Search

High-performance and low-cost metal halide perovskite scintillator materials have important applications in X-ray detection and imaging. However, large-sized perovskite scintillator panel with high transmittance, low toxicity and long-term stability is still lacking. Herein, Eu2+ doped cesium alkaline earth chloride nanocrystals (Eu2+: CsCaCl 3 , Eu2+: CsSrCl 3 , and Eu2+: Cs 2 BaCl 4 NCs) embedded in glasses through conventional melt-quenching and subsequent heat-treatment were developed. These NCs doped glasses exhibited highly efficient and narrowband photoluminescence in blue region. Benefitting from the large X-ray absorption coefficient and high photoluminescence quantum yied, these Eu2+: CsCaCl 3 NCs doped glass scintillator shows light yield of ∼9300 photons/MeV, detection limit of ∼213.8 μGy/s, and spatial resolution of 30.0 lp/mm. These results demonstrated that glasses containing Eu2+ doped cesium alkaline earth chloride nanocrystals are promising for X-ray detection and imaging. [ABSTRACT FROM AUTHOR]

The healthcare system in India faces an acute shortage of medical staff, significantly impacting the nation's ability to provide sufficient healthcare services. X-ray reports are paramount to orthopaedic surgeons for making critical patient care decisions. Implementing automated systems for detecting bone fractures offers a potentially efficient solution to supplement the limited workforce. However, these systems encounter substantial hurdles, such as inconsistent image quality and the risk of incorrect diagnosis due to the limitations of current technology. The research provides a specialised tool for identifying bone fractures with high precision (97% accuracy) and an excellent overall rating (F1 score of 0.98), showing it can reliably detect fractures. The assessment of this model is augmented by visual tools like heatmaps and performance graphs, providing an in-depth analysis of its operational effectiveness. Furthermore, creating a user-friendly interface is intended to streamline the adoption of this tool in clinical settings. Notwithstanding its demonstrated precision, the model must navigate data-related challenges, precisely data complexity and the representation of different categories, to prevent skewed outcomes. Clarifying the model's decision-making process and adaptability to various clinical situations are also critical. The study emphasises the need for thorough testing to ensure the model's dependability in diagnosing fractures before being deployed effectively in the medical field. [ABSTRACT FROM AUTHOR]

[Display omitted] Amyloid- β (A β) plaques from Alzheimer's Disease (AD) can be visualized ex vivo in label-free brain samples using synchrotron X-ray phase-contrast tomography (XPCT). However, for XPCT to be useful as a screening method for amyloid pathology, it is essential to understand which factors drive the detection of A β plaques. The current study was designed to test the hypothesis that A β -related contrast in XPCT could be caused by A β fibrils and/or by metals trapped in the plaques. Fibrillar and elemental compositions of A β plaques were probed in brain samples from different types of AD patients and AD models to establish a relationship between XPCT contrast and A β plaque characteristics. XPCT, micro-Fourier-Transform Infrared spectroscopy and micro-X-Ray Fluorescence spectroscopy were conducted on human samples (one genetic and one sporadic case) and on four transgenic rodent strains (mouse: APPPS1, ArcA β , J20; rat: TgF344). A β plaques from the genetic AD patient were visible using XPCT, and had higher β -sheet content and higher metal levels than those from the sporadic AD patient, which remained undetected by XPCT. A β plaques in J20 mice and TgF344 rats appeared hyperdense on XPCT images, while they were hypodense with a hyperdense core in the case of APPPS1 and ArcA β mice. In all four transgenic strains, β -sheet content was similar, while metal levels were highly variable: J20 (zinc and iron) and TgF344 (copper) strains showed greater metal accumulation than APPPS1 and ArcA β mice. Hence, a hyperdense contrast formation of A β plaques in XPCT images was associated with biometal entrapment within plaques. The role of metals in Alzheimer's disease (AD) has been a subject of continuous interest. It was already known that amyloid- β plaques (A β), the earliest hallmark of AD, tend to trap endogenous biometals like zinc, iron and copper. Here we show that this metal accumulation is the main reason why A β plaques are detected with a new technique called X-ray phase contrast tomography (XPCT). XPCT enables to map the distribution of A β plaques in the whole excised brain without labeling. In this work we describe a unique collection of four transgenic models of AD, together with a human sporadic and a rare genetic case of AD, thus exploring the full spectrum of amyloid contrast in XPCT. [ABSTRACT FROM AUTHOR]

The growth of the CsI(Tl) scintillators deposited on glass substrates with proper wavelength matching the mainstream semiconductor circuits is crucial for X-ray imaging industry. But the coupling loss between the scintillators and silicon based photo sensors has limited the performance. So fabricating CsI(Tl) films on monocrystalline silicon is greatly important for next-generation high performance X-ray image devices. However, the lattice and thermal mismatch between CsI(Tl) and Si always deteriorates the morphology and structure, and thus degrades the property of the CsI(Tl) scintillation converters. Here, by utilizing crystalline graphene(Gr) as a buffer layer, the van der Waals epitaxial growth of CsI(Tl) film on Si(111) substrate is reported and its advanced applications are demonstrated. The introduced graphene buffer layer extremely frees the stress between CsI(Tl) and Si substrate. Therefore, the CsI(Tl) films show perfect micro-columnar and crystalline structures, and then, exhibit much higher light output and signal to noise ratio, and better modulation transfer functions and a bar pattern X-ray image compared to that on bare Si(111) substrate. This facile method not only lays the foundation for the epitaxy of the alkali halide crystals, including CsI(Tl), onto Si-based detectors and its applications in radiation detection, but also may broaden a new perspective of deposition of CsI(Tl) scintillators into flexible substrates. [ABSTRACT FROM AUTHOR]

This article explore lung cancer using a hybrid deep learning (DL) model. Thus, this article offers a hybrid CNN along with the SVM classification method with tuned hyperparameters, which is the orthogonal Convolution neural network-support vector machine OCNN-SVM model. Each lung image may be automatically categorized and analyzed by this system to determine whether cancer cells are present. CNN has fewer parameters and is easier to train than a fully linked network with an exact count of hidden units. SVM has also been used to remove irrelevant data that has an adverse effect on accuracy. The effectiveness of this method is assessed in this research, and the findings show that the proposed orthogonal Convolution neural network-support vector machine (OCNN-SVM) model has been successful in categorizing lung images. [ABSTRACT FROM AUTHOR]

Micron/sub-micron hard X-ray imaging is an important development direction of X-ray detection technology. Scintillation screens with excellent X-ray stopping power and high light output are desired to obtain good imaging quality. Europium-doped lutetium oxide (Lu 2 O 3 :Eu) film with micro-columnar structure is an ideal candidate for this application. In this study, micro-columnar structured Lu 2 O 3 :Eu films were prepared on quartz glass substrates by laser chemical vapor deposition (LCVD) method. The influences of preparation conditions on structure and morphology properties of films were investigated by X-ray diffraction (XRD) and scanning electron microscopy (SEM). Photoluminescence and scintillation properties of the films, including photoluminescence excitation (PLE), photoluminescence (PL), PL decay, X-ray excitation luminescence (XEL), and afterglow curves, were recorded. The relationships between structure, morphology, luminescence properties of films, and preparation conditions were investigated and discussed as well. The preparation conditions include laser power, oxygen flow rate, and precursor evaporation temperature. In addition, dual-layer Lu 2 O 3 :Eu film was prepared for the first time by just turning off the laser. [ABSTRACT FROM AUTHOR]

In this research work, a new deep learning model named VGG-COVIDNet has been proposed which can classify COVID-19 cases from normal cases over X-Rays and CT scan images of lungs. Medical practitioners use the X-Rays and CT scan images of lungs to identify whether a person is infected from COVID or not. In present times, it is very important to give real time COVID prediction with high reliability of results. Deep learning models equipped with machine learning support have been found very influential in accurate prediction of COVID or Non-COVID cases in real time. However, there are some limitations associated with the performance of these model which are model size, achieving good balance of model size and accuracy, and making a single model fitting well for both X-Ray and CT Scan image datasets. Keeping in mind these performance constraints, this new model (VGG-COVIDNet) has been proposed for real time prediction of COVID cases with good balance of model size and accuracy working well for both type of datasets (CT Scan and X-Ray). In order to control model size, an improved version of VGG-16 architecture has been proposed which contains only 13 convolutional layers and 5 fully connected layers. Multiple dropout layers have been added in the proposed architecture which can drop some percentage of features and applies random transformations to decrease the model over-fitting issue. Keeping in mind the primary goal to increase the model accuracy the proposed model has been trained on different datasets with ReLU activation function which is one of the best non-linear activation functions. Four different capacity datasets with CT scan and X-Ray images have been used to validate the performance of proposed model. The proposed model gives an overall accuracy of more than 90% on both types of input datasets i.e. X-Ray and CT Scan. [ABSTRACT FROM AUTHOR]

• Global Context Feature Extraction (GCFE) module is proposed, which can extract multi-scale global contextual information. • A Dual Scale Feature Aggregation (DSFA) module is proposed to fuse the features from different scales. • A learnable Gabor convolution layer is designed to enhance its ability to capture the edge and contour information of object. • A Spatial Attention (SA) mechanism is designed to further enhance the spatial structure information of object. Prohibited Object Detection (POD) in X-ray images plays an important role in protecting public safety. Automatic and accurate POD is required to relieve the working pressure of security inspectors. However, the existing methods cannot obtain a satisfactory detection accuracy, and especially, the problem of object occlusion also has not been solved well. Therefore, in this paper, according to the specific characteristics of X-ray images as well as low-level and high-level features of Convolutional Neural Network (CNN), different feature enhancement strategies have been elaborately designed for occluded POD. First, a learnable Gabor convolutional layer is designed and embedded into the low layer of the network to enhance the network's capability to capture the edge and contour information of object. A Spatial Attention (SA) mechanism is then designed to weight the output features of the Gabor convolutional layer to enhance the spatial structure information of object and suppress the background noises simultaneously. For the high-level features, Global Context Feature Extraction (GCFE) module is proposed to extract multi-scale global contextual information of object. And, a Dual Scale Feature Aggregation (DSFA) module is proposed to fuse these global features with those of another layer. To verify the effectiveness of the proposed modules, they are embedded into typical one-stage and two-stage object detection frameworks, i.e., Faster R-CNN and YOLO v5L, obtaining POD-F and POD-Y methods, respectively. The proposed methods have been extensively evaluated on three publicly available benchmark datasets, namely SIXray, OPIXray and WIXray. The experimental results show that, compared with existing methods, the proposed POD-Y method can achieve a state-of-the-art detection accuracy. And POD-F can also achieve a competitive detection performance among the two-stage detection methods. 1 1 https://github.com/Open-my-paper-code/POD. [ABSTRACT FROM AUTHOR]

COVID-19 had caused the whole world to come to a standstill. The current detection methods are time consuming as well as costly. Using Chest X-rays (CXRs) is a solution to this problem, however, manual examination of CXRs is a cumbersome and difficult process needing specialization in the domain. Most of existing methods used for this application involve the usage of pretrained models such as VGG19, ResNet, DenseNet, Xception, and EfficeintNet which were trained on RGB image datasets. X-rays are fundamentally single channel images, hence using RGB trained model is not appropriate since it increases the operations by involving three channels instead of one. A way of using pretrained model for grayscale images is by replicating the one channel image data to three channel which introduces redundancy and another way is by altering the input layer of pretrained model to take in one channel image data, which comprises the weights in the forward layers that were trained on three channel images which weakens the use of pre-trained weights in a transfer learning approach. A novel approach for identification of COVID-19 using CXRs, Contrast Limited Adaptive Histogram Equalization (CLAHE) along with Homomorphic Transformation Filter which is used to process the pixel data in images and extract features from the CXRs is suggested in this paper. These processed images are then provided as input to a VGG inspired deep Convolutional Neural Network (CNN) model which takes one channel image data as input (grayscale images) to categorize CXRs into three class labels, namely, No-Findings, COVID-19, and Pneumonia. Evaluation of the suggested model is done with the help of two publicly available datasets; one to obtain COVID-19 and No-Finding images and the other to obtain Pneumonia CXRs. The dataset comprises 6750 images in total; 2250 images for each class. Results obtained show that the model has achieved 96.56% for multi-class classification and 98.06% accuracy for binary classification using 5-fold stratified cross validation (CV) method. This result is competitive and up to the mark when compared with the performance shown by existing approaches for COVID-19 classification. [ABSTRACT FROM AUTHOR]

In recent years, copper-based halide scintillators have attracted tremendous attention due to their excellent luminescent properties and low manufacturing costs. Herein, a high-performance and low-cost Cs 5 Cu 3 Cl 6 I 2 scintillator is prepared by simple mechanical grinding. The mixed-halide Cs 5 Cu 3 Cl 6 I 2 phosphor exhibits a blue emission centered at 475 nm with a large stokes shift, originating from the self-trapped exciton emission of Cu sites. The photoluminescence quantum yield (PLQY) of Cs 5 Cu 3 Cl 6 I 2 can be increased to 88.4% from 20.4% by the efficient suppression of the anion vacancy defects. In addition, the Cs 5 Cu 3 Cl 6 I 2 scintillator shows a high steady-state X-ray to light conversion efficiency of about 57000 photons/MeV, good X-ray linear response, and low detection limit of 71.9 nGy air /s. The X-ray imaging results based on the Cs 5 Cu 3 Cl 6 I 2 scintillator screen display a high spatial resolution of 9.0 line-pairs per millimeter (lp/mm). Furthermore, Cs 5 Cu 3 Cl 6 I 2 exhibits good radiation stability under a total dose of 113.58 Gy air. Overall, the Cs 5 Cu 3 Cl 6 I 2 scintillator prepared by mechanical grinding method has the advantages of low cost, high efficiency, and good radiation resistance, suggesting its huge potential in X-ray detection and imaging. [ABSTRACT FROM AUTHOR]

This work demonstrated a perovskite intermediate assisted hot-pressing method to fabricate FAPbBr 3 polycrystalline wafer X-ray detectors with near-single-crystal performance. The DMSO vapor released from the decomposition of FAPbBr 3 ·DMSO during the hot-pressing process will promote the in-situ growth of FAPbBr 3 crystal grains and improve the crystallinity, resulting in remarkable X-ray detection performance. [Display omitted] • FAPbBr 3 ·DMSO intermediate perovskite phase assisted hot-pressing approach. • In-situ FAPbBr 3 crystal growth promoted by DMSO vapor from FAPbBr 3 ·DMSO. • Quality improvement of polycrystalline perovskite wafers by hot-pressing process. • Polycrystalline FAPbBr 3 with X-ray detection properties similar to single crystals. Polycrystalline perovskite wafers featured in customizable in dimensions and thickness, represent a frontier in mass production of X-ray detectors. Nevertheless, inherent low crystallinity, elevated defect density, and grain boundaries in polycrystalline wafers typically impair the detection performance. Herein, a novel hot-pressing approach employing the perovskite intermediate phase FAPbBr 3 ·DMSO was demonstrated to improve the quality and X-ray detection performance of polycrystalline perovskite wafers. The in-situ growth of FAPbBr 3 wafers were promoted via dimethyl sulfoxide (DMSO) vapor released from the decomposition of FAPbBr 3 ·DMSO phase during the hot-pressing process, resulting in compact morphology, large grain size, superior crystallinity and diminished defect density. The resulted wafers exhibit a high ion activation energy (E a) of 0.45 eV and a substantial mobility-lifetime product (μτ) of 7.41 × 10−4 cm2 V−1. These advancements equip FAPbBr 3 wafer-based detectors with remarkable sensitivity of 3694.6 μC Gy air −1 cm−2, low detection limit (LoD) of 43.8 nGy air s−1, and stable operational performance, comparable to that of single-crystal alternatives. Moreover, the detectors exhibit exceptional X-ray imaging capabilities with a spatial resolution of 4.41 lp mm−1. Thus, the thermally induced decomposition characteristic of perovskite intermediate phase presents a novel avenue for the amelioration of polycrystalline perovskite wafers, heralding a leap forward in X-ray detection performance. [ABSTRACT FROM AUTHOR]

Organic polymers are light weight, low toxic and environmentally stable candidates of interest in X-ray detection application. But low attenuation and high recombination rate of charge carriers cause low sensitivity is major limitation of these detectors. In this work, organic polymers (PS/PMMA) composites were prepared with high-Z inorganic BiI 3 by simple dry mixing technique. The organic-inorganic hybrid further embedded with conductive carbon filler (MWCNT, CB, GP) to improve the charge collection of the samples. Resistivity and mobility of the samples were studied with help of Hall measurements and mobility-lifetime was calculated by Hecth equation and found (2.1 ± 0.2) × 10−3 cm2V−1. The elemental analysis of the samples had been done by XPS analysis. The X-ray investigations done by using dental X-ray source and the sensitivity of the samples increases from 3.4 to 200 μGy−1 cm−3 by incorporating CB filler with a low leakage current of order of 33.3 pA/cm2. • The composite exhibits a high SNR of 192 with low noise equivalent dose of 1.9 nGy−1 Hz−0.5 • The sensitivity has been increased by 100-fold for hybrid after embedding carbon filler at a low bias of 32V. • A novel solvent free technique to synthesis organic-inorganic hybrid has been used. • The prepared polymer composite has low leakage current density (3.33 pA/cm2) at low bias compared to α-selenium (10 pA/mm2). [ABSTRACT FROM AUTHOR]

The Low Gain Avalanche Detector (LGAD) is a promising technology for soft X-ray imaging at the next generation light sources as well as for particle tracking applications in high energy physics experiments. However, the lack of a thin entrance window is a limiting factor for deploying LGADs in some applications. In order to exploit the unique scientific imaging opportunities at the new XFELs, finely segmented detectors that can detect soft X-rays with energies as low as 30 eV are needed. The sensors must be able to provide an internal gain of ∼10 to amplify the generated small signal to be above the noise floor of the readout electronics and must have an extremely shallow entrance window to allow the absorption of soft X-rays in the active volume of the sensor. In 2020, we proposed a novel thin entrance window LGAD device concept. We have now produced the first wafer run. We will describe the design and simulation of the new device, as well as test results. Bench test measurements on single-pixel test structures show gain of 7 for shallow absorption. [ABSTRACT FROM AUTHOR]

A simple method of in-situ growth using anodized aluminum oxide templates is used to prepare a high-resolution pixelated scintillator array Cs 5 Cu 3 Cl 6 I 2 with enhanced light direction limitation for X-ray imaging, The Cs 5 Cu 3 Cl 6 I 2 @AAO film performs excellent stability under long-term X-ray irradiation, making it a reliable option for cost-effective pixelated indirect X-ray imaging. [Display omitted] • A perovskite array scintillation film Cs 5 Cu 3 Cl 6 I 2 @AAO via an in-situ growth strategy was fabricated. • A spatial resolution of approximately 20 lp mm−1 and a detection limit of 0.152 μGy·s−1 were achieved. • Excellent stability under long-term X-ray irradiation of Cs 5 Cu 3 Cl 6 I 2 @AAO was studied. Lead-free halide perovskites have shown promising application for indirect X-ray detection as fascinating scintillator. The fabrication of pixelated scintillator films leveraging directional confinement allows high-resolution imaging, yet process complexity and the potential crystal structure damage pose challenges that compromises the corresponding scintillator performance. In this work, a facile in-situ strategy for growing scintillation perovskite of Cs 5 Cu 3 Cl 6 I 2 within anodic aluminum oxide (AAO) membrane is developed as scintillator Cs 5 Cu 3 Cl 6 I 2 @AAO film. The as-fabricated pixelated scintillator array with an enhanced light directional confinement for high-resolution X-ray imaging is demonstrated. The corresponding film achieves a spatial resolution of approximately 20 lp mm−1 and a detection limit of 0.152 Gy·s−1. Moreover, the Cs 5 Cu 3 Cl 6 I 2 @AAO film performs excellent stability under long-term X-ray irradiation, making it a reliable option for cost-effective pixelated indirect X-ray imaging. [ABSTRACT FROM AUTHOR]

The perovskite scintillators have been extensively studied recently for their merits of tunable emission spectra and simple preparation processes. However, the practical applications of perovskite scintillator-based X-ray image sensor are still impeded by inadequate radioluminescence, poor environmental stability, and low imaging resolution. Herein, we demonstrate a scalable co-firing method to fabricate high-quality lead-free Cs 3 Cu 2 I 5 perovskite scintillator and an Indium (In)-doping strategy is introduced to enhance its radioluminescence performance at the same time. The In-doped Cs 3 Cu 2 I 5 obtains a high PLQY of 77.9% and a relative light output of 53372 ph/MeV, which are 0.34 and 1.08 times higher than those of the undoped counterpart, respectively. The X-ray detection limit of the In:Cs 3 Cu 2 I 5 can reach 150.55 nGy air /s, 36.53 times lower than the requirement for X-ray medical diagnosis. The synthesized scintillator also shows superior stability under continuous high dose X-ray irradiation of 6800 μGy air /s for 120 minutes, maintaining 95% of its initial radioluminescence intensity. Furthermore, a large-area (300 cm2) flexible perovskite scintillator film is prepared, which owns a much competitive resolution of 10 lp/mm and less distortion in X-ray imaging. This work provides a practical path for the wide application of perovskite scintillator in the field of X-ray detection and imaging in near future. [Display omitted] • A co-firing method for lead-free indium doped Cs 3 Cu 2 I 5 perovskite scintillators has been proposed. • The indium doped Cs 3 Cu 2 I 5 shows superior environmental and radiation stability. • A large-area flexible scintillator film is prepared for high-resolution imaging. [ABSTRACT FROM AUTHOR]

[Display omitted] • MAPbBr 3 NCs are in-situ space-confined encapsulated in metal–organic frameworks. • bMOF⊃MAPbBr 3 realizes room-temperature scintillation and exceptional X-ray imaging. • bMOF⊃MAPbBr 3 shows enhanced stability against various stimuli and X-rays. • The role of the MOF and the mechanism of improved performance are elucidated. The development of perovskite nanocrystals (NCs) based composites with enhanced stability and exceptional photoelectric properties is of great significance for their application in scintillators for X-ray imaging, but it remains challenging. Herein, we demonstrate a novel and stable scintillator, achieved through a host–guest strategy involving the confinement of perovskite NCs, e.g., MAPbBr 3 NCs, in metal–organic frameworks (MOFs). The host MOF, bio-MOF-100 (denoted as bMOF), facilitates the in-situ space-confined formation of MAPbBr 3 NCs while providing quantum confinement, surface passivation, and protection to these guests. This host–guest strategy results in high exciton binding energy, bright and efficient luminescence, and significantly enhancing their stability against various factors such as air, heat, UV, solvents and X-ray irradiation. Consequently, this advancement prompts the transition of their application scenarios from the colloidal state to the solid state. The bMOF⊃MAPbBr 3 scintillator exhibits a linear response to X-ray with a detection limit determined to be 170 nGy air s−1. Moreover, the bMOF⊃MAPbBr 3 –PMMA scintillator screen demonstrates high-quality X-ray imaging with an impressive spatial resolution of 14.7 lp mm−1. This work provides a new avenue for the development of perovskite NCs-based host–guest composites and paves the way for the broader implementation in solid-state optoelectronic applications. [ABSTRACT FROM AUTHOR]

The silicon-on-insulator pixel (SOIPIX) detector is a unique monolithic-structure imaging device currently being developed by the SOIPIX group led by the High Energy Accelerator Research Organization (KEK). The detector team at KEK Photon Factory (PF) is also developing an X-ray camera using INTPIX4NA with a 14.1 × 8.7 mm2 sensitive area and 425,984 (832 column × 512 row matrix) pixels, with a pixel size of 17 × 17 µm2. The detector has high resolution and sensitivity for low-intensity X-rays, making it suitable for imaging in optical systems with lower X-ray intensities, such as an X-ray zooming microscope using two Fresnel zone plates (FZPs), which is also under development at PF. To enable imaging under such conditions, we developed a detector cooling system using a Peltier element to support longer exposure time (0.5 s per frame). Additionally, we developed a new readout system using DAQ boards developed by PF, equipped with SiTCP-XG (network controller implemented on field-programmable gate array) that supports 10 Gbps Ethernet for high-frame-rate imaging at several hundred hertz. The new X-ray camera was tested at the PF BL-14A, BL-14B, and AR-NE1A experimental stations, and the resolution and sensitivity characteristics were confirmed. Given these confirmed characteristics, this X-ray camera is suitable for X-ray imaging using 5–20 keV X-rays under low-intensity, low-contrast conditions. These conditions are ideal for capturing soft tissues with poor contrast, objects with fine structures, and specimens vulnerable to radiation damage. • SOIPIX INTPIX4NA detector based X-ray camera was developed at KEK Photon Factory. • INTPIX4NA detector has a 14.1 × 8.7 mm2 sensitive area (17 μ m pitch 832 × 512 pixel matrix). • This is suit for imaging with 5–20 keV X-ray under low-intensity/contrast conditions. • 10GbE DAQ system and Peltier based detector cooling system were also developed. • The resolution and sensitivity characteristics were tested/confirmed at KEK PF. [ABSTRACT FROM AUTHOR]

With the extensive application of object detection in intelligent security, the demand for detecting prohibited items in X-ray images has become increasingly stringent. Unlike natural images, X-ray images present unique challenges such as complex backgrounds and mutual occlusion between prohibited and normal items. Consequently, applying traditional detection methods to X-ray images remains a significant challenge. To tackle these challenges, we have developed a unique frequency-aware dual-stream transformers (FDTNet) that is specifically designed for analyzing X-ray images. The FDTNet consists of two streams: one handles the original image, while the other deals with an image that has been enhanced with frequency domain features. In order to achieve precise detection of prohibited items, we introduce a frequency-aware module (FAM) that enhances the representation of prohibited items by utilizing information from the frequency domain. This FAM can be easily integrated into other backbones or detectors as it is a plug-and-play module. Additionally, to enhance the fusion of feature maps from both streams, we utilize a global and channel attention module (GCA) that aggregates texture representations for spatial feature streams. Our evaluation of the proposed FDTNet on the OPIXray datasets and PIDray datasets demonstrates that our detection mAP achieves 88.02 and 68.2, respectively. Extensive experiments conducted on publicly available datasets provide substantial evidence that our proposed network significantly improves the detection of prohibited items compared to state-of-the-art methods. [Display omitted] • The dual-stream design is used to extract RGB features and frequency features respectively • Global and channel attention module enhances the features generated by the RGB stream using attention mechanisms. • Frequency-aware module encodes frequency features, enabling better capture frequency information. [ABSTRACT FROM AUTHOR]

Landmark detection using X-ray imaging is vital for disease screening, treatment, and prognosis. It provides a framework for subsequent tasks, including segmentation, classification, and target detection. Existing landmark detection methods exhibit limits with the increasing number of X-ray examiners. Not only they serve specific data types, but also their ability to learn the complete semantic information from this dataset is limited, potentially affecting their widespread adoption. We address these challenges by proposing a universal landmark detection model for multidomain X-ray imaging, UniverDetect. By progressively acquiring local semantic information, global semantic insights, and anatomical structure knowledge at various levels, the model ensured that the detected landmarks were closely aligned with the ground-truth labels. UniverDetect consists of three key components. The landmark detection module (LDM) utilizes a U-net network equipped with our innovative pyramid depthwise separable (PDS) convolution module for initial landmark detection. The landmark refinement module (LRM) integrates a fine-tuning module comprising continuously extended convolution blocks. Finally, the landmark correction module (LCM) incorporates a graph convolutional network (GCN) to rectify offset errors during partial landmark detection. An inherent feature of this model is its domain- generalization capability, which enables continuous learning across diverse domains. This model can concurrently learn from eight domains, covering 118 landmarks within a diverse dataset of 5969 images. Extensive experiments on multiple datasets demonstrate that this method consistently outperforms state-of-the-art approaches. This study presents a versatile and effective solution to reduce doctors' workload while providing precise quantitative analysis. [ABSTRACT FROM AUTHOR]

The backscatter X-ray system makes an image by detecting scattered particles from an object in the opposite direction by Compton scattering. This system has the advantage of detecting drugs or explosives composed of organic substances. In this study, we developed a backscatter X-ray detection system. The 6-ch DAQ system is able to store acquired data for 50 μs as 8 bytes and the 6-ch high voltage power supply board provides adjustable power from 0 to 1600 V. Using this detection system, we varied the tube voltage from 80 to 160 kV and observed backscatter X-ray images of two plastic phantoms at 160 kV. The results indicate a need to optimize the speed of the collimator and data acquisition time of the DAQ system to improve image quality. The backscatter X-ray imaging technology exhibits high scalability, making it applicable not only to security screening but also for medical and industrial purposes. [ABSTRACT FROM AUTHOR]

• Liquid epitaxy boosts δ-CsPbI 3 's one-dimensional growth, enhancing carrier transition. • Sensitivity reaches 1768.46 μC Gy air -1 cm−2 at 432 V mm−1, outperforming α-Se and single crystalline δ-CsPbI 3 detectors. • Retains 91.34 % sensitivity after 7 days in air, showcasing impressive long-term stability. • Successful integration with a thin-film transistor array for 8-bit imaging in a 64 × 64 matrix. • Opens the door for commercial high-performance direct X-ray detectors, solving the "absorption vs. transportation" issue. An ideal direct X-ray detector should convert a low dose of X-ray photons into large quantity of electrical signals, coupled with sustained long-term stability. Nevertheless, a notable conflict arises between X-ray absorption efficiency and carrier transport in thick polycrystalline perovskite films. Moreover, conventional perovskite materials exhibit inherent challenges regarding the stability of their crystal phase and the consistency of the photocurrent. To circumvent these limitations, a polycrystalline perovskite thick film is proposed using orthorhombic CsPbI 3 (δ-CsPbI 3) as a highly stable active material. Combined with the liquid epitaxy process, δ-CsPbI 3 prefers one-dimensional growth along the carrier transportation direction, which suppresses the formation of grain boundaries, enabling high carrier mobility while maintaining X-ray absorption for a thick polycrystalline film. Consequently, the polycrystalline δ-CsPbI 3 based detector exhibits a highest sensitivity of 1768.46 μC Gy air -1 cm−2 at an electric field of 432 V mm−1 which is 88.42-fold higher than α-Se based detectors and 190-fold higher than the single crystalline δ-CsPbI 3 based detector, respectively. The sensitivity maintains 91.34 % of its initial state after 7 days exposure in the air. Combing with a thin-film transistor array, the detector achieves 8-bit imaging within a 64 × 64 matrix. This work provides a feasible method for commercialized production of high-performance direct X-ray detectors. [ABSTRACT FROM AUTHOR]

The Aluminium Conductor Composite Core (ACCC) is a critical component of power transmission that needs automated nondestructive defect detection to prevent wire breaking accidents and ensure regular city operations. Unfortunately, the current supervised target detection scheme is limited in its generalization ability due to the diversity of defect morphology and the high cost of acquiring samples. To overcome these challenges, we propose an automatic defect detection method based on a modified Skip-GANomaly model using X-ray images of ACCC wires as input. We experiment with semi-supervised deep learning reconstruction methods to mitigate the lack of abnormal samples and improve the generalization ability of unknown defects. We also explore hierarchical reconstruction and Skip-Connection adjustment to enhance the reconstruction effect and defect identification based on Resnet50. The results show that our method can achieve high accuracy, recall, and precision levels of over 99 %, significantly highlighting the difference in defect morphology. Compared to existing supervised schemes, our Defect Detection Scheme with Hierarchical Reconstruction and Anomaly-Subtracted Image Discrimination (DHRAD) eliminates dependence on the number of abnormal samples and the diversity of defect types in the training set, and has the ability to detect defects with unknown morphology. Therefore, DHRAD provides an effective detection scheme for automatic nondestructive defect detection of ACCC in operation, based on computer vision and semi-supervised learning. [ABSTRACT FROM AUTHOR]

Automatic and rapid screening of COVID-19 from the radiological (X-ray or CT scan) images has become an urgent need in the current pandemic situation of SARS-CoV-2 worldwide. However, accurate and reliable screening of patients is challenging due to the discrepancy between the radiological images of COVID-19 and other viral pneumonia. So, in this paper, we design a new stacked convolutional neural network model for the automatic diagnosis of COVID-19 disease from the chest X-ray and CT images. In the proposed approach, different sub-models have been obtained from the VGG19 and the Xception models during the training. Thereafter, obtained sub-models are stacked together using softmax classifier. The proposed stacked CNN model combines the discriminating power of the different CNN's sub-models and detects COVID-19 from the radiological images. In addition, we collect CT images to build a CT image dataset and also generate an X-ray images dataset by combining X-ray images from the three publicly available data repositories. The proposed stacked CNN model achieves a sensitivity of 97.62% for the multi-class classification of X-ray images into COVID-19, Normal and Pneumonia Classes and 98.31% sensitivity for binary classification of CT images into COVID-19 and no-Finding classes. Our proposed approach shows superiority over the existing methods for the detection of the COVID-19 cases from the X-ray radiological images. [ABSTRACT FROM AUTHOR]

• We analyze testing protocols used for Covid-19 detection used in the literature. • We successfully classify COVID images whose lungs areas are turned to black. • We try using different datasets for training and testing. • We show that many highly cited paper on this topic use biased testing protocols. In this paper, we compare and evaluate different testing protocols used for automatic COVID-19 diagnosis from X-Ray images in the recent literature. We show that similar results can be obtained using X-Ray images that do not contain most of the lungs. We are able to remove the lungs from the images by turning to black the center of the X-Ray scan and training our classifiers only on the outer part of the images. Hence, we deduce that several testing protocols for the recognition are not fair and that the neural networks are learning patterns in the dataset that are not correlated to the presence of COVID-19. Finally, we show that creating a fair testing protocol is a challenging task, and we provide a method to measure how fair a specific testing protocol is. In the future research we suggest to check the fairness of a testing protocol using our tools and we encourage researchers to look for better techniques than the ones that we propose. [ABSTRACT FROM AUTHOR]

Thanks to the low melting point of hybrid glass, (ETP) 2 MnBr 4 namely, scintillators of arbitrary shapes were synthesized in a flexible silicon mold at low temperature (ca. 180 ℃), representing a new route to a transparent bulk of highly luminescence. [Display omitted] • The (ETP) 2 MnBr 4 glass was synthesized at a low temperature down to 180 ℃. • The luminescent glass exhibited a high transparency over 85% and a nearly-unity PL QY. • The internal crystallization of the hybrid glass was effectively driven by a mild annealing process at 60 ℃. • The low melting point of glass enabled the use of silicone molds for varied shapes, such as slide, monolith, and rod. • The ensuing scintillating screen for X-ray imaging achieved a high spatial resolution (26.8 lp/mm). In contrast to all-inorganic scintillators, organic–inorganic hybrid glass of low melting-point has many advantages in fabricating bulky and transparent scintillator at low temperature. Here, the (ETP) 2 MnBr 4 (ETPBr = ethyltriphenylphosphonium bromide) glass was successfully synthesized at 180 ℃, which exhibited a high transparency over 85 % (ranging from 500 to 800 nm) and a nearly-unity photoluminescence quantum yield. A mild annealing process at 60 ℃ was found effective to drive the interior crystallization of hybrid glass, which was only achievable at several hundred degrees for inorganic glass. The interior crystallization significantly improved the luminescence intensity at the expense of optical transparency. Importantly, based on the low melting point of (ETP) 2 MnBr 4 glass, flexible silicone molds were used as container to obtain a variety of scintillators of arbitrary sizes and shapes, such as alphabet, slide, monolith, and rod. The (ETP) 2 MnBr 4 glass was used as scintillating screen in X-ray detection and imaging, demonstrating a high light yield (66000 photons/MeV of annealed glass) and a high spatial resolution (26.8 lp/mm of transparent glass), respectively. This work not only refined the synthesis process of bulk scintillator, but also opened many avenues in luminescent volumetric display and three-dimensional imaging. [ABSTRACT FROM AUTHOR]

[Display omitted] • BN nanosheets act as a barrier, inhibiting ion migration within perovskite layers. • BN also improved charge transport and carrier mobility. • Perovskite photodiodes incorporated with BN exhibit exceptional X-ray stability. Metal halide perovskites have been widely used in optoelectronic applications due to their excellent optoelectronic properties. However, ensuring their stability during operation remains a significant challenge. In this study, we investigated the charge carrier dynamics of perovskite films and devices, comparing those with and without the insertion of boron nitride on the grain boundaries. It was revealed that the charge transport and stability could be significantly enhanced with the present of boron nitride nanosheets on the grain boundaries. The incorporation of boron nitride led to a substantial improvement in charge carrier mobility and lifetime, without any noticeable changes in phase segregation or photostability. Moreover, the perovskite detectors incorporating boron nitride exhibited suppressed ion migration and dark current, while demonstrating an enhanced photoresponse and radiation exposure capability. These findings indicate that the addition of insulating boron nitride nanosheets acts as a stabilizer, enhancing the stability of both the perovskite thin films and the devices. Additionally, the incorporation of boron nitride significantly improved the device performance benefiting from the enhanced charge transport, indicating that the boron nitride nanosheets enhanced perovskite photodiodes possess great potential for X-ray detection and imaging. [ABSTRACT FROM AUTHOR]

Waste management plays an important role in environmental protection and resource recycling. In fact, traditional waste recycling requires a large number of workers to sort manually, which is not only labor-intensive and time-consuming, but also increases the health risk for workers. To further improve the efficiency of waste detection and classification, related scholars have used computer vision technology to achieve automatic waste management. However, existing methods tend to use RGB images as input, requiring workers to open waste bags and disperse waste items in advance. To avoid comprehensive preparation procedures and identify occluded waste items, we use deep learning models to detect and recognize waste items in X-ray images. Compared to RGB images, X-ray images can effectively preserve boundary information and reflect material types. To take advantage of the inherent characteristics of X-ray images, we propose a novel X-ray Characteristic Enhancement Module (XCEM) to improve the performance of X-ray waste detection. XCEM consists of three sub-modules, namely Hybrid Interaction Module (HIM), Multi-scale Material Perception Module (MMPM), and Boundary Guidance Module (BGM). Specifically, HIM not only generates soft and hard boundary maps, but also achieves information interaction and feature enhancement of different boundary maps. Meanwhile, MMPM can effectively capture different multi-scale material features. In addition, BGM uses auxiliary boundary information and attention mechanisms to effectively enhance critical material features. As a plug-and-play module, XCEM can be readily inserted into the most popular detection pipelines. We select several representative one-stage and two-stage methods and perform related experiments on the WIXRay dataset. Experimental results show that our method can achieve consistent performance gains on diverse detection paradigms. This study promotes the development of intelligent waste inspection and recycling. • An efficient solution based on X-ray images for waste detection and classification. • The proposed XCEM can make use of the inherent characteristics of X-ray images. • The XCEM can achieve consistent performance gains on diverse detection models. • Several representative methods are explored for waste detection in X-ray images. • Using computer vision and deep learning can achieve automatic waste management. [ABSTRACT FROM AUTHOR]

As for the characteristics of the objects in the airtight package in the X-ray image, some prohibited items of the airtight package are difficult to be detected from the X-ray images with complex and overlapped backgrounds. In this article, the cooperative knowledge distillation method is used to enhance the prohibited items detection model in the X-ray image. To efficiently implement hard example mining, this article designs an Multi-task Classification Head (MCH) for teachers to provide prior knowledge of image-level and instance-level predictions. Different from the distillation method in which the students imitate the teacher, the algorithm in this article is implemented by the cooperation between teacher and student. In order to verify the effectiveness of this algorithm, a series of related experiments are carried out on PIDray and SIXray respectively. Experiments show that the algorithm improves the AP of State-of-the-Art dense object detectors (e.g., RetinaNet, ATSS, GFL, and TOOD) in SIXray by 1% ∼ 2%. Especially for prohibited items that are difficult to be found in X-ray images, the algorithm is more effective, and the dense object detectors can achieve a performance improvement of about AP of 2% on the Hidden subset of PIDray. The experiments demonstrate that the cooperative knowledge distillation algorithm proposed in this article can effectively enhance the performance of prohibited items detection, particularly showing more pronounced improvements in detecting hard examples. [ABSTRACT FROM AUTHOR]

X-ray detection has been extensively applied in various fields including medical imaging, security detection, and industrial non-destructive testing. Recently, organic-metal halide perovskites (OMHP) are being under the spotlight of the academia in X-ray detection and imaging, owing to their outstanding photoelectric properties such as high photoluminescence quantum yield, large X-ray attenuation coefficient, high carrier mobility-lifetime (μτ) product and high defect-tolerant nature as well as low-cost raw materials and facile preparation technology. The reported perovskite X-ray detectors have displayed superb sensitivity and high-spatial-resolution X-ray imaging, promisingly challenging the traditional commercial X-ray detectors based on Si, α -Se or CsI:TI. Inspired by these exciting results, we summarize the recent progress of OMHP X-ray detectors. At first, we briefly introduce the working mechanism of indirect/direct X-ray detectors and the corresponding device structure, followed by a detailed discussion of the performance parameters of X-ray detectors. Then, we further demonstrate the achievements of OMHP in X-ray detection and imaging in terms of device type, perovskite composition, film species, fabrication technique, and optimized strategies, where the interplay between perovskite constituent/type, preparation technology and device performance are strongly emphasized. Finally, the challenges and prospects of OMHP-based X-ray detectors for the future development toward the commercialized application are proposed. [Display omitted] • The working mechanism of indirect/direct X-ray detectors and the corresponding device performance parameters are discussed. • The achievements of perovskite in X-ray detection and imaging are demonstrated. • The challenges and prospects of perovskite-based X-ray detectors for the future development are proposed. [ABSTRACT FROM AUTHOR]

Silicon carbide fibre/silicon carbide (SiC f /SiC) composites are important for manufacturing the hot-section components of aero engines and supersonic vehicles. Hence, quality control, as well as qualitative and quantitative non-destructive testing and evaluation (NDT&E) are critical. A grey (G) value method for the characterisation and NDT&E of manufacturing defects in SiC f /SiC composites based on the attenuation behaviour of low-energy X-rays was proposed, and a digital X-ray imaging detection system was developed. Specimens with artificial and manufacturing defects were evaluated, thereby revealing that imperfections were induced when the SiC f /SiC composites were formed at the high-temperatures; microcracks (100-μm-wide) and rectangular defects (0.1-mm-deep) were detected with a sensitivity exceeding 100 μm. Our results demonstrated that 'voids', 'microcracks', 'porosity', 'polymer impregnation inhomogeneity', 'fibre-lack', and 'gap-delamination' were the typical manufacturing defects caused during formation of SiC f /SiC composites at high temperatures; the minimum deviation between the detected and designed length of a 10-mm-long microcrack in the 3.0-mm-thick SiC f /SiC composite specimen was ~3%; the manufacturing defects were effectively characterised and evaluated using the distribution behaviours of G values and digital radiographic imaging features. Image 1 [ABSTRACT FROM AUTHOR]

State-of-the art X-ray imaging cameras using silicon sensors for X-ray detection have demonstrated a frame-rate of 10 MHz and excellent performance for X-ray energies below 20 keV. We proposed a pixelated ultrafast inorganic scintillator-based front imager for GHz hard X-ray imaging. The proposed imager is featured with a total absorption for hard X-ray photons, and provides sub-ns scintillation pulse width crucial for X-ray bunches of a few ns spacing foreseen at the proposed MaRIE facility. We measured temporal response of a dozen ultrafast and fast inorganic scintillators at the 10-ID-B site of the Advanced Photon Source (APS) of ANL. Crystal's response to hybrid X-ray beam of 30 keV, consisting of singlet bunches of 50 ps width and septuplet bunches of 27 ps width with 2.83 ns bunch spacing, was measured. Ultrafast inorganic scintillators, such as BaF 2 :Y and ZnO:Ga, show clearly resolved X-ray bunches for septuplets, as well as no degradation of amplitude for continuous eight septuplets, providing a proof of principle for the ultrafast inorganic scintillator-based total absorption front imager for the proposed MaRIE project. [ABSTRACT FROM AUTHOR]

Lead halide perovskites with excellent optoelectronic properties have attracted extensive attention and made amazing progress for X-ray detectors and imaging. However, lead is highly toxic to humans, animals and ecosystems, posing a great safety concern to its commercial application. It has become an urgent need to develop stable and environment-friendly lead-free alternatives. In this review, we summarize recent progress in lead-free halide perovskites (LFHPs) and derivatives toward X-ray detectors and imaging. First, we introduce the working principle of X-ray detectors and the key figure of merit in direct and indirect detection processes. In addition, we summarize state-of-the-art lead-free halide perovskites preparation methods. Furthermore, we comprehensively discuss the structural dimensions, optoelectronic properties of lead-free halide perovskites and their recent advances in X-ray detection and imaging. Meanwhile, the stabilities of LFHPs-based X-ray detectors are discussed. Finally, we outline several main issues of state-of-the-art LFHPs-based X-ray detectors and provide prospects to overcome these limitations. [ABSTRACT FROM AUTHOR]

Extraction of various structures from the chest X-ray (CXR) images and abnormalities classification are often performed as an initial step in computer-aided diagnosis/detection (CAD) systems. The shape and size of lungs may hold clues to serious diseases such as pneumothorax, pneumoconiosis and even emphysema. With the growing number of patients, the doctors overwork and cannot counsel and take care of all their patients. Thus, radiologists need a CAD system supporting boundary CXR images detection and image classification. This paper presents our automated approach for lung boundary detection and CXR classification in conventional poster anterior chest radiographs. We extract the lung regions, sizes of regions, and shape irregularities with segmentation techniques that are used in image processing on chest radiographs. From CXR image we extract 18 features using the gray level co-occurrence matrix (GLCM). It allows us to classify the CXR image as normal or abnormal using the probabilistic neural network (PNN) classifier. The proposed method has competitive results with comparatively shorter training time and better accuracy. [ABSTRACT FROM AUTHOR]

The rising requirement for radiation detection materials for practical applications has inspired to burgeoning investigation of scintillator materials. High performance X-ray detection require high spatial resolution and long-term stability, particularly for targeted objects at extreme conditions. Here, the CaF 2 :Eu2+ glass ceramic (GC), in which the CaF 2 :Eu2+ nanoparticles are wrapped by the glassy matrix, is successfully obtained the melting method. The as-obtained CaF 2 :Eu2+ GC manifests bright blue radioluminescence (RL) emission peaked at 470 nm thanks to the effective 5d-4f transition of Eu2+ ions. In addition, the as-obtained CaF 2 :Eu2+ GC presents high transmittance of 84.2% and visible light, contributing an excellent spatial resolution of 15 lp/mm at room temperature. Importantly, the as-obtained CaF 2 :Eu2+ GC exhibits high robustness at water conditions and high thermal stability with X-ray resolution of 12.1 lp/mm at 473 K. Our work demonstrates that CaF 2 :Eu2+ GC scintillators provide an excellent visualization tool for high-resolution scintillators X-ray images in harsh conditions. • The reduction efficiency of Eu2+ is significantly improved by mixing the reducing agent with glass ceramic raw and sintering. • The CaF 2 :Eu2+ glass ceramic is successfully obtained by melt-quenching method. • Multiple characterization prove that Eu2+, the luminescent center of glass ceramic, is greatly reduced in glass ceramic. • The strategy significantly reduces the light scattering and enhance the stability of the emitting centers. • The CaF 2 :Eu2+ glass ceramic for high resolution X-ray detection in harsh conditions. [ABSTRACT FROM AUTHOR]

[Display omitted] • Scintillator screen with micro/nano particles embedded into delignified wood. • Vertical column structured material suppressing the light lateral spreading. • Linear relationship between light yield and X-ray dose rate. • High spatial resolution X-ray imaging achieved. Nanocrystalline scintillators with low-cost, fast response, and high light yield are widely used for X-ray imaging. However, they fail in high-energy X-ray imaging because of the fundamental limitations due to lateral radiation spreading in thicker device-compatible active layers. This issue is resolved by using the novel nanocomposite containing CsPbBr 3 scintillation single-microcrystalites embedded into transparent, natural wood-derived light-guiding fibrous structures. The CsPbBr 3 crystals convert X-ray to visible photons with a high photoluminescence quantum efficiency (76 %), and an average fast photoluminescence decay time of 25.9 ns. The delignified wood-derived fiber-like lumina effectively guide light, while suppressing the lateral spreading of scintillation photons. This unique porous nanocomposite material offers an excellent X-ray detection performance, and linear response in a wide parameter range. The developed scintillator screen achieves well-resolved, high-contrast X-ray imaging, featuring a very high spatial resolution of 11.9 lp/mm at a modulation transfer function of 0.2, thus exceeding the benchmark industry standards and offering a new advanced materials platform for radiation detection and dosimetry applications. [ABSTRACT FROM AUTHOR]

• A light weight CORONA-NET for diagnosing COVID-19 from chest X-ray images. • Deep feature extraction is performed by CNN, reduced yet strengthened by DWT. • The dataset included 3000 X-rays obtained locally through hospital in Denmark. • The method achieves excellent performance in comparison with the existing methods. • The proposed system has a 99.56 percent accuracy and 99.667 percent specificity. Since December 2019, COVID-19 has posed the most serious threat to living beings. With the advancement of vaccination programs around the globe, the need to quickly diagnose COVID-19 in general with little logistics is fore important. As a consequence, the fastest diagnostic option to stop COVID-19 from spreading, especially among senior patients, should be the development of an automated detection system. This study aims to provide a lightweight deep learning method that incorporates a convolutional neural network (CNN), discrete wavelet transform (DWT), and a long short-term memory (LSTM), called CORONA-NET for diagnosing COVID-19 from chest X-ray images. In this system, deep feature extraction is performed by CNN, the feature vector is reduced yet strengthened by DWT, and the extracted feature is detected by LSTM for prediction. The dataset included 3000 X-rays, 1000 of which were COVID-19 obtained locally. Within minutes of the test, the proposed test platform's prototype can accurately detect COVID-19 patients. The proposed method achieves state-of-the-art performance in comparison with the existing deep learning methods. We hope that the suggested method will hasten clinical diagnosis and may be used for patients in remote areas where clinical labs are not easily accessible due to a lack of resources, location, or other factors. [ABSTRACT FROM AUTHOR]

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the malposition based on position detection of CVC tip via X-ray images. To reduce the workload of the clinicians and the percentage of malposition occurrence, we propose an automatic catheter tip detection framework based on a convolutional neural network (CNN). The proposed framework contains three essential components which are modified HRNet, segmentation supervision module, and deconvolution module. The modified HRNet can retain high-resolution features from start to end, ensuring the maintenance of precise information from the X-ray images. The segmentation supervision module can alleviate the presence of other line-like structures such as the skeleton as well as other tubes and catheters used for treatment. In addition, the deconvolution module can further increase the feature resolution on the top of the highest-resolution feature maps in the modified HRNet to get a higher-resolution heatmap of the catheter tip. A public CVC Dataset is utilized to evaluate the performance of the proposed framework. The results show that the proposed algorithm offering a mean Pixel Error of 4.11 outperforms three comparative methods (Ma's method, SRPE method, and LCM method). It is demonstrated to be a promising solution to precisely detect the tip position of the catheter in X-ray images. • An automatic catheter tip detection framework based on X-ray images is proposed. • The high-resolution features are maintained from start to end for tip detection. • The intermediate outputs show the catheter and the potential positions for the tip. • The framework shows the potential of machine Explainability. [ABSTRACT FROM AUTHOR]

• In this research, we introduced a novel TB-UNet based on dilated fusion block (DF) and Attention gate (AG) mechanism for accurate segmentation of lung regions. • We also proposed TB-DenseNet, which is based on five dual convolution blocks, DenseNet-169 layer, and a feature fusion block for the precise classification of tuberculosis images. • The experiments have been performed on three chest X-ray (CXR) datasets, segmented images, and original images are fed to TB-DenseNet for better classification. Tuberculosis still significantly impacts the world's population, with more than 10 million people getting sick each year. Researchers have focused on developing computer-aided diagnosis (CAD) technology based on X-ray imaging to support the identification of tuberculosis, and deep learning is a popular and efficient method. However, deep learning-based CAD approaches usually ignore the relationship between the two vision tasks of specific region segmentation and classification. In this research, we introduced a novel TB-UNet, which is based on dilated fusion block (DF) and Attention block (AB) block for accurate segmentation of lungs regions and achieved the highest results in terms of Precision (0.9574), Recall (0.9512), and F1score (0.8988), IoU (0.8168) and Accuracy (0.9770). We also proposed TB-DenseNet which is based on five dual convolution blocks, DenseNet-169 layer, and a feature fusion block for the precise classification of tuberculosis images. The experiments have been performed on three chest X-ray (CXR) datasets, segmented images, and original images are fed to TB-DenseNet for better classification. Furthermore, the proposed method is tested against simultaneously three different diseases, such as Pneumonia, COVID-19, and Tuberculous. The highest results are achieved in terms of Precision (0.9567), Recall (0.9510), F1score (0.9538), and Accuracy (0.9510). The achieved results reflect that our proposed method produces the highest accuracy compared to the state-of-the-art methods. The source code is available at: https://github.com/ahmedeqbal/TB-DenseNet. [ABSTRACT FROM AUTHOR]

The present project will adopt the principle and technology of X-ray imaging to quickly measure the mass thickness (wherein the mass thickness of the item =density of the item × thickness of the item) of the irradiated items and thus to determine whether the packaging size and inside location of the item will meet the requirements for treating thickness upon electron beam irradiation processing. The development of algorithm of X-ray mass thickness detector as well as the prediction of dose distribution have been completed. The development of the algorithm was based on the X-ray attenuation. 4 standard modules, Al sheet, Al ladders, PMMA sheet and PMMA ladders, were selected for the algorithm development. The algorithm was optimized until the error between tested mass thickness and standard mass thickness was less than 5%. Dose distribution of all energy (1–10 MeV) for each mass thickness was obtained using Monte-carlo method and used for the analysis of dose distribution, which provides the information of whether the item will be penetrated or not, as well as the Max. dose, Min. dose and DUR of the whole item. [ABSTRACT FROM AUTHOR]

[Display omitted] • Two semiconductive Ba(II)-based CPs 1 and 2 with small exciton binding energy (E b) values were successfully prepared. • The 2 -based film detector achieves superior direct X-ray detection performance among CP-based detectors. • The enhanced π-π interactions are beneficial to exciton separation and charge carrier transport irradiated by X-ray. High-performance and low-cost X-ray detector is crucial for medical imaging, nondestructive industrial detection and security checks. Semiconductive coordination polymers (CPs) with designable structures, tunable property and high cost-effectiveness have recently emerged as promising materials in direct X-ray detection. However, due to the strong Coulomb interactions between photogenerated electrons and holes, most of CPs often exhibit high exciton binding energies, resulting in relatively insufficient exciton dissociation as well as low photocurrent output and detection sensitivity in turn. Here, we employed the anthracene-based ligand to obtain two semiconductive CPs, {[Ba 2 (Hadba) 4 (DMF) 8 ]·DMF} n 1 (H 2 adba = 4,4′-(9,10-anthracenediyl)dibenzoic acid, DMF = N , N -dimethylformamide) and [Ba(Hadba) 2 (DMA) 4 ] n 2 (DMA = N , N -dimethylacetamide). Both of them can effectively convert X-ray into electrical signals. Compared with compound 1 , compound 2 has a reduced E b (44.9 meV) caused by the reinforced π-π interactions, contributing to the facilitated carrier transport, a significant enhance in mobility-lifetime product (μτ) and detection sensitivity irradiated by X-ray. Based on the optimized detection performance, we prepared a flexible 2 -based composite film detector with a low detection of 1.02 μGy/s that meets the standard for medical imaging. In particular, this film-based detector achieves a high sensitivity of 137.31 μCGy−1 cm−2 and μτ product of 3.03 × 10−3 cm2 V−1, which are superior to all previously reported CP-based detectors and much higher than commercial α -Se. Simultaneously, a 5 × 5 pixelated X-ray imaging device was further constructed to show its potential application in direct X-ray detection and imaging. [ABSTRACT FROM AUTHOR]

Gaseous polarimetry applies in soft X-ray polarization detection, typically like the Gas Pixel detector (GPD) and the micropattern time projection chamber (TPC). The polarization phase angles resolve from photoelectron track trajectories for both of them. The photoelectron track images derived from read-out pixels or strips are the key to determining the performance of the polarimetry. Gaseous X-ray polarimetry is regularly optimized and diagnosed by the Geant4 associated with Garfield++ and finite element analysis software (full simulation). Although the results are more realistic by the full simulation, the sample generation is low efficiency, especially for large gain values of the multiplier stage. The 2-D photoelectron track images regularly generate by a gaussian smear of initial ionization electrons at present. However, discrepancies exist in the modulation curves, resulting in fuzzy diagnoses and optimization of polarimetry. In this study, a fast simulation framework is constructed, the reconstruction of polarization phase angles and energy spectrum of the samples obtained from the fast simulation are consistent with those from experiments and the full simulation, and the deviation of modulation factor is within 2% for both situations of the GPD and TPC. In addition, the fast simulation greatly improves the sample generation efficiency. These results illustrate the fast simulation model is relative accuracy and high efficiency, which provides a useful tool for gaseous X-ray polarimetry. [ABSTRACT FROM AUTHOR]

Semiconductor sensors based on the rad-optic effect enable ultra-fast detection of X-rays and play an important role in fusion diagnostics. Obtaining the responsivity of the semiconductor ultrafast response material is an important part of characterization. In this work, the refractive index change mechanism of the semiconductor under X-ray irradiation was analyzed, and the quantitative relationship between the diffraction efficiency and the X-ray photon energy was established through the LT-AlGaAs diffraction imaging experiments. The impulse responses of LT-AlGaAs under 1 keV–10 keV X-ray radiation were calculated, revealing the variation of responsivity with radiated photon energy. Imaging experiments of LT-AlGaAs were performed by bombarding an Al target to generate 1.5 keV X-rays. The diffraction images were obtained in agreement with the simulations. The responsivity of the semiconductor chip increases with the square of the incident X-ray power density. This study provides meaningful analyses for the development of ultra-fast X-ray imaging systems based on the rad-optic effect. [ABSTRACT FROM AUTHOR]

The application of deep learning to X-ray image classification and recognition has attracted increasing attention in intelligent radiographic testing. In this study, we developed a defect detection method for X-ray images of aeroengine turbine blades using a novel unsupervised adversarial learning strategy. A defect detection model is proposed based on a generative adversarial network (GAN), which consists of a generator network, a discriminator network, and an extra encoder network. Employing an encoder–decoder–encoder subnetwork in the generator network enables the model to map an input image to a low-dimensional encoding vector, which is subsequently used to reconstruct the input image. The extra encoder network mapped the reconstructed image to a new encoding vector. Model training is implemented with non-defective X-ray image samples by minimising the distance between the original input image and the generated image (reconstruction loss) and the encoding vector distance (encoding loss). Defect detection is achieved using a generator network that can reconstruct non-defect samples but cannot reconstruct those with defects well. The effects of input image size, number of encoding nodes, and type of reconstruction loss on the performance of the defect detection model were studied. Consequently, the proposed model with an input image size of 128 × 128, 600 encoding nodes, and L 2 reconstruction loss can achieve a detection accuracy of 0.911. This study proposes a method for developing intelligent radiographic testing techniques for the quality management of aeroengines. [ABSTRACT FROM AUTHOR]

Although biopsy-based necrosis rate is a golden standard for reflecting the sensitivity of bone tumor and guiding postoperative chemotherapy, it requires biopsy which is invasive and time-consuming. In this paper, we develop a new necrosis rate detection method using time series X-ray images instead of biopsy. To overcome the limitations of few-shot samples, the proposed method utilizes a Generative Adversarial Network with Long Short-term Memory to generate time series X-ray images. For further data expansion, an image-to-image translation network is applied for producing the initial images. These augmented data are treated as the training set of a 3D-Convolutional Neural Network classification model. Our method expands the few-shot bone tumor X-rays by 10 times, and approaches the necrotic rate classification result of biopsy, which is the state-of-the-art technique in the detection of few-shot bone tumor necrosis rate. Furthermore, it provides an efficient method to investigate the bone tumor necrosis rate in few-shot samples. • A deep learning method is proposed to detect necrosis rate with few-shot X-rays. • The Conv-LSTM-GAN network in our method is designed to generate bone tumor images. • Our method expands bone tumor images by 10 times and achieves biopsy-like results. [ABSTRACT FROM AUTHOR]

COVID-19 quickly became a global pandemic after only four months of its first detection. It is crucial to detect this disease as soon as possible to decrease its spread. The use of chest X-ray (CXR) images became an effective screening strategy, complementary to the reverse transcription-polymerase chain reaction (RT-PCR). Convolutional neural networks (CNNs) are often used for automatic image classification and they can be very useful in CXR diagnostics. In this paper, 21 different CNN architectures are tested and compared in the task of identifying COVID-19 in CXR images. They were applied to the COVIDx8B dataset, a large COVID-19 dataset with 16,352 CXR images coming from patients of at least 51 countries. Ensembles of CNNs were also employed and they showed better efficacy than individual instances. The best individual CNN instance results were achieved by DenseNet169, with an accuracy of 98.15% and an F1 score of 98.12%. These were further increased to 99.25% and 99.24%, respectively, through an ensemble with five instances of DenseNet169. These results are higher than those obtained in recent works using the same dataset. • This paper compares 21 CNN architectures for COVID-19 detection in CXR images. • DenseNet169 achieved an accuracy of 98.15% and an F1 score of 98.12%. • An ensemble of DenseNet169 instances increased the F1 score to 99.24%. • The training was repeated five times for each model to get more reliable results. [ABSTRACT FROM AUTHOR]

Object detection algorithms based on deep learning have been widely used in the intelligent detection of prohibited items in X-ray images during the security inspection process. However, security inspection is a process that emphasizes timeliness, and the low inference efficiency brought by overly complex deep neural networks is not allowed. In this paper, we propose a lightweight object detection framework based on the YOLOv4 algorithm, named LightRay. Where MobileNetV3 is applied as the feature extraction backbone. To effectively deal with the detection problem of prohibited items with small sizes in complex backgrounds, a feature enhancement network in shallow layers is proposed. Where, the Lightweight Feature Pyramid Network (LFPN) and the Convolutional Block Attention Module (CBAM) effectively achieve feature fusion of different scales, while strengthening the features of small objects. The experimental results show that the mAP of the lightRay model is 87.28% on the SIXray data set, while the FLOPs of the model are reduced to the original 1/5, and Params is reduced to 1/3 of the original. In addition, some ablation experiments confirm the ability of the LightRay model the detection of prohibited items with small sizes. The codes of LightRay are released at https://github.com/zhg-SZPT/LightRay. [ABSTRACT FROM AUTHOR]

Scattered x rays are detrimental to the image quality of x-ray transmission radiography. Anti-scatter grids have been used in diagnostic x-ray imaging to improve the image quality but are not practical to use for megavoltage (MV) x-ray imaging in radiotherapy since a MV grid would be very bulky, heavy, and costly. An inherent anti-scatter detector based on Čerenkov radiation was introduced recently for MV x-ray imaging. The purpose of this work is to investigate experimentally the anti-scatter property of a single pixel prototype detector. The scatter to primary ratio (SPR) has been measured using a linear accelerator with a 6 MV x-ray beam. It has been found that the SPR for the prototype detector is 30–60% less than that of an ionization chamber, depending on the imaging geometry. This indicates the prototype detector is less sensitive to scattered radiation. [ABSTRACT FROM AUTHOR]

X-ray beams propagate across a target object before they are projected onto a regularly spaced array of detectors to produce a routine X-ray image. A 3D attenuation coefficient distribution is obtained by tomographic reconstruction where scattering is usually regarded as a source of parasitic signals which increase the level of electromagnetic noise that is difficult to eliminate. However, the elastically scattered radiation could be a valuable source of information, because it can provide a 3D topology of electron densities and thus contribute significantly to the optical characterization of the scanned object. The scattering and attenuation data form a complementary base for concurrent retrieval of both electron density and attenuation coefficient distributions. In this paper we developed the 3D reconstruction method that combines both data inputs and produces better image resolution compared to traditional technology. [ABSTRACT FROM AUTHOR]

• COVID-19 images were analyzed with a new preprocessing model. • In this study, feature extraction was performed from COVID-19 images according to RGB values. • The proposed model was tested by statistical methods. • The results of both normal data and feature-reduced data were compared. The COVID-19 pandemic spread all over the world, starting in China in late 2019, and significantly affected life in all aspects. As seen in SARS, MERS, COVID-19 outbreaks, coronaviruses pose a great threat to world health. The COVID-19 epidemic, which caused pandemics all over the world, continues to seriously threaten people's lives. Due to the rapid spread of COVID-19, many countries' healthcare sectors were caught off guard. This situation put a burden on doctors and healthcare professionals that they could not handle. All of the studies on COVID-19 in the literature have been done to help experts to recognize COVID-19 more accurately, to use more accurate diagnosis and appropriate treatment methods. The alleviation of this workload will be possible by developing computer aided early and accurate diagnosis systems with machine learning. Diagnosis and evaluation of pneumonia on computed tomography images provide significant benefits in investigating possible complications and in case follow-up. Pneumonia and lesions occurring in the lungs should be carefully examined as it helps in the diagnostic process during the pandemic period. For this reason, the first diagnosis and medications are very important to prevent the disease from progressing. In this study, a dataset consisting of Pneumonia and Normal images was used by proposing a new image preprocessing process. These preprocessed images were reduced to 15x15 unit size and their features were extracted according to their RGB values. Experimental studies were carried out by performing both normal values and feature reduction among these features. RGB values of the images were used in train and test processes for MLAs. In experimental studies, 5 different Machine Learning Algorithms (MLAs) (Multi Class Support Vector Machine (MC-SVM), k Nearest Neighbor (k-NN), Decision Tree (DT), Multinominal Logistic Regression (MLR), Naive Bayes (NB)). The following accuracy rates were obtained in train operations for MLAs, respectively; 1, 1, 1, 0.746377, 0.963768. Accuracy results in test operations were obtained as follows; 0.87755, 0.857143, 0.857143, 0.877551, 0.938776. [ABSTRACT FROM AUTHOR]