Search

We describe a method to compute photon–matter interaction and atomic dynamics with x-ray lasers using a hybrid code based on classical molecular dynamics and collisional-radiative calculations. The forces between the atoms are dynamically determined based on changes to their electronic occupations and the formation of a free electron cloud created from the irradiation of photons in the x-ray spectrum. The rapid transition from neutral solid matter to dense plasma phase allows the use of screened potentials, reducing the number of non-bonded interactions. In combination with parallelization through domain decomposition, the hybrid code handles large-scale molecular dynamics and ionization. This method is applicable for large enough samples (solids, liquids, proteins, viruses, atomic clusters, and crystals) that, when exposed to an x-ray laser pulse, turn into a plasma in the first few femtoseconds of the interaction. We present four examples demonstrating the applicability of the method. We investigate the non-thermal heating and scattering of bulk water and damage-induced dynamics of a protein crystal using an x-ray pump–probe scheme. In both cases, we compare to the experimental data. For single particle imaging, we simulate the ultrafast dynamics of a methane cluster exposed to a femtosecond x-ray laser. In the context of coherent diffractive imaging, we study the fragmentation as given by an x-ray pump–probe setup to understand the evolution of radiation damage in the time range of hundreds of femtoseconds. [ABSTRACT FROM AUTHOR]

Dual-energy imaging represents a versatile and evolving technology with wide-ranging applications in medicine and beyond. Recent technological developments increased the potential for improved diagnostic accuracy and expanded imaging capabilities across various fields. The purpose of this work is to design and develop an energy-integrating multilayer detector, known as a sandwich detector, aimed at single-shot dual-energy imaging tasks such as material discrimination and contrast cancellation. The sandwich detector uses two complementary metal oxide semiconductor advanced pixel sensors of 50 μm pixel size. The top and bottom sensors detect low-energy (LE) and high-energy (HE) photons, with sensors coupled with 250 and 600 μm scintillators, respectively. For better spectral separation between layers without excessively affecting the detected statistic in the bottom layer, the insertion of a 0.25-mm Cu filter between the layers was found to be the optimal choice, from among the tested 0-, 0.25-, and 0.5-mm filter options. The thickness selection for scintillator and intermediate Cu filter was carried out through a dual-energy simulation model. The experiments confirmed the model's reliability in selecting the optimal thicknesses of the intermediate Cu filter, thereby providing reassurance also on the choice of the top scintillator. [ABSTRACT FROM AUTHOR]

The ability to visualize x-ray and neutron emission from fusion plasmas in 3D is critical to understand the origin of the complex shapes of the plasmas in experiments. Unfortunately, this remains challenging in experiments that study a fusion concept known as Magnetized Liner Inertial Fusion (MagLIF) due to a small number of available diagnostic views. Here, we present a basis function-expansion approach to reconstruct MagLIF stagnation plasmas from a sparse set of x-ray emission images. A set of natural basis functions is "learned" from training volumes containing quasi-helical structures whose projections are qualitatively similar to those observed in experimental images. Tests on several known volumes demonstrate that the learned basis outperforms both a cylindrical harmonic basis and a simple voxel basis with additional regularization, according to several metrics. Two-view reconstructions with the learned basis can estimate emission volumes to within 11% and those with three views recover morphology to a high degree of accuracy. The technique is applied to experimental data, producing the first 3D reconstruction of a MagLIF stagnation column from multiple views, providing additional indications of liner instabilities imprinting onto the emitting plasma. [ABSTRACT FROM AUTHOR]

Pulsed-power-driven underwater electrical explosion of cylindrical or conical wire arrays produces supersonic water jets that emerge from a bath, propagating through the air above it. Interaction of these jets with solid targets may represent a new platform for attaining materials at high pressure (>1010 Pa) conditions in a university-scale laboratory. However, measurements of the internal structure of such jets and how they interact with targets are difficult optically due to large densities and density contrasts involved. We utilized multi-frame x-ray radiographic imaging capabilities of the ID19 beamline at the European Synchrotron Radiation Facility to explore the water jet and its interaction with a 50 μm thick copper foil placed a few mm from the surface of water. The jet was generated with a ∼130 kA-amplitude current pulse of ∼450 ns rise time applied to a conical wire array. X-ray imaging revealed a droplet-type structure of the jet with an average density of <400 kg/m3 propagating with a velocity of ∼1400 m/s. Measurements of deformation and subsequent perforation of the target by the jet suggested pressures at the jet–target interface of ∼5 × 109 Pa. The results were compared to hydrodynamic simulations for better understanding of the jet parameters and their interaction with the foil target. These results can be used in future research to optimize the platform, and extend it to larger jet velocities in the case of higher driving currents supplied to the wire array. [ABSTRACT FROM AUTHOR]

High transparency Ce3+-doped dense gadolinium aluminum borosilicate (GS x) glass scintillator was synthesized in reducing atmosphere by melt-quenching process. The transmittance of the glasses exceeds 80%, and the light attenuation length is between 5-20 cm within the range of 400–600 nm. GS x glass shows an photoluminescence (PL) in range of 350–550 nm, with the strongest emission peak around 420 nm. The PL decay time of GS x glasses is around 37 ns, with a maximum PL quantum yield of 44.05%. The integrated X-ray excited luminescence (XEL) intensity of GS S glass is 52.5% compared with BGO crystal. For X-ray imaging, GS L glass based imaging system shows a high spatial resolution of 9 lp/mm, which is comparable to CsI:Tl X-ray detectors. Under γ-ray, the highest light yield of GS S glass is 1235 ph/MeV with an energy resolution of 24.0% at 662 keV, close to that of BSO crystal. The scintillation decay time of GS x glasses is consisted of fast (∼100 ns) and slow (∼560 ns) components. In thermally stimulated luminescence (TSL), GS S glass exhibits a strong TSL peak at approximately 440 K, with low intensity shoulders at about 520 K, implying different types of defects and traps. Therefore, GS x glass has promising prospects for X-ray imaging and high-energy physics applications. [ABSTRACT FROM AUTHOR]

Radiological findings play an essential and complementary role in diagnosing Covid-19, assessing its severity, and managing its patients. Artificial intelligence technology based on medical imaging, which has made exciting developments by being applied in many areas, has become an area of interest for the rapid and accurate detection of the disease in the fight against the Covid-19 pandemic. The main difficulty is the inability to obtain a large dataset size with quality and standard images that neural networks need to perform well. Aiming at this problem, this study proposes a Siamese neural network-based deep learning framework for accurate diagnostics of Covid-19 using chest X-ray (CXR) images. The pre-trained VGG16 architecture, based on the transfer learning approach, forms the backbone of the Siamese neural network. The outputs of the backbones are joined together by a merging layer, and then the output passes through a fully connected layer. Based on this structure, category-aware Siamese-based models are produced for each class. The predictions from the models are combined using a voting mechanism to reduce the possibility of misclassification and to make better decisions. The framework was evaluated using a publicly available dataset for the 4-class classification task for Covid-19 pneumonia, lung opacity, normal, and non-Covid-19 viral pneumonia images. The findings reveal the high discrimination ability of the framework, trained using only 10 images per class in less training time, achieving an average test accuracy of 92%. Our framework, which learns a single Siamese-based pairwise model for each class, effectively captures class-specific features. Additionally, it has the potential to deal with data scarcity and long training time problems in multi-class classification tasks. [ABSTRACT FROM AUTHOR]

Orthopedic trauma results in the injury of bone joints and tendons of the body. A radiologist reviews and monitors large numbers of radiographs daily, which can lead to the diagnostic error. Therefore, there is a need to automate the detection of bone fractures in X-ray images, particularly humerus bone fractures. In this paper, we have proposed an ensemble model that can detect the fracture in an x-ray image. In this paper, we proposed an ensemble model designed for fracture detection in X-ray images. An ensemble model combines multiple diverse models to improve predictive accuracy and robustness by aggregating their individual predictions. The model leverages MobileNetV2, Vgg16, InceptionV3, and ResNet50, using histogram equalization for preprocessing and a Global Average Pooling layer for feature extraction. The entire humerus from the public Mura-v1.1 dataset is utilized for analysis, utilizing a single training-validation split. The dataset is divided into a ratio of 80:20 for experiments for the training and validation datasets. The proposed model outperformed the modified deep-learning models and achieved 92.96%, 91.62%, and 92.14% accuracy, recall, and F1 scores, respectively. The ensemble model presented effectively automates bone fracture detection in X-ray images of the humerus, demonstrating superior performance compared to modified deep-learning models. A comparison has been made between a novel ensemble model and state-of-the-art models, bench-marking their performance. These findings underscore its potential for enhancing diagnostic accuracy and efficiency in orthopedic radiology. • Novel technique using an ensemble model for humerus fracture detection in X-ray images. • Combines MobileNetV2, Vgg16, InceptionV3, and ResNet50 for enhanced predictive accuracy. • Uses histogram equalization before data augmentation and Global Average Pooling. • Achieved 92.96% accuracy, 91.62% recall, and 92.14% F1 score, outperforming other models. [ABSTRACT FROM AUTHOR]

The effect of different filler types on the properties of asphalt mortar before and after water saturation was studied by laboratory tests. Under both dry and water-saturated circumstances, four alternative fillers, limestone powder, hydrated lime, PO42.5 cement, and brake pad powder, are used, evaluated, and compared. The study methodology included characterizing the micromorphology, while X-ray diffraction imaging analysis and scanning electron microscopy were used to determine the chemical composition of the asphalt mortar following water saturation. To quantify the effects of moisture on the bonding mechanisms, surface energy concepts were employed to compute the surface free energy parameters of the asphalt mortar made with different filler materials. Dynamic shear rheometry was employed in the investigation to describe the rheological characteristics of the asphalt mortar as a function of filler under different water saturation conditions. The bonding strength of the asphalt mortars with various fillers was then quantitatively measured using pullout tests to account for the coupling effects of moisture and temperature. The findings of the laboratory tests generally showed that the asphalt mortar's effectiveness declined following moisture conditioning and saturation in water. However, hydrated lime, brake pad powder, and cement showed promise in strengthening the bonding of fillers and asphalt, with hydrated lime being superior. Likewise, the asphalt mortar's ability to tolerate moisture and resist water damage was also generally improved by hydrated lime. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusion The non‐prewhitening computational model observer with eye filter (NPWE) has been shown to reasonably predict human observer performance in general radiography and is an appropriate substitute when real clinical trials are not feasible. In this study, the NPWE model observer is used to detect specific tasks (circular designer nodules) ranging between 1 and 30 mm in diameter using chest and abdomen phantom images acquired across the diagnostic energy range (60–125 kVp) with and without an anti‐scatter grid.The aim of this study was to derive tube voltage (kVp) settings that return maximal NPWE detectability (d’) of designer nodules, for digital radiography (DR) chest and abdomen imaging.Images of a chest phantom (LucAl phantom) and a surrogate for an abdomen (18.5 cm PMMA) were acquired across the diagnostic energy range (60–125 kVp) with matched effective dose (for the respective anatomies), with and without an anti‐scatter grid, on a general x‐ray system. Images were captured using an Agfa DX‐D 40C wireless indirect caesium iodide (CsI) imaging panel. Modulation transfer function (MTF), normalized noise power spectrum (NNPS), and contrast (C) were measured in each image and the detectability index d’ was calculated for circular designer nodules with diameters ranging from 1 to 30 mm (in steps of 1 mm).The calculated d’ peaked at a nodule diameter of 3 mm irrespective of tube voltage, for both chest and abdomen images. A tube voltage of 80 kVp returned maximal d’ for chest imaging across all nodule diameters both with and without an anti‐scatter grid. A tube voltage of 70 kVp returned maximal d’ for abdomen imaging.The NPWE observer model has been used to derive tube voltages (kVp) that return maximal detectability (d’) of designer nodules for chest and abdomen radiography using a modern DR imaging system. This will provide the medical physicist with a starting point in the task of optimising tube voltage range for chest and abdomen imaging. [ABSTRACT FROM AUTHOR]

Convolutional Neural Network (CNN)-based models are prone to adversarial attacks, which present a significant hurdle to their reliability and robustness. The vulnerability of CNN-based models may be exploited by attackers to launch cyber-attacks. An attacker typically adds small, carefully crafted perturbations to original medical images. When a CNN-based model receives the perturbed medical image as input, it misclassifies the image, even though the added perturbation is often imperceptible to the human eye. The emergence of such attacks has raised security concerns regarding the implementation of deep learning-based medical image classification systems within clinical environments. To address this issue, a reliable defense mechanism is required to detect adversarial attacks on medical images. This study will focus on the robust detection of pneumonia in chest X-ray images through CNN-based models. Various adversarial attacks and defense strategies will be evaluated and analyzed in the context of CNN-based pneumonia detection. From earlier studies, it has been observed that a single defense mechanism is usually not effective against more than one type of adversarial attack. Therefore, this study will propose a defense mechanism that is effective against multiple attack types. A reliable defense framework for pneumonia detection models will ensure secure clinical deployment, facilitating radiologists and doctors in their diagnosis and treatment planning. It can also save time and money by automating routine tasks. The proposed defense mechanism includes a convolutional autoencoder to denoise perturbed Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) adversarial images, two state- of-the-art attacks carried out at five magnitudes, i.e., ε (epsilon) values. Two pre-trained models, VGG19 and VGG16, and our hybrid model of MobileNetV2 and DenseNet169, called Stack Model, have been used to compare their results. This study shows that the proposed defense mechanism outperforms state-of-the-art studies. The PGD attack using the VGG16 model shows a better attack success rate by reducing overall accuracy by up to 67%. The autoencoder improves accuracy by up to 16% against PGD attacks in both the VGG16 and VGG19 models. [ABSTRACT FROM AUTHOR]

Copper‐based organic–inorganic hybrid halides (OIHHs) have garnered significant interest in X‐ray imaging due to their flexible structural adjustability, efficient light emission, strong X‐ray absorption, etc. Herein, four copper‐based OIHH crystals composed of the same organic ligands (isopropyl triphenylphosphonium cations, IPP+) and inorganic parts (Cu2I42−) are synthesized by varying the ratios of raw materials and types of reaction solvents. Although these crystals share identical structures, they exhibit different luminescent behaviors (blue, green, white, and yellow) attributed to vacancy defects originating from CuI. Notably, the novel copper‐based OIHH (CP2) with green emission shows the best luminescence efficiency (99.54%) and excellent scintillation performance (50675 photons MeV−1). The traditional technology of scintillation screens mixing scintillator powders and polymers often results in light scattering due to powder aggregation and inhomogeneity. To address this challenge, the dispersant polyvinyl pyrrolidone is introduced to prepare uniform rod‐like microcrystals of CP2. The scintillation screen based on CP2 microcrystals achieves a high spatial resolution of 16–18 lp mm−1, surpassing the resolution of most copper‐based OIHH scintillators. Furthermore, it is imaging capabilities are validated using a commercial X‐ray flat panel detector, demonstrating imaging performance comparable to that of commercial scintillators. [ABSTRACT FROM AUTHOR]

X-ray baggage inspection ensures transport and border security, as it prevents hazardous objects from entering secure areas. Currently, deep learning is the state-of-the-art approach for automated threat object detection and classification. These networks require extensive training data; however, the number of publicly available datasets of X-ray images is limited. To overcome this, we propose an image generation pipeline that generates new data by superimposing simulated X-ray images of 3D models onto real baggage X-rays. This approach allows researchers to train deep neural networks without requiring additional imaging or manual labeling. The effectiveness and reliability of our image simulation pipeline are demonstrated, integrating advanced techniques such as distortion with diffusion models. We conducted hundreds of YOLOv5 trainings with a combination of real images from the SIXray dataset and simulated X-rays containing wrenches and handguns. Testing was performed exclusively on unaltered real images. Training exclusively with 16,000 simulated images of grayscale wrenches resulted in an A P 0.5 of 72.7%. For the handguns, using only 50 real images yielded an A P 0.5 of 78.8%; however, by adding 16,000 simulated X-rays to these real images, the A P 0.5 increased to 91.6%. Our results prove that using simulated images of threat objects can improve the performance of object detection models. As modern object detectors process images in real-time, they establish themselves as a feasible approach for aiding inspectors and even fully automating baggage inspection. Our novel superimposition and colorization techniques are not only relevant to security but can also be employed in other areas of X-ray imaging. [ABSTRACT FROM AUTHOR]

The accurate classification of bone tumours is crucial for guiding clinical decisions regarding treatment and follow-up. However, differentiating between various tumour types is challenging due to the rarity of certain entities, high intra-class variability, and limited training data in clinical practice. This study proposes a multimodal deep learning model that integrates clinical metadata and X-ray imaging to improve the classification of primary bone tumours. The dataset comprises 1,785 radiographs from 804 patients collected between 2000 and 2020, including metadata such as age, affected bone site, tumour position, and gender. Ten tumour types were selected, with histopathology or tumour board decisions serving as the reference standard. Methods: Our model is based on the NesT image classification model and a multilayer perceptron with a joint fusion architecture. Descriptive statistics included incidence and percentage ratios for discrete parameters, and mean, standard deviation, median, and interquartile range for continuous parameters. Results: The mean age of the patients was 33.62 ± 18.60 years, with 54.73% being male. Our multimodal deep learning model achieved 69.7% accuracy in classifying primary bone tumours, outperforming the Vision Transformer model by five percentage points. SHAP values indicated that age had the most substantial influence among the considered metadata. Conclusion: The joint fusion approach developed in this study, integrating clinical metadata and imaging data, outperformed state-of-the-art models in classifying primary bone tumours. The use of SHAP values provided insights into the impact of different metadata on the model's performance, highlighting the significant role of age. This approach has potential implications for improving diagnostic accuracy and understanding the influence of clinical factors in tumour classification. [ABSTRACT FROM AUTHOR]

Bright and fast scintillators are highly crucial for high-speed X-ray imaging in the medical diagnostic radiology including angiography and cardiac computed tomography. The CsPbBr3 nanocrystal scintillator featuring a nanosecond radioluminescence decay time is a promising candidate. However, it suffers from a substantial photon self-absorption limiting the light output, and being bright and fast simultaneously is difficult. Here we design and in-situ synthesize multi-site ZnS(Ag)-CsPbBr3 heterostructures to modulate the bright and fast features of scintillators. We find external energy from ZnS(Ag) can effectively transfer to CsPbBr3 based on the non-radiative Förster resonance energy transfer, resulting in a light yield of 40,000 photons MeV−1. By combing a radioluminescence decay time of 36 ns and a spatial resolution of 30 lp mm−1, the scintillator enables high-speed X-ray imaging at 200 frames per second. This study showcases the structure design is significant for obtaining bright and fast perovskite scintillators for the real-time X-ray imaging. Yang et al. report in-situ growth of ZnS(Ag)-CsPbBr3 heterostructures through all solid-phase synthesis for X-ray scintillators. The multiple contact sites promote light yield via efficient energy transfer from ZnS(Ag) into CsPbBr3 and enable fast decay for high-speed X-ray imaging at 200 fps. [ABSTRACT FROM AUTHOR]

Accurately detecting a variety of lung abnormalities from heterogenous chest X-ray (CXR) images and writing radiology reports is often difficult and time-consuming.To access the utility of a novel artificial intelligence (AI) system (MOM-ClaSeg) in enhancing the accuracy and efficiency of radiologists in detecting heterogenous lung abnormalities through a multi-reader and multi-case (MRMC) observer performance study.Over 36,000 CXR images were retrospectively collected from 12 hospitals over 4 months and used as the experiment group and the control group. In the control group, a double reading method is used in which two radiologists interpret CXR to generate a final report, while in the experiment group, one radiologist generates the final reports based on AI-generated reports.Compared with double reading, the diagnostic accuracy and sensitivity of single reading with AI increases significantly by 1.49% and 10.95%, respectively (P <  0.001), while the difference in specificity is small (0.22%) and without statistical significance (P = 0.255). Additionally, the average image reading and diagnostic time in the experimental group is reduced by 54.70% (P <  0.001).This MRMC study demonstrates that MOM-ClaSeg can potentially serve as the first reader to generate the initial diagnostic reports, with a radiologist only reviewing and making minor modifications (if needed) to arrive at the final decision. It also shows that single reading with AI can achieve a higher diagnostic accuracy and efficiency than double reading. [ABSTRACT FROM AUTHOR]

Neutron imaging has gained significant importance as a material characterisation technique and is particularly useful to visualise hydrogenous materials in objects opaque to other radiations. Fields of application include investigations of hydrogen in metals as well as metal corrosion, thanks to the fact that neutrons can penetrate metals better than e.g. X-rays and are highly sensitive to hydrogen. However, at interfaces refraction effects sometimes obscure the attenuation image, which is used for hydrogen quantification. Refraction, a differential phase effect, diverts the neutron beam away from the interface in the image leading to intensity gain and intensity loss regions, which are superimposed to the attenuation image, thus obscuring the interface region and hindering quantitative analyses of e.g. hydrogen content in the vicinity of the interface. For corresponding effects in X-ray imaging, a phase filter approach was developed and is generally based on transport-of-intensity considerations. Here, we compare such an approach, that has been adapted to neutrons, with another simulation-based assessment using the ray-tracing software McStas. The latter appears superior and promising for future extensions which enable fitting forward models via simulations in order to separate phase and attenuation effects and thus pave the way for overcoming quantitative limitations at refracting interfaces. [ABSTRACT FROM AUTHOR]

This article discusses two cases of primary intraosseous glomus tumors with NOTCH2/3 fusions, both of which presented in the long bones. The patients were male, one young adult and one middle-aged adult. The tumors were characterized by nests of monomorphic epithelioid neoplasms with granular cytoplasm that were associated with dilated blood vessels. The tumors were classified as glomus tumors of uncertain malignant potential based on their size and the presence of focal spindled morphology and nuclear atypia. Recurrent NOTCH2/3 fusions have been identified in soft tissue glomus tumors, particularly in visceral lesions with malignant features. However, the relevance of these fusions in intraosseous tumors is unclear, and further clinical follow-up may be necessary. [Extracted from the article]

The study of biological soft tissue structures at the micron scale details the function of healthy and pathological tissues, which is vital in the diagnosis and treatment of diseases. Speckle based X-ray phase contrast tomographic scans at a nanometer scale have the potential to thoroughly analyse such tissues in a quantitative and qualitative manner. Diamond light source, the UKs national synchrotron facility developed and refined a 1-D X-ray speckle-based imaging technique, referred to as Fly scan mode. This novel image acquisition technique was used to perform a rapid structural composition scan of rodent lung histology samples. The rodent samples were taken from healthy and Staphylococcus aureus induced acute respiratory distress syndrome models. The analysis and cross comparison of the fly scan method, absorption-based tomography and conventional histopathology H&E staining microscopy are discussed in this paper. This analysis and cross comparison outline the ways the speckle-based technique can be of benefit. These advantages include improved soft tissue contrast, 3-D volumetric rendering, segmentation of specific gross tissue structures, quantitative analysis of gross tissue volume. A further advantage is the analysis of cellular distribution throughout the volumetric rendering of the tissue sample. The study also details the current limitations of this technique and points to ways in which future work on this imaging modality may progress. [ABSTRACT FROM AUTHOR]

Using high-resolution micro-CT imaging at 2.98 μm/voxel, we compared the percolation of hydrogen in gas injection with gas expansion for a hydrogen-brine system in Bentheimer sandstone at 1 MPa and 20 °C, representing hydrogen storage in an aquifer. We introduced dimensionless numbers to quantify the contribution of advection and expansion to displacement. We analysed the 3D spatial distribution of gas and its displacement in both cases and demonstrated that in gas injection, hydrogen can only advance from a connected cluster in an invasion-percolation type process, while in gas expansion, hydrogen can access more of the pore space even from disconnected clusters. The average gas saturation in the sample increased from 30% to 50% by gas expansion, and we estimated that 10% of the expanded volume is attributed to hydrogen exsolution from the brine. This work emphasises the importance of studying the combined effects of pressure decline and gas withdrawal in hydrogen storage to assess the influence of gas expansion on remobilising trapped gases. [Display omitted] • High-resolution X-ray imaging studied hydrogen injection and expansion in a sandstone. • Disconnected gas clusters can expand and reconnect during pressure decline. • Gas expansion increased the average gas saturation from 30% to 50% as pressure declined. • Hydrogen exsolution from brine increased the expanded gas volume by 10%. • Hydrogen accessed more of the larger pores by expansion than by injection. [ABSTRACT FROM AUTHOR]

Heart disease has been the leading cause of mortality worldwide in the recent decade. Since 2019, new lung-related infections have increased heart attack mortality. To minimize mortality, a unified framework is needed to predict early diagnosis utilizing different patient data. Existing methods failed to produce automatic solutions on the unified approach to cardiac problems considering lung infections. A unique automated disease diagnosis and classification framework using patient chest X-ray images and Electrocardiogram (ECG) signal is proposed. This integrated framework is unique in diagnosing and monitoring lung disease and cardiac problems utilizing patient X-ray and ECG. The proposed system is called the Deep Intelligence Framework for Diseases Detection (DIFDD). DIFDD procedures include pre-processing, automated feature extraction, and classification. An effective pre-processing method is designed to improve X-ray and ECG data. The 2D and 1D Convolutional Neural Network (CNN) techniques are proposed to extract automated features from pre-processed X-ray and ECG data. According to feature learning, automated detection uses several classifiers. Based on classifier results, a consolidated approach is presented for medical judgment on the patient's health for suitable treatment. The simulation results using the synthetic dataset revealed the efficiency of the proposed DIFDD model over the existing methods. The overall accuracy of the DIFDD model is improved by 1.5% and computational overhead is reduced by 13.56%. [ABSTRACT FROM AUTHOR]

Computer-aided diagnosis (CAD) techniques, exemplified by chest x-ray (CXR)-based methods, offer a cost-effective alternative for early-stage COVID-19 diagnosis compared to expensive options such as polymerase chain reaction (PCR) and computed tomography (CT) scan. Despite efforts to diagnose COVID-19 with CXR-based methods, their performance could be improved by considering the spatial relationships between regions of interest (ROIs) in CXR images. This oversight hinders the ability to accurately identify areas of the human lung most vulnerable to COVID-19. This model implements a two-way classification system to differentiate between lung X-ray impressions, accurately determining whether they are affected or normal. The effectiveness of this system is assessed using metrics such as accuracy, recall, precision, and F1-score. We employed over 2409 samples of X-ray images in the COVID-19 diagnosis process. The results obtained from the VGG16 model showcase outstanding performance, with a recognition rate of 99.58% for X-ray images and 94.29% for CT-scan pictures within the given sample size and two-class categorization. This model surpasses all existing approaches documented in the literature. Medical professionals and healthcare workers can effectively utilize this proposed system, leveraging X-rays and CT scans of human lungs to identify COVID-19 cases accurately. [ABSTRACT FROM AUTHOR]

Organic scintillators, pivotal in security and medical applications, face challenges due to limited X‐ray absorption and exciton utilization. Herein, a novel class of organic scintillators is introduced, named guest‐induced thermally activated delayed fluorescence (TADF) within supramolecular macrocycles via host‐guest through‐space charge transfer (TSCT). Four co‐crystals are obtained through orthogonal crystallizations involving calix[3]acridan (C[3]A) and calix[3]phenothiazine (C[3]P) macrocycles as hosts, along with 1,2‐dicyanobenzene (DCB) and 4‐bromo‐1,2‐benzenedicarbonitrile (BrDCB) as guests. Interestingly, DCB@C[3]A and BrDCB@C[3]A co‐crystals exhibit strong host‐guest TSCT with reduced single‐triplet energy gap for efficient TADF emission, which leads to enhanced exciton utilization and X‐ray absorption, yielding radioluminescence intensities over 29 and 25 times higher than C[3]A. Similarly, substituting C[3]A with C[3]P, the obtained TADF co‐crystals also outperform C[3]P in scintillation performance. Additionally, the scintillation color of co‐crystals can be adjusted by varying the electron‐donating abilities of macrocycles and the electron‐accepting abilities of guests, offering a simpler color‐tuning mechanism than covalent‐bonded scintillators. Furthermore, the flexible film based on DCB@C[3]A exhibits promising application in X‐ray radiography, showcasing a high spatial resolution of 20 lp mm−1 @MTF = 0.77. The innovative strategy of fabricating organic scintillators via reversible non‐covalent interactions presents a novel solution for designing color‐tunable and high‐performance scintillators. [ABSTRACT FROM AUTHOR]

Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data. Recent efforts have utilized pre-trained contrastive image-text models like CLIP, adapting them for medical use by fine-tuning the model with chest X-ray images and corresponding reports for zero-shot pathology classification, thus eliminating the need for pathology-specific annotations. However, most studies continue to use the same contrastive learning objectives as in the general domain, overlooking the multi-labeled nature of medical image-report pairs. In this paper, we propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. We aim to improve the performance of zero-shot pathology classification without relying on external knowledge. Our method can be applied to any pre-trained contrastive image-text encoder and easily transferred to out-of-domain datasets without further training, as it does not use external data. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models, with an average macro AUROC increase of 4.3%. Additionally, our method outperforms the state-of-the-art and marginally surpasses board-certified radiologists in zero-shot classification for the five competition pathologies in the CheXpert dataset. [ABSTRACT FROM AUTHOR]

Objective: The aim is to detect impacted teeth in panoramic radiology by refining the pretrained MedSAM model. Study design: Impacted teeth are dental issues that can cause complications and are diagnosed via radiographs. We modified SAM model for individual tooth segmentation using 1016 X-ray images. The dataset was split into training, validation, and testing sets, with a ratio of 16:3:1. We enhanced the SAM model to automatically detect impacted teeth by focusing on the tooth's center for more accurate results. Results: With 200 epochs, batch size equals to 1, and a learning rate of 0.001, random images trained the model. Results on the test set showcased performance up to an accuracy of 86.73%, F1-score of 0.5350, and IoU of 0.3652 on SAM-related models. Conclusion: This study fine-tunes MedSAM for impacted tooth segmentation in X-ray images, aiding dental diagnoses. Further improvements on model accuracy and selection are essential for enhancing dental practitioners' diagnostic capabilities. [ABSTRACT FROM AUTHOR]

Background: Detecting vertebral structural damage in patients with ankylosing spondylitis (AS) is crucial for understanding disease progression and in research settings. Objectives: This study aimed to use deep learning to score the modified Stoke Ankylosing Spondylitis Spinal Score (mSASSS) using lateral X-ray images of the cervical and lumbar spine in patients with AS in Asian populations. Design: A deep learning model was developed to automate the scoring of mSASSS based on X-ray images. Methods: We enrolled patients with AS at a tertiary medical center in Taiwan from August 1, 2001 to December 30, 2020. A localization module was used to locate the vertebral bodies in the images of the cervical and lumbar spine. Images were then extracted from these localized points and fed into a classification module to determine whether common lesions of AS were present. The scores of each localized point were calculated based on the presence of these lesions and summed to obtain the total mSASSS score. The performance of the model was evaluated on both validation set and testing set. Results: This study reviewed X-ray image data from 554 patients diagnosed with AS, which were then annotated by 3 medical experts for structural changes. The accuracy for judging various structural changes in the validation set ranged from 0.886 to 0.985, whereas the accuracy for scoring the single vertebral corner in the test set was 0.865. Conclusion: This study demonstrated a well-trained deep learning model of mSASSS scoring for detecting the vertebral structural damage in patients with AS at an accuracy rate of 86.5%. This artificial intelligence model would provide real-time mSASSS assessment for physicians to help better assist in radiographic status evaluation with minimal human errors. Furthermore, it can assist in a research setting by offering a consistent and objective method of scoring, which could enhance the reproducibility and reliability of clinical studies. [ABSTRACT FROM AUTHOR]

The world first came to know the existence of COVID-19 (SARS-CoV-2) in December 2019. Initially, doctors struggled to diagnose the increasing number of patients due to less availability of testing kits. To help doctors primarily diagnose the virus, researchers around the world have come up with some radiology imaging techniques using the Convolutional Neural Network (CNN). Previously some research methods were based on X-ray images and others on CT scan images. Few research methods addressed both image types, with the proposed models limited to detecting only COVID and NORMAL cases. This limitation motivated us to propose a 42-layer CNN model that works for complex scenarios (COVID, NORMAL, and PNEUMONIA_VIRAL) and more complex scenarios (COVID, NORMAL, PNEUMONIA_VIRAL, and PNEUMONIA_ BACTERIA). Furthermore, our proposed model indicates better performance than any other previously proposed models in the detection of COVID-19. [ABSTRACT FROM AUTHOR]

This work will review and discuss the use of computerised X-ray tomography (CXT) for analysing ancient, manufactured items, like stone building materials, glass and ceramics. It will consider particular techniques required, and/or of benefit, for CXT of heritage materials, such as special precautions during the experimentation to ensure there is no damage to the materials, special imaging methods such as elemental-specific imaging, and sample-specific image analysis requirements. This study shows how the knowledge of internal features, particularly pores, discerned from CXT can be used to reverse engineer the artefact fabrication process. CXT can be used to obtain information on both the raw materials (such as types and impurities) and fabrication techniques used. These abilities can then be used to establish technological evolution and the incidence of ancient behaviours like recycling and allow the linking of particular items to specific production sites. It will also be seen how CXT can aid the development of effective conservation techniques. This work will also consider how conclusions drawn from CXT data can be amended or augmented by the use of complementary non-destructive characterisation methods, such as gas overcondensation. [ABSTRACT FROM AUTHOR]

Pulmonary diseases, including pneumonia, represent a significant health challenge and are often diagnosed using X-rays. This study investigates the effectiveness of artificial intelligence (AI) in enhancing the diagnostic capabilities of X-ray imaging. Using Python and the PyTorch framework, we developed and trained several deep learning models based on DenseNet architectures (DenseNet121, DenseNet169, and DenseNet201) on a dataset comprising 5856 annotated X-ray images classified into two categories: Normal (Healthy) and Pneumonia. Each model was evaluated on its ability to classify images with metrics including binary accuracy, sensitivity, and specificity. The results demonstrated accuracy rates of 92% for Normal and 97% for Pneumonia. The models also showed significant improvements in diagnostic accuracy and reduced time for disease detection compared to traditional methods. This study underscores the potential of integrating convolutional neural networks (CNNs) with medical imaging to enhance diagnostic precision and support clinical decision-making in the management of pulmonary diseases. Further research is encouraged to refine these models and explore their application in other medical imaging domains. [ABSTRACT FROM AUTHOR]

Objectives: This study aims to develop an automated approach for estimating the vertical rotation of the thorax, which can be used to assess the technical adequacy of chest X-ray radiographs (CXRs). Methods: Total 800 chest radiographs were used to train and establish segmentation networks for outlining the lungs and spine regions in chest X-ray images. By measuring the widths of the left and right lungs between the central line of segmented spine and the lateral sides of the segmented lungs, the quantification of thoracic vertical rotation was achieved. Additionally, a life-size, full body anthropomorphic phantom was employed to collect chest radiographic images under various specified rotation angles for assessing the accuracy of the proposed approach. Results: The deep learning networks effectively segmented the anatomical structures of the lungs and spine. The proposed approach demonstrated a mean estimation error of less than 2° for thoracic rotation, surpassing existing techniques and indicating its superiority. Conclusions: The proposed approach offers a robust assessment of thoracic rotation and presents new possibilities for automated image quality control in chest X-ray examinations. Advances in knowledge: This study presents a novel deep-learning-based approach for the automated estimation of vertical thoracic rotation in chest X-ray radiographs. The proposed method enables a quantitative assessment of the technical adequacy of CXR examinations and opens up new possibilities for automated screening and quality control of radiographs. [ABSTRACT FROM AUTHOR]

The coronavirus occurred in Wuhan (China) first and it was declared a global pandemic. To detect coronavirus X-ray images can be used. Convolutional neural networks (CNNs) are used commonly to detect illness from images. There can be lots of different alternative deep CNN models or architectures. To find the best architecture, hyper-parameter optimization can be used. In this study, the problem is modeled as a multi-objective optimization (MOO) problem. Objective functions are multi-class cross entropy, error ratio, and complexity of the CNN network. For the best solutions to the objective functions, multi-objective hyper-parameter optimization is made by NSGA-III, NSGA-II, R-NSGA-II, SMS-EMOA, MOEA/D, and proposed Swarm Genetic Algorithms (SGA). SGA is a swarm-based algorithm with a cross-over process. All six algorithms are run and give Pareto optimal solution sets. When the figures obtained from the algorithms are analyzed and algorithm hypervolume values are compared, SGA outperforms the NSGA-III, NSGA-II, R-NSGA-II, SMS-EMOA, and MOEA/D algorithms. It can be concluded that SGA is better than others for multi-objective hyper-parameter optimization algorithms for COVID-19 detection from X-ray images. Also, a sensitivity analysis has been made to understand the effect of the number of the parameters of CNN on model success. [ABSTRACT FROM AUTHOR]

We systematically investigate the variability of polarized X-rays on a timescale of a few seconds in the low/hard state of the black hole binary Cygnus X-1. The correlation between polarization degrees and angles with X-ray intensity was analyzed using data collected by the Imaging X-ray Polarimetry Explorer (IXPE) in 2022 June. Given that X-ray variability in the low/hard state of Cygnus X-1 is non-periodic, flux peaks were aggregated to suppress statistical fluctuations. We divided the temporal profiles of these aggregated flux peaks into seven time segments and evaluated the polarization for each segment. The results reveal that the polarization degree was 4.6% |$\pm$| 1.2% and 5.3% |$\pm$| 1.2% before and after the peak, respectively, but decreased to 3.4% |$\pm$| 1.1% and 2.7% |$\pm$| 1.1% in the segments including and immediately following the peak. Furthermore, the polarization angle exhibited a slight shift from approximately 30 |$^{\circ }$| to |${\sim} 40^{\circ }$| before and after the peak. These findings suggest that the accretion disk contracts with increasing X-ray luminosity, and the closer proximity of the X-ray emitting gas to the black hole may lead to reduced polarization. [ABSTRACT FROM AUTHOR]

This study evaluated the mechanical performance of a cellulose nanocrystal (CNC)-based composite, consisting of hydroxyapatite and natural fibers, mimicking the mechanical properties of real bone. The effect of natural nanofibers on the cutting force of the composite was evaluated for suitability in surgical training. Although hydroxyapatite has been extensively studied in bone-related applications, the exploration of epoxy-based composites incorporating both hydroxyapatite and CNC represents a novel approach. The evaluation involved a load cell with an oscillating saw. The uniform distribution of CNCs within the composite was assessed using 3D X-ray imaging. The cutting force was found to be 4.005 ± 0.5469 N at a feed rate of 0.5 mm/s, comparable to that required when cutting real bone with the osteon at 90°. The 90-degree orientation of the osteon aligns with the cutting direction of the oscillating saw when performing knee replacements on the tibia and femur bones. The addition of CNCs resulted in changes in fracture toughness, leading to increased material fragmentation and surface irregularities. Furthermore, the change in the cutting force with depth was similar to that of real bone. The developed composite material enables bone-cutting surgeries using bioceramics and natural fibers without the risks associated with cadavers or synthetic fibers. Mold-based computed tomography data allows for the creation of various bone forms, enhancing skill development for surgeons. [ABSTRACT FROM AUTHOR]

In modern society, the amount of e-waste is growing year by year. Waste electronic items are complex, highly heterogeneous systems, containing organic material as well as several exotic, valuable, toxic, mostly metallic elements. In this study, the potential of X-ray and neutron radiography to reveal the inner structure of various complex e-waste was investigated. The images obtained using the two techniques were evaluated together to investigate the possibility of a more efficient segmentation of the individual components. The advantages and limitations of the two methods were identified for the studied waste types. X-ray radiography was found to be preferable for the identification of small metallic parts and for revealing the internal structure of e-waste with thick plastic coatings. Neutron radiography allowed for the identification of several components that did not provide sufficient contrast with X-ray imaging due to their similar X-ray attenuation compared to their surroundings. The combination of the two methods opens up new opportunities and could provide much more effective segmentation than either method alone. [ABSTRACT FROM AUTHOR]

Objectives: Attenuation correction is a critical phenomenon in quantitative positron emission tomography (PET) imaging with its own special challenges. However, computed tomography (CT) modality which is used for attenuation correction and anatomical localization increases patient radiation dose. This study was aimed to develop a deep learning model for attenuation correction of whole-body 68Ga-DOTATATE PET images. Methods: Non-attenuation-corrected and computed tomography-based attenuation-corrected (CTAC) whole-body 68Ga-DOTATATE PET images of 118 patients from two different imaging centers were used. We implemented a residual deep learning model using the NiftyNet framework. The model was trained four times and evaluated six times using the test data from the centers. The quality of the synthesized PET images was compared with the PET-CTAC images using different evaluation metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean square error (MSE), and root mean square error (RMSE). Results: Quantitative analysis of four network training sessions and six evaluations revealed the highest and lowest PSNR values as (52.86±6.6) and (47.96±5.09), respectively. Similarly, the highest and lowest SSIM values were obtained (0.99±0.003) and (0.97±0.01), respectively. Additionally, the highest and lowest RMSE and MSE values fell within the ranges of (0.0117±0.003), (0.0015±0.000103), and (0.01072±0.002), (0.000121±5.07xe-5), respectively. The study found that using datasets from the same center resulted in the highest PSNR, while using datasets from different centers led to lower PSNR and SSIM values. In addition, scenarios involving datasets from both centers achieved the best SSIM and the lowest MSE and RMSE. Conclusion: Acceptable accuracy of attenuation correction on 68Ga-DOTATATE PET images using a deep learning model could potentially eliminate the need for additional X-ray imaging modalities, thereby imposing a high radiation dose on the patient. [ABSTRACT FROM AUTHOR]

In X-ray CT imaging, there are some cases where the obtained CT images have serious ring artifacts and noise, and these degraded CT images seriously affect the quality of clinical diagnosis. Thus, developing an effective method that can simultaneously suppress ring artifacts and noise is of great importance. Total variation (TV) is a famous prior regularization for image denoising in the image processing field, however, for degraded CT images, it can suppress the noise but fail to reduce the ring artifacts. To address this issue, the L 0 smoothing filter is incorporated with TV prior for CT ring artifacts and noise removal problem where the problem is transformed into several optimization sub-problems which are iteratively solved. The experiments demonstrate that the ring artifacts and noise presented in the CT image can be effectively suppressed by the proposed method and meanwhile the detailed features such as edge structure can be well preserved. As the superiority of TV and L 0 smoothing filters are fully utilized, the performance of the proposed method is better than the existing methods such as the TV-based method and L 0 -based method. [ABSTRACT FROM AUTHOR]

Spatial resolution of scintillator is crucial for high‐quality X‐ray imaging, especially in tiny and complicated electronic component. In this work, PrPP2MnBr4 single crystal is obtained by dual‐solvent evaporation method, which gives an unprecedented high spatial resolution of 104.3 lp/mm, representingstate of the art among non‐lead metal halides. The study also conducts the preparation of large area scintillation screen (10 cm × 10 cm) by solidifying melted salt PrPP2MnBr4, thus giving an excellent X‐ray imaging with spatial resolution of 53.5 lp mm−1, which demonstrates its application on large area detection. [ABSTRACT FROM AUTHOR]

This paper presents advanced workflows that combine 3D X-ray microscopy (XRM), nanoscale tomography, and deep learning (DL) to generate a detailed visualization of the interior of electronic devices and assemblies to enable the study of internal components for failure analysis (FA). Newly developed techniques, such as the integration of DL-based algorithms for 3D image reconstruction to improve scan quality through increased contrast and denoising, are also discussed in this article. In addition, a DL-based tool called DeepScout is presented. DeepScout uses 3D XRM scans in targeted regions of interest as training data for upscaling high-resolution in a low-resolution dataset, of a wider field of view, using a neural network model. Ultimately, these workflows can be run independently or complementary to other multiscale correlative microscopy evaluations, e.g., electron microscopy, and they will provide valuable insights into the inner workings of electronic packages and integrated circuits at multiple length scales, from macroscopic features on electronic devices (i.e., hundreds of mm) to microscopic details in electronic components (in the tens of nm). Understanding advanced electronic systems through X-ray imaging and machine learning—perhaps complemented with some additional correlative microscopy investigations—can speed development time, increase cost efficiency, and simplify FA and quality inspection of printed circuit boards (PCBs) and electronic devices assembled with new emerging technologies. [ABSTRACT FROM AUTHOR]

Transcatheter arterial embolization is one of the important tools in the interventional treatment of hepatocellular carcinoma. However, the existing embolic agents cannot achieve long-term visualization effectiveness. Therefore, we developed a radiopaque embolic microsphere (PTADE@Ta) capable of long-term imaging. PTADE@Ta was successfully prepared by dispersing tantalum nanoparticles in a poly (diallyl terephthalate) via photopolymerization. The microspheres were characterized by SEM observation and thermogravimetric analysis. The in vitro biocompatibility was assessed by determining the cell metabolic activity of human umbilical vein endothelial cells, and the in vivo biocompatibility was assessed by observing tissue sections from New Zealand white rabbits. Their non-degradability was verified by their degradability in lysozyme solution. The radiopaque effect was verified by X-ray and CT imaging capability. The results showed that the embolic product has good dispersibility, thermal stability, biocompatibility and long-term imaging. [ABSTRACT FROM AUTHOR]

This paper presents a lightweight and accurate convolution neural network (CNN) based on encoder in vision transformer structure, which uses multigroup convolution rather than multilayer perceptron and multiheaded self-attention. We propose a group convolution block called multigroup convolution attention (MGCA) and squeeze and excitation (SE). The MGCA includes two parts: three 1 × 1 convolutions concatenated along the channel dimension and depth-wise separable convolution. SE is used as a skip connection to provide long-range dependencies. MGCA-SE is introduced to reduce the number of parameters in state-of-the-art network in order to use fewer datasets for training CNN. Furthermore, we provide a lightweight network based on MGCA-SE in Resnet architecture called Resnet-multigroup convolution attention-squeeze and excitation (Res-MGCA-SE) in order to have early detection and treatment of medical images. Finally, Res-MGCA-SE is evaluated on lung cancer and Covid-19 chest X-ray and CT and images. According to our research findings, MGCA-SE can change convolutional layers in state-of-the-art networks and switch them to lightweight networks with properties comparable to heavy-weight networks. [ABSTRACT FROM AUTHOR]

Bone illnesses arise at a young age itself, so bone age assessment (BAA) is primarily utilized in paediatrics to identify their growth. Several BAA-related methods are employed to determine bone maturity; however, they do not give accuracy and the rate of error increases. To overcome this issue, in this manuscript, TW3-based Region of Interest (ROI) identification and classification with Chaotic ANN (CANN), as well as Deep Neural Network optimized with Evolved Gradient Direction optimizer (EVGO) architecture, is proposed for an Automated BAA classification. In this, Hand X-Ray images are taken from the Digital Hand Atlas (DHA) dataset and the Radiological Society of North America (RSNA) database. Here, Tanner-Whitehouse (TW3) and Shallow convolution neural network (SCNN) is utilized for extracting the ROI regions such as radius, ulna, and short bones (RUS) from the wrist region of the left hand. After that, the extracted ROI feature data are given to CANN for predicting BAA. Then, the predicted data are classified using the DNN-EVGO network. The bone age evaluation is then classified depending on maturity phases. The proposed approach is activated in MATLAB. Simulation outcomes of TW3- SCNN- CANN- DNN-EVGO- BAA methods for DHA database attain higher accuracy of 45.75%, 37.64%, 24.64% when analysed to the existing models, such as Faster Region-Convolutional Neural network oriented feature learning with optimal trained Recurrent Neural Network for BAA for paediatrics (TW3-F-R-CNN-AF-SFO), Multi-objective segmentation approach for BAA under parameter tuning- U-net architecture, and TW3-based fully automated bone age assessment system using deep neural networks (TW3-F-R-CNN-VGGNet-CNN-BAA). [ABSTRACT FROM AUTHOR]

With the increasing strain on the health system, there is a growing need for automatic medical image diagnosis. Emerging technologies for medical diagnosis can help to achieve the goals of sustainable development. However, analyzing medical images can be challenging due to uncertain data, ambiguity, and impreciseness. To address this issue, we have developed a novel BoneNet-NS technique to classify fractures in X-ray bone images. The proposed approach is based on the power of deep learning (DL) and neutrosophic set (NS) to deal with aleatoric uncertainty. Moreover, we present two frameworks for integrating NS with DL models: BoneNet-NS1 and BoneNet-NS2. We employ various DL models, including Xception, ResNet52V2, DenseNet121, and customized CNN to evaluate both frameworks. Furthermore, 4924 X-ray bone images are utilized to distinguish between fractured and non-fractured classes. The statistical analyses demonstrate that BoneNet-NS2 performs better than BoneNet-NS1 for most DL models. Specifically, using the ResNet52V2 model, our proposed BoneNet-NS2 achieved the highest accuracy, log loss, precision, recall, F1-score, and AUC with values of 99.7%, 0.006, 99.7%, 99.7%, 99.7%, and 99.7%, respectively. [ABSTRACT FROM AUTHOR]

The layered double perovskite microcrystals show excellent stability both under ambient condition and under X-ray irradiation, their luminescent properties and applications in X-ray imaging have been demonstrated. [Display omitted] Metal halide perovskites, as a new class of attractive and potential scintillators, are highly promising in X-ray imaging. However, their application is limited by the sensitivity to moisture and irradiation. To address this issue, we reported a 2D layered double perovskite material Cs 4 Cd 1-x Mn x Bi 2 Cl 12 that exhibits high stability both under ambient condition and under X-ray irradiation. Cs 4 Cd 1-x Mn x Bi 2 Cl 12 demonstrates superior scintillation performance, including excellent X-ray response linearity and a high light yield (∼34,450 photons/MeV). More importantly, the X-ray excited emission intensity maintains 92% and 94% of its original value after stored at ambient condition for over two years and after X-ray irradiation with a total dose of 11.4 Gy, respectively. By mixing with PDMS (polydimethylsiloxane), we have successfully produced a high-quality flexible film that can be bent freely while maintaining its excellent scintillation properties. The scintillating screen exhibits outstanding imaging ability with a spatial resolution of up to 16.7 line pairs per millimeter (lp/mm), also, the superiority of this scintillation screen in flexible X-ray imaging is demonstrated. These results indicate the huge potential of this high-stability double perovskite scintillator in X-ray imaging. [ABSTRACT FROM AUTHOR]

This study proposes a walnut target detection algorithm based on improved YOLOv5 and x‐ray imaging to meet the demand for internal quality detection and removal in the Xinjiang walnut industry. By replacing the C3 module in the backbone layer with the C2f module and the couple‐head in the head layer with the decouple‐head, the algorithm reduces computational complexity, enhances robustness and generalizability, and retains more spatial information, thereby improving the performance of multicategory small target detection. In addition, this paper replaces the original CIOU loss function with the EIOU loss function to improve the convergence speed of the algorithm's accuracy and boundary aspect ratio. Compared with the original model, the improved model, improved YOLOv5, maintains the same average precision for normal walnuts while increasing the average precision for shriveled walnuts and empty‐shell walnuts by 8.2% and 0.4%, respectively. Compared with other mainstream models, such as VGG16, ResNet50, YOLOv5s, YOLOv7, YOLOv8s, YOLOv9s, and YOLOv10s, this model achieves the highest detection accuracy and good detection performance, with a single‐image detection time of 11.9 ms, meeting the requirements for real‐time detection. This work lays a foundation for automatic robot detection of the internal quality and removal of walnuts, showing practical application potential. Practical applications: Xinjiang stands as a prominent producer of walnuts; however, due to the decentralized nature of its cultivation and management processes, a notable prevalence of internal empty shells and shrinkage is observed, which substantially diminishes their commercial value. The integration of YOLOv5 with x‐ray imaging technology promises to enhance the precision of internal quality assessments of walnuts. The improved YOLOv5 model, as delineated in this study, exhibits the highest detection accuracy when benchmarked against a multitude of other models. It achieves a detection latency of merely 11.9 ms per image, thereby satisfying the stringent demands for real‐time detection applications. This model is designed for integration into x‐ray systems with an adjunctive sorting mechanism, which facilitates the inspection and exclusion of defective walnuts on conveyor belts. [ABSTRACT FROM AUTHOR]

Featured Application: Importance of the evaluation of radiation doses to highly radiosensitive organs in children using dental cone beam computed tomography, given that children are highly sensitive to radiation. Dental cone beam computed tomography (CBCT) is a diverse 3D X-ray imaging technique that has enabled clear visualization of the teeth and surrounding structures. The most common diagnostic purpose of dental CBCT examination in children is ectopic eruption and impacted teeth, and a small field of view (FOV) is often used. Since it is difficult for children to control their body movements, reducing the rotation angle is effective. However, no studies have examined the effects of different rotation angles on radiation doses to highly radiosensitive organs in children using small FOVs. The purpose of this study was to examine the effects of small FOVs (4 × 4 cm and 6 × 6 cm) and rotation angles (360° and 180°) on doses that highly sensitize organs in children using dental CBCT. The entrance surface doses to lenses, thyroid lobes, parotid glands, and sublingual glands of a pediatric whole-body phantom were measured. By reducing the FOV from 6 × 6 cm to 4 × 4 cm, the dose to the sublingual gland could be significantly decreased. Additionally, by reducing the rotation angle from 360° to 180°, the lens dose can be decreased significantly. As the rate of dose reduction varies among organs, it is important to consider the relative positions of different organs with respect to the FOV and the trajectory of the X-ray tube. [ABSTRACT FROM AUTHOR]

Pneumonia is a condition characterised by the sudden inflammation of lung tissue, which is triggered by microorganisms such as fungi, viruses, and bacteria. Chest X-ray imaging (CXR) can detect pneumonia, but it requires considerable time and medical expertise. Consequently, the objective of this study is to diagnose pneumonia using CXR imaging in order to effectively detect early cases of pneumonitis in children. The study employs the ensemble transfer learning convolutional neural network (ETL-CNN) transfer learning ensemble, which combines multiple CNN transfer learning models. Resnet50-VGG19 and VGG19-Xception are the ETL-CNN models used in this investigation. Comparing ETL-CNN models to CNN transfer learning models such as Resnet50, VGG19, and Xception. Pediatric CXR pneumonia, which consists of a normal and pneumonia image, is the source of these study results. The results of this analysis indicate that Resnet50-VGG19 achieved the highest level of accuracy, 99.14%. Additionally, the Resnet50-VGG19 obtained the highest levels of precision and recall when comparing to other models. Consequently, the conclusion of this study is that the Resnet50-VGG19 model can generate acceptable classification performance for pediatric pneumonia based on CXR. This study improves classification results for performance when compared to earlier studies. [ABSTRACT FROM AUTHOR]

Multiple pathologic conditions can lead to a diseased and symptomatic glenohumeral joint for which total shoulder arthroplasty (TSA) replacement may be indicated. The long-term survival of implants is limited. With the increasing incidence of joint replacement surgery, it can be anticipated that joint replacement revision surgery will become more common. It can be challenging at times to retrieve the manufacturer of the in situ implant. Therefore, certain systems facilitated by AI techniques such as deep learning (DL) can help correctly identify the implanted prosthesis. Correct identification of implants in revision surgery can help reduce perioperative complications and complications. DL was used in this study to categorise different implants based on X-ray images into four classes (as a first case study of the small dataset): Cofield, Depuy, Tornier, and Zimmer. Imbalanced and small public datasets for shoulder implants can lead to poor performance of DL model training. Most of the methods in the literature have adopted the idea of transfer learning (TL) from ImageNet models. This type of TL has been proven ineffective due to some concerns regarding the contrast between features learnt from natural images (ImageNet: colour images) and shoulder implants in X-ray images (greyscale images). To address that, a new TL approach (self-supervised pertaining (SSP)) is proposed to resolve the issue of small datasets. The SSP approach is based on training the DL models (ImageNet models) on a large number of unlabelled greyscale medical images in the domain to update the features. The models are then trained on a small labelled data set of X-ray images of shoulder implants. The SSP shows excellent results in five ImageNet models, including MobilNetV2, DarkNet19, Xception, InceptionResNetV2, and EfficientNet with precision of 96.69%, 95.45%, 98.76%, 98.35%, and 96.6%, respectively. Furthermore, it has been shown that different domains of TL (such as ImageNet) do not significantly affect the performance of shoulder implants in X-ray images. A lightweight model trained from scratch achieves 96.6% accuracy, which is similar to using standard ImageNet models. The features extracted by the DL models are used to train several ML classifiers that show outstanding performance by obtaining an accuracy of 99.20% with Xception+SVM. Finally, extended experimentation has been carried out to elucidate our approach's real effectiveness in dealing with different medical imaging scenarios. Specifically, five different datasets are trained and tested with and without the proposed SSP, including the shoulder X-ray with an accuracy of 99.47% and CT brain stroke with an accuracy of 98.60%. [ABSTRACT FROM AUTHOR]

The application of CdZnTe(CZT) crystals in infrared focal plane detectors and x-ray imaging detectors is hindered by the low infrared transmittance (IRT) and the presence of Cd/Te inclusions/precipitation. Over the preceding decades, strategies involving Cd vapor control during the growth process and substrate post-annealing have been posited to address these challenges. Presently, the prioritized approach is the utilization of substrate post-annealing, owing to the limited precision in comprehending the Cd-Te equilibrium and the intricacies associated with Cd vapor control technology. This study delves into the effect of the removed surface layer depth of a CZT and the selection of the (111) A-face or (111) B-face on IRT during Cd atmosphere annealing. It is recommended that a minimum of 60 μm of the surface layer be eliminated using chemical mechanical polishing technology before annealing. Experimental findings further reveal that Cd atom diffusion from the (111) A-face results in an IRT enhancement of up to 60%, in stark contrast to the slight improvement observed with the (111) B-face after annealing. The mechanism of Cd atom diffusions affecting the IRT in the annealing process is discussed. [ABSTRACT FROM AUTHOR]

The automated creation of medical reports from images of chest X-rays has the potential to significantly reduce workloads for healthcare providers and accelerate patient care, especially in environments with limited resources. This study provides an extensive overview of deep learning-based techniques designed for radiology report generation from chest X-ray pictures automatically. By examining recent research, we delve into various deep learning architectures and techniques used for this task, including transformer-based approaches, attention mechanisms, sequence-to-sequence models, adversarial training methods, and hybrid models. We also discuss about the datasets used for evaluation and training, as well as future directions and research problems in this area. The significance of deep learning in revolutionizing radiology reporting is further emphasized by our review, which also highlights the need for additional research to address challenges such data accessibility, image quality variability, interpretation of complex findings, and contextual integration. The objective of this research is to present a comparative analysis of cutting-edge methods for developing automated medical report generation to enhance patient outcomes and healthcare delivery. [ABSTRACT FROM AUTHOR]

In medical imaging, accurate diagnosis heavily relies on effective image enhancement techniques, particularly for X-ray images. Existing methods often suffer from various challenges such as sacrificing global image characteristics over local image characteristics or vice versa. In this paper, we present a novel approach, called G-CLAHE (Global-Contrast Limited Adaptive Histogram Equalization), which perfectly suits medical imaging with a focus on X-rays. This method adapts from Global Histogram Equalization (GHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to take both advantages and avoid weakness to preserve local and global characteristics. Experimental results show that it can significantly improve current state-of-the-art algorithms to effectively address their limitations and enhance the contrast and quality of X-ray images for diagnostic accuracy. [ABSTRACT FROM AUTHOR]

We present the first joint spectral and imaging analysis of hard X-ray (HXR) emission from three microflares observed by the Nuclear Spectroscopic Telescope ARray (NuSTAR) and Solar Orbiter/Spectrometer/Telescope for Imaging X-rays (STIX). We studied 5 joint spectra from GOES A7, B1, and B6 class microflares from active region AR12765 on 2020 June 6 and 7. As these events are very bright for NuSTAR, resulting in extremely low (<1 per cent) livetime, we introduce a pile-up correction method. All five joint spectra were fitted with an isothermal model finding temperatures in the 9–11 MK range. Furthermore, three joint spectra required an additional non-thermal thick-target model finding non-thermal powers of |$10^{25}$| – |$10^{26}$| erg s |$^{-1}$|⁠. All the fit parameters were within the ranges expected for HXR microflares. The fit results give a relative scaling of STIX and NuSTAR mostly between 6 and 28 per cent (one outlier at 52 per cent) suggesting each instrument are well calibrated. In addition to spectral analysis, we performed joint HXR imaging of the June 6 and one of the June 7 microflares. In NuSTAR's field of view (FOV), we observed two separate non-thermal sources connected by an elongated thermal source during the June 6 microflares. In STIX's FOV (44 |$^{\circ }$| W with respect to NuSTAR), we imaged thermal emission from the hot flare loops which when reprojected to an Earth viewpoint matches the thermal sources seen with NuSTAR and in the hotter EUV channels with the Solar Dynamic Observatory's Atmospheric Imaging Assembly. [ABSTRACT FROM AUTHOR]