) continues to be a leading global cause of illness and death, highlighting an urgent need for rapid, precise diagnostic solutions. Conventional methods, such as chest X-rays and sputum smear microscopy, often lack adequate sensitivity and specificity, resulting in treatment delays and increased transmission. This research introduces a novel device leveraging deep learning to enhance TB diagnosis, utilizing a convolutional neural network (CNN) model designed to automatically detect TB-related abnormalities in chest X-ray images. The device, powered by a large annotated dataset, incorporates transfer learning to fine-tune pre-trained models, maximizing diagnostic performance. Key evaluation metrics—accuracy, precision, recall, and F1-score—demonstrate the model’s efficacy compared to traditional diagnostics. Preliminary findings show that the AI-driven approach significantly enhances diagnostic accuracy, reducing false negatives and facilitating faster screenings. These results suggest that embedding AI technology in clinical workflows can enable earlier TB detection, optimize healthcare resources, and improve patient outcomes. Future directions include testing the device across diverse clinical environments and exploring integration with mobile health technologies to broaden access to rapid TB diagnostics.

Congruent Glass Composite Scintillator for Efficient High-Energy Ray Detection.

The scintillator is the most crucial component in the high-energy ray detection system. The available scintillators suffer from the insurmountable drawbacks including poor shaping ability for single crystal and ceramic and low efficiency for glass. Here, a glass composite scintillator is proposed from a congruent crystallization system which possesses both excellent processability and high scintillating yield. It can be fabricated into diverse shapes and sizes including the bulk and tiny fiber. Benefitting from the unique compositing combination with a high crystallization ratio, the glass composite exhibits a giant scintillating light yield of ≈26,000 photons per MeV. The practical application for X-ray imaging is demonstrated and a high spatial resolution of 12 lpmm-1 is achieved. Furthermore, the fiber derived detector is built and the remote and micro-area detection is realized. These findings not only represent a novel design concept for the development of glass composite but also suggest a great step for expanding the scope of scintillators.

Optimizing pulmonary chest x-ray classification with stacked feature ensemble and swin transformer integration

This research presents an integrated framework designed to automate the classification of pulmonary chest x-ray images. Leveraging convolutional neural networks (CNNs) with a focus on transformer architectures, the aim is to improve both the accuracy and efficiency of pulmonary chest x-ray image analysis. A central aspect of this approach involves utilizing pre-trained networks such as VGG16, ResNet50, and MobileNetV2 to create a feature ensemble. A notable innovation is the adoption of a stacked ensemble technique, which combines outputs from multiple pre-trained models to generate a comprehensive feature representation. In the feature ensemble approach, each image undergoes individual processing through the three pre-trained networks, and pooled images are extracted just before the flatten layer of each model. Consequently, three pooled images in 2D grayscale format are obtained for each original image. These pooled images serve as samples for creating 3D images resembling RGB images through stacking, intended for classifier input in subsequent analysis stages. By incorporating stacked pooling layers to facilitate feature ensemble, a broader range of features is utilized while effectively managing complexities associated with processing the augmented feature pool. Moreover, the study incorporates the Swin Transformer architecture, known for effectively capturing both local and global features. The Swin Transformer architecture is further optimized using the artificial hummingbird algorithm (AHA). By fine-tuning hyperparameters such as patch size, multi-layer perceptron (MLP) ratio, and channel numbers, the AHA optimization technique aims to maximize classification accuracy. The proposed integrated framework, featuring the AHA-optimized Swin Transformer classifier utilizing stacked features, is evaluated using three diverse chest x-ray datasets-VinDr-CXR, PediCXR, and MIMIC-CXR. The observed accuracies of 98.874%, 98.528%, and 98.958% respectively, underscore the robustness and generalizability of the developed model across various clinical scenarios and imaging conditions.

Convolutional neural network-based classification of craniosynostosis and suture lines from multi-view cranial X-rays

Early and precise diagnosis of craniosynostosis (CSO), which involves premature fusion of cranial sutures in infants, is crucial for effective treatment. Although computed topography offers detailed imaging, its high radiation poses risks, especially to children. Therefore, we propose a deep-learning model for CSO and suture-line classification using 2D cranial X-rays that minimises radiation-exposure risks and offers reliable diagnoses. We used data comprising 1,047 normal and 277 CSO cases from 2006 to 2023. Our approach integrates X-ray-marker removal, head-pose standardisation, skull-cropping, and fine-tuning modules for CSO and suture-line classification using convolution neural networks (CNNs). It enhances the diagnostic accuracy and efficiency of identifying CSO from X-ray images, offering a promising alternative to traditional methods. Four CNN backbones exhibited robust performance, with F1-scores exceeding 0.96 and sensitivity and specificity exceeding 0.9, proving the potential for clinical applications. Additionally, preprocessing strategies further enhanced the accuracy, demonstrating the highest F1-scores, precision, and specificity. A qualitative analysis using gradient-weighted class activation mapping illustrated the focal points of the models. Furthermore, the suture-line classification model distinguishes five suture lines with an accuracy of > 0.9. Thus, the proposed approach can significantly reduce the time and labour required for CSO diagnosis, streamlining its management in clinical settings.

Humidity-responsive actuators of synthesized graphene oxide/gelatin composite hydrogels: Effect of oxidation degree of graphene oxide

In this study, graphene oxide (GO) was prepared for humidity-responsive actuator application. GO has outstanding properties such as single-atom thickness, abundant oxygen, water solubility, and good moisture absorption. GO was prepared at various graphite:potassium permanganate (oxidizer) ratios (1:1, 1:2, 1:3, and 1:4; the corresponding structures are denoted as GO1, GO2, GO3, and GO4, respectively). The GO particles synthesized according to the effect of the oxidizer ratio were characterized to elucidate the internal morphology and humidity response. The defects and disorders and morphological properties of the GO particles were characterized by Raman spectroscopy and transmission electron microscopy (TEM), respectively. To study the humidity-responsive properties, the prepared GO was blended with gelatin (GEL). The bending angle of the GO/GEL hydrogel was studied at relative humidities of 80–85 % at 37 ºC. The internal structure morphology of the blend gel was analyzed by synchrotron radiation X-ray tomographic microscopy. GO2/GEL was selected for the development of a humidity-responsive actuator because of its optimal intensity ratio (ID/IG) in the Raman spectrum. X-ray and TEM images showed the good dispersion of GO2 particles in the hydrogel matrix. GO2/GEL exhibited the largest bending angle (θ = 930.11 ± 49.28º) and fast humidity response (angular rate of change ∼ 9.380 ± 0.513 ºs−1). Thus, GO2 particles are suitable for use as a humidity-responsive material for humidity actuator applications.

Blast injury with foreign body in maxillary sinus: A case report

Abstract BACKGROUND. Foreign bodies of paranasal sinuses are very rare in ENT clinical practice. CASE REPORT. We will discuss the case of a 38-year-old gentleman who showed up at our Emergency Room with loss of vision in his left eye following a blast injury. The initial physical examination identified a ruptured globe in the left eye, which caused left-eye blindness. An immediate plain X-ray revealed a metallic object lodged in the left maxillary sinus, reaching up to the left sphenoid sinus. The external approach was used to manage the patient surgically, with no intra- or postoperative complications. CONCLUSION. Inadequate managing of foreign bodies in the paranasal sinuses might result in significant morbidity. They must be removed surgically, either endoscopically or via an external method.

Biportal Endoscopic TLIF With an Expandable Cage: Technical Note and Preliminary Results in Terms of Segmental Lordosis Achievement and Disc Height Elevation.

Biportal endoscopic transforaminal lumbar interbody fusion (BE-TLIF) is a minimally invasive TLIF (MIS-TLIF) technique, commonly performed with various cage types. Expandable cages are particularly effective in achieving segmental lordosis (SL) and disc height (DH) elevation in minimally invasive TLIF. However, the published literature lacks details regarding how these outcomes can be accomplished using BE-TLIF with an expandable cage. Nine cases (10 levels) of BE-TLIF with an expandable cage were reviewed. Procedures including unilateral laminotomy and bilateral decompression, cage expansion trials, and bilateral facetectomies were carried out under biportal endoscopy to achieve SL and DH elevation. Postoperative standing x-ray images at 3 months and reconstructed computed tomography images were analyzed. The sublaminar decompression angle-measured as the angle between the spinous process and the sublaminar decompression line on axial computed tomography-was used to evaluate contralateral sublaminar decompression. All procedures were completed without changes to the surgical methods. Eight patients underwent single-level fusion, with 4 of them receiving additional decompression at adjacent levels. One patient underwent a 2-level fusion. Four cases utilized 12° lordotic cages, while the rest employed 20° hyperlordotic cages. The total time for each fusion was 152.5 ± 38.5 minutes. Segmental lordosis increased by 5.1°, with anterior and posterior DH elevations of 4.8 ± 1.7 mm and 3.1 ± 1.8 mm, respectively. No endplate injuries or early cage subsidence occurred. The mean sublaminar decompression angle was 31.8° ± 7.0°. BE-TLIF with an expandable cage may offer benefits in SL correction and DH elevation. These advantages are attributed to the use of more lordotic expandable cages, combined with contralateral facetectomies and careful endplate preparation-key features of the BE-TLIF technique. SL correction and DH elevation can be achieved through BE-TLIF, which helps to reduce the recurrence of symptoms and improves the lumbar lordotic curve.

Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique.

Knee osteoarthritis (KOA) represents a well-documented degenerative arthropathy prevalent among the elderly population. KOA is a persistent condition, also referred to as progressive joint Disease, stemming from the continual deterioration of cartilage. Predominantly afflicting individuals aged 45 and above, this ailment is commonly labeled as a "wear and tear" joint disorder, targeting joints such as the knee, hand, hips, and spine. Osteoarthritis symptoms typically increase gradually, contributing to the deterioration of articular cartilage. Prominent indicators encompass pain, stiffness, tenderness, swelling, and the development of bone spurs. Diagnosis typically involves the utilization of Radiographic X-ray images, Magnetic Resonance Imaging (MRI), and Computed Tomography (CT) Scan by medical professionals and experts. However, this conventional approach is time-consuming, and also sometimes tedious for medical professionals. In order to address the limitation of time and expedite the diagnostic process, deep learning algorithms have been implemented in the medical field. In the present investigation, four pre-trained models, specifically CNN, AlexNet, ResNet34 and ResNet-50, were utilized to predict the severity of KOA. Further, a Deep stack ensemble technique was employed to achieve optimal performance resulting to the accuracy of 99.71%.

WCAY object detection of fractures for X-ray images of multiple sites

The WCAY (weighted channel attention YOLO) model, which is meticulously crafted to identify fracture features across diverse X-ray image sites, is presented herein. This model integrates novel core operators and an innovative attention mechanism to enhance its efficacy. Initially, leveraging the benefits of dynamic snake convolution (DSConv), which is adept at capturing elongated tubular structural features, we introduce the DSC-C2f module to augment the model’s fracture detection performance by replacing a portion of C2f. Subsequently, we integrate the newly proposed weighted channel attention (WCA) mechanism into the architecture to bolster feature fusion and improve fracture detection across various sites. Comparative experiments were conducted, to evaluate the performances of several attention mechanisms. These enhancement strategies were validated through experimentation on public X-ray image datasets (FracAtlas and GRAZPEDWRI-DX). Multiple experimental comparisons substantiated the model’s efficacy, demonstrating its superior accuracy and real-time detection capabilities. According to the experimental findings, on the FracAtlas dataset, our WCAY model exhibits a notable 8.8% improvement in mean average precision (mAP) over the original model. On the GRAZPEDWRI-DX dataset, the mAP reaches 64.4%, with a detection accuracy of 93.9% for the “fracture” category alone. The proposed model represents a substantial improvement over the original algorithm compared to other state-of-the-art object detection models. The code is publicly available at https://github.com/cccp421/Fracture-Detection-WCAY .

Improving deep learning U-Net++ by discrete wavelet and attention gate mechanisms for effective pathological lung segmentation in chest X-ray imaging.

Since its introduction in 2015, the U-Net architecture used in Deep Learning has played a crucial role in medical imaging. Recognized for its ability to accurately discriminate small structures, the U-Net has received more than 2600 citations in academic literature, which motivated continuous enhancements to its architecture. In hospitals, chest radiography is the primary diagnostic method for pulmonary disorders, however, accurate lung segmentation in chest X-ray images remains a challenging task, primarily due to the significant variations in lung shapes and the presence of intense opacities caused by various diseases. This article introduces a new approach for the segmentation of lung X-ray images. Traditional max-pooling operations, commonly employed in conventional U-Net++ models, were replaced with the discrete wavelet transform (DWT), offering a more accurate down-sampling technique that potentially captures detailed features of lung structures. Additionally, we used attention gate (AG) mechanisms that enable the model to focus on specific regions in the input image, which improves the accuracy of the segmentation process. When compared with current techniques like Atrous Convolutions, Improved FCN, Improved SegNet, U-Net, and U-Net++, our method (U-Net++-DWT) showed remarkable efficacy, particularly on the Japanese Society of Radiological Technology dataset, achieving an accuracy of 99.1%, specificity of 98.9%, sensitivity of 97.8%, Dice Coefficient of 97.2%, and Jaccard Index of 96.3%. Its performance on the Montgomery County dataset further demonstrated its consistent effectiveness. Moreover, when applied to additional datasets of Chest X-ray Masks and Labels and COVID-19, our method maintained high performance levels, achieving up to 99.3% accuracy, thereby underscoring its adaptability and potential for broad applications in medical imaging diagnostics.