Search Results (284)

Pneumonia remains a serious global health issue, particularly affecting vulnerable groups such as children and the elderly, where timely and accurate diagnosis is critical for effective treatment. Recent advances in deep learning have significantly enhanced pneumonia detection using chest X-rays, yet many current methods still face challenges with interpretability, efficiency, and clinical applicability. In this work, we proposed a YOLOv11-based deep learning framework designed for real-time pneumonia detection, strengthened by the integration of Grad-CAM for visual interpretability. To further enhance robustness, the framework incorporated preprocessing techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE) for contrast improvement, region-of-interest extraction, and lung segmentation, ensuring both precise localization and improved focus on clinically relevant features. Evaluation on two publicly available datasets confirmed the effectiveness of the approach. On the COVID-19 Radiography Dataset, the system reached a macro-average accuracy of 98.50%, precision of 98.60%, recall of 97.40%, and F1-score of 97.99%. On the Chest X-ray COVID-19 & Pneumonia dataset, it achieved 98.06% accuracy, with corresponding high precision and recall, yielding an F1-score of 98.06%. The Grad-CAM visualizations consistently highlighted pathologically relevant lung regions, providing radiologists with interpretable and trustworthy predictions. Comparative analysis with other recent approaches demonstrated the superiority of the proposed method in both diagnostic accuracy and transparency. With its combination of real-time processing, strong predictive capability, and explainable outputs, the framework represents a reliable and clinically applicable tool for supporting pneumonia and COVID-19 diagnosis in diverse healthcare settings. Full article

Background/Objectives: Full-spine radiography is frequently performed from childhood to adulthood, raising concerns about radiation-induced breast cancer risk. To assess such probabilistic risks as cancer, accurate estimation of equivalent and effective organ doses is essential. The purpose of this study is to investigate X-ray imaging conditions for radiation reduction based on breast organ dose and to evaluate the accuracy of simulation software for dose calculation. Methods: Breast organ doses from full-spine radiography were calculated using the Monte Carlo-based dose calculation software PCXMC. Breast organ doses were estimated under various technical conditions of full-spine radiography (tube voltage, distance, grid presence, and beam projection). Dose reduction methods were explored, and variations in dose and error due to phantom characteristics and photon history number were evaluated. Results: Among the X-ray conditions, the greatest radiation reduction effect was achieved by changing the imaging direction. Changing from the anteroposterior to posteroanterior direction reduced doses by approximately 76.7% to 89.1% (127.8–326.7 μGy) in children and 80.4% to 91.1% (411.3–911.1 μGy) in adults. In addition, the study highlighted how phantom characteristics and the number of photon histories influence estimated doses and calculation error, with approximately 2 × 10⁶ photon histories recommended to achieve a standard error ≤ 2%. Conclusions: Modifying radiographic conditions is effective for reducing breast radiation exposure in patients with scoliosis. Furthermore, to ensure the accuracy of dose calculation software, the number of photon histories must be adjusted under certain conditions and used while verifying the standard error. This study demonstrates how technical modifications, projection selection, and phantom characteristics influence breast radiation exposure, thereby supporting the need for patient-tailored imaging strategies that minimize radiation risk while maintaining diagnostic validity. The findings may be useful in informing radiographic protocols and the development of safer imaging guidelines for both pediatric and adult patients undergoing spinal examinations. Full article

Lung ultrasound (LUS) has emerged as a valuable diagnostic modality for the evaluation of respiratory disorders in neonates, infants and children. LUS has high diagnostic accuracy for identification of lung lesions in neonates, infants and children, where most lung lesions abut the pleura. Furthermore, LUS has the advantage of rapid execution and ease of use, and does not require ionizing radiation. Its sensitivity, cost-effectiveness, and clinical efficiency make it an important tool for supporting clinical decision-making and improving patient management. Moreover, LUS may represent a reliable alternative to chest radiography for the assessment of pediatric lung conditions and, in selected cases, could potentially replace routine chest X-rays (CXRs). Because LUS is a user-friendly technique that enables real-time imaging without radiation, it has increasingly been used in clinical practice in recent years. Here, we discuss the diagnostic role of LUS for the accurate identification of pulmonary lesions in pediatric patients. In addition, we present LUS sonographic findings associated with common pediatric lung diseases, including signs and artifacts that can be used during diagnosis and evaluation of pediatric patients. Full article

This work aims to leverage generative modeling-based anomaly detection to enhance interpretability in AI failure detection systems and to aid data curation for large repositories. For failure detection interpretability, this retrospective study utilized 3339 CT scans (525 patients), divided patient-wise into training, baseline test, and anomaly (having failure-causing attributes—e.g., needles, ascites) test datasets. For data curation, 112,120 ChestX-ray14 radiographs were used for training and 2036 radiographs from the Medical Imaging and Data Resource Center for testing, categorized as baseline or anomalous based on attribute alignment with ChestX-ray14. StyleGAN2 networks modeled the training distributions. Test images were reconstructed with backpropagation and scored using mean squared error (MSE) and Wasserstein distance (WD). Scores should be high for anomalous images, as StyleGAN2 cannot model unseen attributes. Area under the receiver operating characteristic curve (AUROC) evaluated anomaly detection, i.e., baseline and anomaly dataset differentiation. The proportion of highest-scoring patches containing needles or ascites assessed anomaly localization. Permutation tests determined statistical significance. StyleGAN2 did not reconstruct anomalous attributes (e.g., needles, ascites), enabling the unsupervised detection of these attributes: mean (±standard deviation) AUROCs were 0.86 (±0.13) for failure detection and 0.82 (±0.11) for data curation. 81% (±13%) of the needles and ascites were localized. WD outperformed MSE on CT (p < 0.001), while MSE outperformed WD on radiography (p < 0.001). Generative models detected anomalous image attributes, demonstrating promise for model failure detection interpretability and large-scale data curation. Full article

Background: Osteoporosis screening in dental practice is challenging because dual-energy X-ray absorptiometry is not easily applicable to jaw bones. Objective: This study aimed to evaluate the diagnostic performance of a logistic regression model combining intraoral bone mineral density (BMD) using DentalSCOPE with the panoramic mandibular cortical index (MCI) for osteoporosis screening. Methods: Among 104 patients included in the study, 83 who underwent both intraoral and panoramic radiography were retrospectively selected as a training cohort to develop a logistic regression model for osteoporosis prediction. The mean age was 52.4 years, and 65.1% were female. Intraoral radiographs were analyzed using DentalSCOPE^® (Media Co., Tokyo, Japan) to determine BMD in the alveolar region (al-BMD). On panoramic radiographs, experienced radiologists determined the MCI. An additional 21 patients (mean age 63.1 years; 81.0% female) were prospectively enrolled as an external validation cohort. The trained model was applied to both the training (internal) and external cohorts to evaluate its diagnostic performance, which was compared with that of intraoral or panoramic radiography, using receiver operating characteristic (ROC) analysis. Results: In the training cohort, areas under the ROC curve (AUCs) of al-BMD and MCI were 0.74 and 0.82, respectively, while the combined model showed improved performance with an AUC of 0.88. In the external validation cohort, the AUCs were 0.92 and 0.97 for al-BMD and MCI, respectively. The performance of the combined model improved with an area under the AUC of 1.00. Conclusions: DentalSCOPE-based al-BMD, particularly when combined with panoramic MCI, offers a reliable and practical approach for opportunistic osteoporosis screening in dental care. Full article

Purpose: This study was designed to develop a nanoparticle-based methotrexate (MTX) and sorafenib (SRF)-loaded transferosome (MTX-SRF-TFS) for effective management of arthritis through the transdermal route. Methods: For the preparation of MTX-SRF-TFS, the thin-film hydration technique was selected and optimized using Box–Behnken Design. The particle size of the nanoparticles was determined using a Malvern Zeta sizer and electron microscopy. An in vivo skin retention and penetration study was also conducted to evaluate the designed delivery system. Furthermore, the therapeutic response of MTX-SRF-TFS was determined using the CFA-induced mouse model. Results: The optimized MTX-SRF-TFS formulation (F4), having an average particle size (PS) of 162.20 ± 2.89 nm and percent entrapment efficiency (%EE) of MTX and SRF of 92.16 ± 4.95 and 81.54 ± 3.23, respectively, was selected for further assessment. Due to the deformable nature of MTX-SRF-TFS, MTX and SRF penetrate more deeply into the cutaneous layers, exhibiting an enhanced transdermal effect, as shown by the results of ex vivo skin permeation and retention studies. Furthermore, in vivo anti-arthritic studies have shown the superior pharmacodynamic response of MTX and SRF when incorporated into transferosomes, as it caused a marked reduction in arthritic score and paw diameter in CFA-induced arthritis in BALB/c mice. Histopathology analysis and X-ray radiography also confirmed the findings that MTX-SRF-TFS has improved anti-arthritic response in contrast to plain MTX-SRF gel. Conclusions: The MTX-SRF-TFS is highly effective in managing CFA-induced arthritis, and the designed delivery system should be further evaluated on pharmacokinetic grounds to progress towards clinical studies. Full article

Religious panel paintings (icons) play a pivotal role in the rituals of the Eastern Orthodox Christian Church. However, their continuous use often results in physical degradation, prompting remedial interventions. Quite commonly, alterations were treated by simply applying new paint layers directly over the decayed original, while in some cases, old icons were overpainted merely as a means to renovate and modernize them. Therefore, numerous overpainted icons are currently housed in churches, museums, and private collections across Greece. This study focuses on the investigation of a post-Byzantine icon of Christ Pantokrator, which displays extensive overpainting while retaining a few visible fragments of the original composition. The objective was to assess the extent and condition of preservation of the original artwork, to identify materials and techniques used both in the initial painting and in subsequent restoration phases, and to distinguish between those phases. To achieve these aims, a fully non-invasive diagnostic methodology was implemented, including visible light photography, ultraviolet radiation imaging (UVR/UVL), hyperspectral imaging (MuSIS HS), infrared reflectography (IRRef), X-ray radiography, and macroscopic X-ray fluorescence scanning (MA-XRF). The findings confirm that the original painting remains substantially preserved and is of high artistic quality. Moreover, analysis revealed at least two distinct phases of overpainting, likely dating from the 20th century, while the results suggest that the original artwork probably dates to the first half of the 18th century. The study highlights the need to use complementary techniques in order to non-invasively assess complex artifacts like overpainted icons and offers valuable insights into historical restoration practices providing foundation for future conservation planning. Full article

This study introduces a dual-filter X-ray image enhancement technique designed to elevate the quality of radiographic images of the knee, breast, and wrist, employing the Cream and Bosso algorithms. Our quantitative analysis reveals significant improvements in bone, edge definition, and contrast (p < 0.001). The processing parameters are derived from the relationship between entropy metrics and the filtering parameter d. The results demonstrate contrast enhancements for knee radiographs and for wrist radiographs, while maintaining acceptable noise levels. Comparisons are made with CLAHE techniques, unsharp masking, and deep-learning-based models. This method is a reliable and computationally efficient approach to enhancing clinical diagnosis in resource-limited settings, thereby improving robustness and interpretability. Full article

Objectives: Primary bone tumors such as osteosarcoma and chondrosarcoma are rare but aggressive malignancies that require early and accurate diagnosis. Although X-ray radiography is a widely accessible imaging modality, detecting small or multi lesions remains challenging. Existing deep learning models are often trained on small, single-center datasets and lack generalizability, limiting their clinical effectiveness. Methods: We propose the YOLOv11-MTB, a novel enhancement to YOLOv11 integrating multi-scale Transformer-based attention, boundary-aware feature fusion, and receptive field augmentation to improve detection of small and multi-focal lesions. The model is trained and evaluated on two multi-center datasets, including the BTXRD dataset containing annotated radiographs with lesion types and bounding boxes. Results: YOLOv11-MTB achieves state-of-the-art performance on bone tumor detection tasks. It attains a mean average precision (mAP) of 79.6% on the BTXRD dataset, outperforming existing methods. In clinically relevant categories, the model achieves small-lesion mAP of 55.8% and multi-lesion mAP of 63.2%. Conclusions: The proposed YOLOv11-MTB framework demonstrates promising generalization and accuracy for primary bone tumor detection in radiographic images. Its performance in detecting small and multiple lesions suggests potential for clinical application. Full article

Background/Objectives: Growth prediction may be used by the clinical orthodontist in growing individuals for diagnostic purposes and for treatment planning. This process appraises chronological age and determines the degree of skeletal maturity to calculate residual growth. In developmental deviations, overlooking such diagnostic details might culminate in erroneous conclusions, unstable outcomes, recurrence, and treatment failure. The present review aims to systematically present and explain the available means for predicting growth in humans. Traditional, long-known, popular methods are discussed, and modern digital applications are described. Materials and methods: A search on PubMed and the gray literature up to May 2025 produced 69 eligible studies on future maxillofacial growth prediction without any orthodontic intervention. Results: Substantial variability exists in the studies on growth prediction. In young orthodontic patients, the study of the lateral cephalometric radiography and the subsequent calculation of planes and angles remain questionable for diagnosis and treatment planning. Skeletal age assessment is readily accomplished with X-rays of the cervical vertebrae and the hand–wrist region. Computer software is being implemented to improve the reliability of classic methodologies. Metal implants have been used in seminal growth studies. Biochemical methods and electromyography have been suggested for clinical prediction and for research purposes. Conclusions: In young patients, it would be of importance to reach conclusions on future growth with minimal distress to the individual and, also, reduced exposure to ionizing radiation. Nevertheless, the potential for comprehensive prediction is still largely lacking. It could be accomplished in the future by combining established methods with digital technology. Full article

Background/Objectives: In digital radiography imaging, dual-layer flat-panel detectors (DFDs), in which two flat-panel detector layers are stacked with a minimal distance between the layers and appropriate alignment, are commonly used in material decompositions as dual-energy applications with a single x-ray exposure. DFDs also enable more efficient use of incident photons, resulting in x-ray images with improved noise power spectrum (NPS) and detection quantum efficiency (DQE) performances as single-energy applications. Purpose: Although the development of DFD systems for material decomposition applications is actively underway, there is a lack of research on whether single-energy applications of DFD can achieve better performance than the single-layer case. In this paper, we experimentally observe the DFD performance in terms of the modulation transfer function (MTF), NPS, and DQE with discussions. Methods: Using prototypes of DFD, we experimentally measure the MTF, NPS, and DQE of the convex combination of the images acquired from the upper and lower detector layers of DFD. To optimize DFD performance, a two-step image registration is performed, where subpixel registration based on the maximum amplitude response to the transform based on the Fourier shift theorem and an affine transformation using cubic interpolation are adopted. The DFD performance is analyzed and discussed through extensive experiments for various scintillator thicknesses, x-ray beam conditions, and incident doses. Results: Under the RQA 9 beam conditions of 2.7 μGy dose, the DFD with the upper and lower scintillator thicknesses of 0.5 mm could achieve a zero-frequency DQE of 75%, compared to 56% when using a single-layer detector. This implies that the DFD using 75 % of the incident dose of a single-layer detector can provide the same signal-to-noise ratio as a single-layer detector. Conclusions: In single-energy radiography imaging, DFD can provide better NPS and DQE performances than the case of the single-layer detector, especially at relatively high x-ray energies, which enables low-dose imaging. Full article

Radiography, favoured for its ability to provide a non-invasive insight into the contents of wrapped or coffined artefacts, has revolutionised the study of mummified human and animal remains. Despite this potential, the technology is limited by its capacity to realistically visualise the surface attributes of these often-complex artefacts. In this paper, photogrammetry—a technique widely used in archaeology and heritage applications—is applied to build upon the radiographic investigation of six ancient Egyptian votive artefacts from Manchester Museum; a study which combines the two techniques for the first time on votive material from the collection. The paper showcases the results gained through clinical radiography techniques (digital X-ray and computed tomography) on the internal contents of the artefacts, highlighting the problems encountered when viewing the outer surface. With a simple on-site photogrammetry protocol, improved visualisation was possible, providing photo-realistic renderings with important potential for both research, conservation and engagement. Full article

Objectives: This study aimed to implement a high-resolution Saudi voxel-based anthropomorphic phantom in the OpenMC Monte Carlo (MC) simulation framework. The objective was to evaluate its applicability in radiological simulations, including radiographic imaging and effective dose calculations, tailored to the Saudi population. Methods: A voxel phantom comprising 30 segmented organs/tissues and over 32 million voxels were constructed from full-body computed tomography data and integrated into OpenMC. The implementation involved detailed voxel mapping, material definition using ICRP/ICRU-116 recommendations, and lattice geometry construction. The simulations included X-ray radiography projections using mesh tallies and anterior–posterior effective dose calculations across 20 photon energies (10 keV–1 MeV). The absorbed dose was calculated using OpenMC’s heating tally and converted to an effective dose using tissue weighting factors. Results: The phantom was successfully modeled and visualized in OpenMC, demonstrating accurate anatomical representation. Radiographic projections showed optimal contrast at 70 keV. The effective dose values for 29 organs were calculated and compared with MCNPX, the ICRP-116 reference phantom, and XGBoost-based machine learning (ML) predictions. OpenMC results showed good agreement, with maximum deviations of −35.5% against ICRP-116 at 10 keV. Root mean square error (RMSE) comparisons confirmed reasonable alignment, with OpenMC displaying higher RMSEs relative to other methods due to expanded organ modeling and material definitions. Conclusions: The integration of the Saudi voxel phantom into OpenMC demonstrates its utility for high-resolution dosimetry and radiographic simulations. OpenMC’s Python (version 3.10.14) interface and open-source nature make it a promising tool for radiological research. Future work will focus on combining MC and ML approaches for enhanced predictive dosimetry. Full article

The risk of developing symptomatic knee osteoarthritis (KOA) during a lifetime, i.e., pain, aching, or stiffness in a joint associated with radiographic KOA, was estimated in 2008 to be around 40% in men and 47% in women. The clinical and scientific communities lack an efficient diagnostic method to effectively monitor, evaluate, and predict the evolution of KOA before and during the therapeutic protocol. In this review, we summarize the main methods that are used or seem promising for the diagnosis of osteoarthritis, with a specific focus on non- or low-invasive methods. As standard diagnostic tools, arthroscopy, magnetic resonance imaging (MRI), and X-ray radiography provide spatial and direct visualization of the joint. However, discrepancies between findings and patient feelings often occur, indicating a lack of correlation between current imaging methods and clinical symptoms. Alternative strategies are in development, including the analysis of biochemical markers or acoustic emission recordings. These methods have undergone deep development and propose, with non- or minimally invasive procedures, to obtain data on tissue condition. However, they present some drawbacks, such as possible interference or the lack of direct visualization of the tissue. Other original methods show strong potential in the field of KOA monitoring, such as electrical bioimpedance or near-infrared spectrometry. These methods could permit us to obtain cheap, portable, and non-invasive data on joint tissue health, while they still need strong implementation to be validated. Also, the use of Artificial Intelligence (AI) in the diagnosis seems essential to effectively develop and validate predictive models for KOA evolution, provided that a large and robust database is available. This would offer a powerful tool for researchers and clinicians to improve therapeutic strategies while permitting an anticipated adaptation of the clinical protocols, moving toward reliable and personalized medicine. Full article

Non-destructive testing (NDT) methods are critical for evaluating the structural integrity of and detecting defects in composite materials across industries such as aerospace and renewable energy. This review examines the recent trends and successful implementations of NDT approaches for composite materials, focusing on articles published between 2015 and 2025. A systematic literature review identified 120 relevant articles, highlighting techniques such as ultrasonic testing (UT), acoustic emission testing (AET), thermography (TR), radiographic testing (RT), eddy current testing (ECT), infrared thermography (IRT), X-ray computed tomography (XCT), and digital radiography testing (DRT). These methods effectively detect defects such as debonding, delamination, and voids in fiber-reinforced polymer (FRP) composites. The selection of NDT approaches depends on the material properties, defect types, and testing conditions. Although each technique has advantages and limitations, combining multiple NDT methods enhances the quality assessment of composite materials. This review provides insights into the capabilities and limitations of various NDT techniques and suggests future research directions for combining NDT methods to improve quality control in composite material manufacturing. Future trends include adopting multimodal NDT systems, integrating digital twin and Industry 4.0 technologies, utilizing embedded and wireless structural health monitoring, and applying artificial intelligence for automated defect interpretation. These advancements are promising for transforming NDT into an intelligent, predictive, and integrated quality assurance system. Full article