Search

Purpose. Fast kV-switching (FKS) and dual-layer flat-panel detector (DL-FPD) technologies have been actively studied as promising dual-energy spectral imaging solutions for FPD-based cone-beam computed tomography (CT). However, cone-beam CT (CBCT) spectral imaging is known to face challenges in obtaining accurate and robust material discrimination performance. That is because the energy separation by either FKS or DL-FPD, alone, is still limited, along with apparently unpaired signal levels in the effective low- and high-energy projections in real applications, not to mention the x-ray scatter in cone-beam scan which will make the material decomposition almost impossible if no correction is applied. To further improve CBCT spectral imaging capability, this work aims to promote a source-detector joint multi-energy spectral imaging solution which takes advantages of both FKS and DL-FPD, and to conduct a feasibility study on the first tabletop CBCT system with the joint spectral imaging capability developed. Methods. For CBCT, development of multi-energy spectral imaging can be jointly realized by using an x-ray source with a generator whose kilo-voltages can alternate in tens of Hertz (i.e. FKS), and a DL-FPD whose top- and bottom-layer projections corresponds to different effective energy levels. Thanks to the complimentary characteristics inherent in FKS and DL-FPD, the overall energy separation will be significantly better when compared with FKS or DL-FPD alone, and the x-ray photon detection efficiency will be also improved when compared with FKS alone. In this work, a noise performance analysis using the Cramér–Rao lower bound (CRLB) method is conducted. The CRLB for basis material after a projection-domain material decomposition is derived, followed by a set of numerical calculations of CRLBs, for the FKS, the DL-FPD and the joint solution, respectively. To compensate for the slightly angular mismatch between low- and high- projections in FKS, a dual-domain projection completion scheme is implemented. Afterwards material decomposition from the complete projection data is carried out by using the maximum-likelihood method, followed by reconstruction of basis material and virtual monochromatic images (VMI). In this work, the first FKS and DL-FPD jointly enabled multi-energy tabletop CBCT system, to the best of our knowledge, has been developed in our laboratory. To evaluate its spectral imaging performance, a set of physics experiments are conducted, where the multi-energy and head phantoms are scanned using the 80/105/130 kVp switching pairs and projection data are collected using a prototype DL-FPD, whose both top and bottom layer of panels are composed of 550 μ m of cesium iodine (CsI) scintillators with no intermediate metal filter in-between. Results. The numerical simulations show that the joint spectral imaging solution can lead to a significant improvement in energy separation and lower noise levels in most of material decomposition cases. The physics experiments confirmed the feasibility and superiority of the joint spectral imaging, whose CNRs in the selected regions of interest of the multi-energy phantom were boosted by an average improvement of 21.9%, 20.4% for water basis images and 32.8%, 62.8% for iodine images when compared with that of the FKS and DL-FPD, respectively. For the head phantom case, the joint spectral imaging can effectively reduce the streaking artifacts as well, and the standard deviation in the selected regions of interest are reduced by an average decrement of 19.5% and 8.1% for VMI when compared with that of the FKS and DL-FPD, respectively. Conclusions. A feasibility study of the joint spectral imaging solution for CBCT by utilizing both the FKS and DL-FPD was conducted, with the first tabletop CBCT system having such a capability being developed, which exhibits improved CNR and is more effective in avoiding streaking artifacts as expected. [ABSTRACT FROM AUTHOR]

Metal thio(seleno)phosphates are renowned for their multifaceted physical characteristics and versatile applications, particularly in optoelectronics. In detection applications, a low and stable dark current is crucial, enhancing the sensitivity and signal‐to‐noise ratio of detectors. Herein, a van der Waals layered material has synthesized, CuInP2Se6. Despite its nanometric scale, 2D CuInP2Se6 detector transcends the conventional absorption inefficiencies tied to ultrathin materials. It delivers exceptional ultraviolet–visible detection, characterized by an ultralow, stable dark current of 150 fA, and a noise power density of 27.7 fA Hz−1/2 at room temperature. The in‐depth investigation reveals a responsivity of 4.47 A W−1, an external quantum efficiency of 1369%, a special detectivity of 1.44 × 1013 Jones, and a rapid response speed of 280 µs, positioning it at the pinnacle of 2D photodetector performance. The CuInP2Se6's ultralow, stable dark current paves the way for X‐ray detection, achieving an unprecedented sensitivity of 1.32 × 105 µC Gyair−1 cm−2 and a low detection limit of 0.15 µGyair s−1. Furthermore, 2D CuInP2Se6 detector exhibits a remarkable image‐sensing capability, adeptly capturing intricate patterns with high resolution. This discovery indicates its promise in revolutionizing integrated micro/nano optoelectronic devices, opening avenues for advancements in light and X‐ray detection and imaging technologies. [ABSTRACT FROM AUTHOR]

MOFs have good potential for X-ray detection, but direct X-ray detection in single crystal form is rarely reported. In this work, we successfully synthesized Pb-TCPE, and the single crystal achieves a low detection limit and high detection sensitivity of 4812.6 μC Gyair−1 cm−2, which exhibits great potential for X-ray detection and imaging. [ABSTRACT FROM AUTHOR]

Accurate detection of x-ray radiation is essential for tissue equivalence detection and safety control during medical radiotherapy. Here, a promising radiation detector based on organic 1,8-naphthalimide (C12H7NO2, NTI) single crystals is proposed. NTI single crystals with dimensions of 8 × 2 × 1 mm3 were synthesized by an optimized solvent-cooling method, and the crystal structure was characterized to elucidate the anisotropy mechanism. The coplanar detector made by NTI has a leakage current of less than 0.1 pA at an electric field strength of 1 kV cm−1 and provides excellent detection of 5.49 MeV α-particles (241Am) with a full-energy peak resolution of up to 32.3%. The calculated electron mobility (μ e) and electron mobility-lifetime product (μ τ)e were 7.9 cm2 V−1s−1 and 1.56 × 10−6 cm2 V−1, respectively. Additionally, the detection limit of the NTI detector was 0.35 µGy s−1 in the electric field strength range of 0.2–1.0 kV cm−1 under a 20 kV x-ray beam with a high sensitivity of 56.2 μC Gy−1cm−2. Consequently, the NTI detector achieves an excellent spatial resolution of 0.8–0.9 lp mm−1 in terms of x-ray imaging capability. [ABSTRACT FROM AUTHOR]

Lead‐free hybrid perovskites (HPs) are considered as environmentally friendly photodetection materials. However, there are few studies on self‐powered photodetection in lead‐free HPs, and most of them are achieved through the introduction of chiral ammonium cations induced bulk photovoltaic effect (BPVE). Notably, enantiomeric pure chiral ammonium cations are difficult to synthesize, the quantity is small and the price is high. Therefore, choosing achiral ammonium cations to induce BPVE in lead‐free HPs is crucial. Herein, achiral cations 1,3‐bis(aminomethyl)cyclohexane (1,3‐BMACH) is exploited to induce bulk photovoltaic through confinement effect in (1,3‐BMACH)BiI5, then self‐powered X‐ray detection is successfully realized. Due to the large space in zero‐dimensional (0 D) (MXD)BiI5 (MXD is meta‐xylylenediammonium), the confinement effect is not obvious, resulting in the disorderly arrangement of MXD2+ cations and a centrosymmetry structure of (MXD)BiI5. Benefiting from the large photovoltage (1.0 V) of (1,3‐BMACH)BiI5 under X‐ray, its single crystal devices exhibit ultra‐high sensitivity of 170 µC Gy−1 cm−2 and extremely low detection limit of 49 nGy s−1 under self‐powered mode, which almost surpassing most low‐dimensional single‐phase lead‐free HPs at 0 V bias. This work has promoted the application of lead‐free HPs in the field of self‐powered X‐ray detection. [ABSTRACT FROM AUTHOR]

The emerging 2D layered perovskites have promising optoelectronic properties, good intrinsic stability and reduced ion migration, making them effective for detecting X‐ray radiation. However, their application is constrained by poor out‐of‐plane carrier transport. In this study, inch‐sized high‐quality CsPb2Br5 layered single crystals (SCs) are developed using an organic ligand‐assisted solution process. By modifying the surface energy, the anisotropy of crystal growth is conquered, resulting in CsPb2Br5 SCs with sufficient thickness for X‐ray detection. Importantly, this modification significantly enhanced the crystal quality as the grown CsPb2Br5 SCs exhibited longer photoluminescence lifetime and smaller trap density. Notably, the CsPb2Br5 SCs demonstrate unprecedented out‐of‐plane carrier transport, achieving a high carrier mobility‐lifetime product of 2.53 × 10−2 cm2V−1. This can be attributed to the small interlayer distance and the strong interlayer force of Cs─Br bonding. Furthermore, CsPb2Br5 SCs possess other intriguing attributes for X‐ray detection, including high bulk resistivity and outstanding thermal stability. These advantageous properties enable high‐performance vertical‐structure X‐ray detection with a superior sensitivity of up to 8865.6 µC Gyair−1cm−2 and a low detectable dose rate of 12.7 nGyairs−1. Additionally, CsPb2Br5 SCs exhibit high spatial resolution in X‐ray imaging and exceptional thermal stability, making them promising candidates for nondestructive determination. [ABSTRACT FROM AUTHOR]

Surface defects are crucial to perovskite single crystals (SCs) for versatile optoelectronic applications, whereas suffers from the intricate post‐treatments and unsatisfactory reproducibility within solution growth strategy due to the residue solvent corrosion and adsorbed precursors deposition. Here, an ionic liquid, 1‐butyl‐3‐methylimidazolium bis(trifluoromethylsulfonyl)imide (BMITFSI) is demonstrated, assisted solution growth approach for fabricating high‐quality self‐cleaning perovskite single crystals with no need for any post‐treatment. Benefiting from the in situ assembling in crystalline surface, BMITFSI can effectively decrease the crystallographic trap density by simultaneously introducing the self‐cleaning effect and optimizing the crystalline growth process. Particularly, as fabricated MAPbI3 single crystal exhibits an impressive photodetection performance with a specific detectivity of 2.83 × 1012 Jones in visible‐IR spectrum and a sensitivity of 7.24 × 104 µC Gyair−1 cm−2 in X‐ray detection, which is as good as the conventionally fabricated crystal with elaborate post‐treatments. Based on the chemical composition independent universality, this work paves an easy but efficient route to improve the current crystallization methodology toward high‐quality perovskite SCs fabrication. [ABSTRACT FROM AUTHOR]

The document is a contents list for the journal CrystEngComm. It provides information about the articles and papers included in the issue, as well as the authors and their research topics. The journal focuses on the design and understanding of solid-state and crystalline materials. The document also mentions the Royal Society of Chemistry, which is a leading chemistry community that connects the world with the chemical sciences. [Extracted from the article]

For a long time, single crystals of the organic compound TPB (1,3,5-triphenylbenzene) have been viewed as a scintillator material for indirect X-ray detection. We here attempt to explore their potential for direct detection. A TPB single crystal with a size of up to 20 × 6 × 4 mm3 and without obvious growth steps was obtained using a solvent volatilization method. It has an orthorhombic structure with a high-quality FWHM of as low as 0.059 and preferred grown orientations along (131) and (220). AFM images clarify the two-dimensional nucleation growth mechanism. The fitted bandgap of the as-grown crystal is about 3.65 eV. TPB detectors with vertical and coplanar electrodes with a resistivity of 2.56 × 1013 Ω cm and 6.68 × 1013 Ω cm, respectively, were prepared. The mobilities for electrons (μe) and holes (μh) for the coplanar device were calculated to be 1.12 cm2 V−1 s−1 and 1.02 cm2 V−1 s−1, respectively. Under a 50 kV X-ray beam, the detection limit is as low as 0.35 μGy s−1, and the sensitivity reaches 2.72 μC Gy−1 cm−2. The TPB devices have the ability to detect 241Am@5.49 MeV α particles, showing the full-energy peak collected from the holes with an energy resolution of 39.13% at 700 V. The mobility lifetime product of the TPB devices for electrons (μτ)e and holes (μτ)h were calculated to be up to 2.24 × 10−5 cm2 V−1 and 4.04 × 10−5 cm2 V−1, respectively. The TPB detector could present a spectral response to 241Am@59.5 keV γ-rays from the holes with an energy resolution of 44.25% at 1000 V, which shows the potential for both direct and indirect detection of high-energy radiation. [ABSTRACT FROM AUTHOR]

X-ray nanotomography is a powerful tool for the characterization of nanoscale materials and structures, but it is difficult to implement due to the competing requirements of X-ray flux and spot size. Due to this constraint, state-of-the-art nanotomography is predominantly performed at large synchrotron facilities. We present a laboratory-scale nanotomography instrument that achieves nanoscale spatial resolution while addressing the limitations of conventional tomography tools. The instrument combines the electron beam of a scanning electron microscope (SEM) with the precise, broadband X-ray detection of a superconducting transition-edge sensor (TES) microcalorimeter. The electron beam generates a highly focused X-ray spot on a metal target held micrometers away from the sample of interest, while the TES spectrometer isolates target photons with a high signal-to-noise ratio. This combination of a focused X-ray spot, energy-resolved X-ray detection, and unique system geometry enables nanoscale, element-specific X-ray imaging in a compact footprint. The proof of concept for this approach to X-ray nanotomography is demonstrated by imaging 160 nm features in three dimensions in six layers of a Cu-SiO2 integrated circuit, and a path toward finer resolution and enhanced imaging capabilities is discussed. [ABSTRACT FROM AUTHOR]

The detection of inelastically scattered soft x-rays with high energy resolution usually requires large grating spectrometers. Recently, photoelectron spectrometry for analysis of x-rays (PAX) has been rediscovered for modern spectroscopy experiments at synchrotron light sources. By converting scattered photons to electrons and using an electron energy analyser, the energy resolution for resonant inelastic x-ray scattering (RIXS) becomes decoupled from the x-ray spot size and instrument length. In this work, we develop PAX towards high energy resolution using a modern photoemission spectroscopy setup studying Ba2Cu3O4Cl2 at the Cu L 3-edge. We measure a momentum transfer range of 24% of the first Brillouin zone simultaneously. Our results hint at the observation of a magnon excitation below 100 meV energy transfer and show intensity variations related to the dispersion of dd -excitations. With dedicated setups, PAX can complement the best and largest RIXS instruments, while at the same time opening new opportunities to acquire RIXS at a range of momentum transfers simultaneously and combine it with angle-resolved photoemission spectroscopy in a single instrument. [ABSTRACT FROM AUTHOR]

The Snake is a remarkable Galactic Centre radio filament with a morphology characterized by two kinks along its ∼20 arcmin extent. The major and minor kinks are located where the filament is most distorted from a linear magnetized structure running perpendicular to the Galactic plane. We present Chandra , VLA, and MeerKAT data and report the detection of an X-ray and radio source at the location of the major kink. High-resolution radio images of the major kink reveal a compact source with a steep spectrum with spectral index α ∼ −2.7 surrounded by extended emission. The radio luminosity and steep spectrum of the compact source are consistent with a pulsar. We also show flattening of the spectrum and enhanced synchrotron emissivity away from the position of the major kink along the Snake, which suggests injection of relativistic particles along the Snake. We argue that the major kink is created by a fast-moving (∼500–1000 km s−1) object punching into the Snake, distorting its magnetic structure, and producing X-ray emission. X-ray emission pinpoints an active acceleration site where the interaction is taking place. A secondary kink is argued to be induced by the impact of the high-velocity object producing the major kink. [ABSTRACT FROM AUTHOR]

Soft x-ray detectors play crucial roles in biology, chemistry, and lithography. Current soft x-ray detectors suffer from insufficient responsivity (R), excessively large cell area, and limited stability. Here, the β-Ga2O3 soft x-ray detector is constructed, and the effects of varying the sensitive layer thickness and voltage on the soft x-ray detection characteristics of the device are explored. Meanwhile, the mechanism of the multiplication ionization process from soft x-ray and the photoconductivity gain on the photoresponse performance of the device are analyzed. The device obtains the R up to 3.05 × 103 A/W under 300 eV soft x-ray irradiation at the synchrotron beamline, which is about 1.19 × 104 times higher than that of the conventional device. The Ga2O3 device also maintains stable operation under long-term irradiation and multicycle switching. These results indicate that Ga2O3 is an ideal candidate material for soft x-ray detection, which has great potential for applications such as imaging of biological cells. [ABSTRACT FROM AUTHOR]

Inorganic scintillators play a pivotal role in diverse fields like medical imaging, nondestructive detection, homeland security, and high‐energy physics. However, traditional inorganic scintillators encounter challenges such as high fabrication costs and low light yield. Recently, low‐dimensional metal halide scintillators (LDMHS) have witnessed rapid progress, owing to their distinctive crystal structure and superior radioluminescence performance. Herein, an overview of recent advancements and proposed instructive pathways for achieving high‐performance LDMHS is provided. First, the scintillation physical mechanism and emphasis on the essential requirements of scintillators for diverse applications are elucidated. Furthermore, LDMHS are classified according to B‐site cations, and their respective characteristics and recent advancements are introduced. This encompasses the understanding of structure‐property relationships and the routes and rules for optimizing scintillation performance. Finally, the persisting challenges in this burgeoning field and proposed potential research directions for future exploration are discussed. [ABSTRACT FROM AUTHOR]

Organic scintillators have recently attracted growing attention for X‐ray detection in industrial and medical applications. However, these materials still face critical obstacles of low attenuation efficiency and/or inefficient triplet exciton utilization. Here we developed a new category of organogold(III) complexes, Tp‐Au‐1 and Tp‐Au‐2, through adopting a through‐space interaction motif to realize high X‐ray attenuation efficiency and efficient harvesting of triplet excitons for emission. Thanks to the efficient through‐space charge transfer process, this panel of complexes achieved higher photoluminescence quantum yield and shorter radiative lifetimes compared with the through‐bond reference complexes. Inspiringly, these organogold(III) complexes exhibited polarity‐dependent emission origins: thermally activated delayed fluorescence and/or phosphorescence. Under X‐ray irradiation, Tp‐Au‐2 manifested intense radioluminescence together with a record‐high scintillation light yield of 77,600 photons MeV−1 for organic scintillators. The resulting scintillator screens demonstrated high‐quality X‐ray imaging with >16.0 line pairs mm−1 spatial resolution, outstripping most organic and inorganic scintillators. This finding provides a feasible strategy for the design of superior organic X‐ray scintillators. [ABSTRACT FROM AUTHOR]

Organic scintillators have recently attracted growing attention for X‐ray detection in industrial and medical applications. However, these materials still face critical obstacles of low attenuation efficiency and/or inefficient triplet exciton utilization. Here we developed a new category of organogold(III) complexes, Tp‐Au‐1 and Tp‐Au‐2, through adopting a through‐space interaction motif to realize high X‐ray attenuation efficiency and efficient harvesting of triplet excitons for emission. Thanks to the efficient through‐space charge transfer process, this panel of complexes achieved higher photoluminescence quantum yield and shorter radiative lifetimes compared with the through‐bond reference complexes. Inspiringly, these organogold(III) complexes exhibited polarity‐dependent emission origins: thermally activated delayed fluorescence and/or phosphorescence. Under X‐ray irradiation, Tp‐Au‐2 manifested intense radioluminescence together with a record‐high scintillation light yield of 77,600 photons MeV−1 for organic scintillators. The resulting scintillator screens demonstrated high‐quality X‐ray imaging with >16.0 line pairs mm−1 spatial resolution, outstripping most organic and inorganic scintillators. This finding provides a feasible strategy for the design of superior organic X‐ray scintillators. [ABSTRACT FROM AUTHOR]

Lead‐free metal halide double perovskites have emerged as promising scintillators owing to their superior optoelectronic properties, low‐cost and solution processability. However, it is still challenging to develop high‐performance flexible X‐ray scintillators based on the B(I)‐site alkali metal modulation in lead‐free double perovskite nanocrystals (NCs). Herein, a series of novel Cs2B(I)GdCl6 (B: Li, Na, K) of double perovskite A2B(I)M(III)X6 NCs structures are successfully synthesized, the optical and scintillator properties of which are significantly sensitive to the B(I)‐site alkali metals with the doping of Sb3+. They showed efficient self‐trapped exciton (STE) emission with high photoluminescence quantum yield (PLQY) and exhibited the highest X‐ray detection limit (86 nGyair s−1) and excellent spatial resolutions (>15 lp mm−1). The femtosecond transient absorption measurement and theoretical analysis further revealed that the B(I)‐site alkali metal fundamentally balanced the exciton–phonon coupling with appropriate STEs formation energy barrier and the electron localization and thus improved the optical and scintillator properties. This B(I)‐site alkali metal engineering offers a strategy to develop bright luminescent double perovskite NCs for X‐ray detection and imaging devices. [ABSTRACT FROM AUTHOR]

The anomalous photovoltaic (APV) effect in organic–inorganic hybrid perovskites (OIHPs) has attracted massive interest for developing high‐performance optoelectronic devices. However, exploring the ionizing radiation responsive APV effect remains blank, let alone its potential applications. Herein, the unprecedented APV behavior in a 1D lead‐free OIHP, (4‐AMP)BiI5 (ABI, 4‐AMP = 4‐(aminomethyl)pyridine) under X‐ray irradiation is reported, exhibiting a large above‐bandgap bulk photovoltage of ≈10 V. Such a strong APV effect is closely related to the intrinsic electric polarization in polar ABI, which acts as the driving force for X‐ray‐generated carriers' separation and transport, thus allowing it to be self‐powered. As a result, sensitive self‐powered X‐ray detectors based on high‐quality ABI single crystals are successfully fabricated, possessing a high sensitivity of 66.84 µC Gy−1 cm−2, a low detection limit of 482 nGy s−1, and superior operational stability. This work first demonstrates the ionizing radiation‐responsive APV effect in OIHPs, which further enables passive radiation detection. [ABSTRACT FROM AUTHOR]

Purpose: We investigated the characteristics of radiation-induced current in nano-porous pellet and thin-film anodized tantalum exposed to kVp X-ray beams. We aim at developing a large area (≫cm2) thin-film radiation sensor for medical, national security and space applications. Methods: Large area (few cm2) micro-thin Ta foils were anodized and coated with a counter electrode made of conductive polymer. In addition, several types of commercial electrolytic porous tantalum capacitors were assembled and prepared for irradiation with kVp X-rays. We measured dark current (leakage) as well as transient radiation-induced currents as a function of external voltage bias. Results: Large transient currents (up to 50 nA) under X-ray irradiation (dose rate of about 3 cGy/s) were measured in Ta2O5 capacitors. Small nano-porous Ta and large-area flat Ta foil capacitors show similar current–voltage characteristic curve after accounting for different X-ray attenuation in capacitor geometry. The signal is larger for thicker capacitor oxide. A non-negligible signal for null external voltage bias is observed, which is explained by fast electron production in Ta foils. Conclusions: Anodized tantalum is a promising material for use in large-area, self-powered radiation sensors for X-ray detection and for energy harvesting. [ABSTRACT FROM AUTHOR]

Organic–inorganic hybrid metal halides are widely used in X‐ray detection and imaging due to their high X‐ray absorption efficiency, ease of synthesis, and efficient luminescence. However, the issue of lead toxicity remains a concern. In this study, non‐toxic, 0D 2,2′‐(Ethylenedioxy)bis(ethylamine) manganese (II) bromide (EDBEMnBr4) is synthesized using the simple mechanical grinding method and the solution method that exhibits intense green emission at ≈525 nm. Moreover, the change of structure under the influence of temperature and water significantly affects its fluorescence color under UV light. Scintillator materials with and without moisture exposure showed spatial resolutions of 7 and 4 lp mm−1, and low detection limits of 4.62 and 5.25 µGyair s−1, respectively, meeting medical industry standards (<5.5 µGyair s−1). Furthermore, based on the apparent change in luminescence color triggered by moisture for EDBEMnBr4, a preliminary attempt is made to apply it to humidity monitoring showing that the boundary of color change has a good linear dependence on humidity and time. This work provides new opportunities for Mn‐based metal halides in both X‐ray detection as well as moisture detection. [ABSTRACT FROM AUTHOR]

Significant progress is achieved in the development of hybrid lead halide perovskite‐based X‐ray detectors. An in‐depth understanding of the impact of X‐ray irradiation on charge carrier behaviors is essential to assess the long‐term operational reliability of these devices. In this study, high‐quality methylammonium lead bromide (MAPbBr3) single crystals with good environmental stability are grown by an inverse temperature method, and the evolution of their carrier transport capacity is investigated by tracking the optoelectronic properties of MAPbBr3 single crystal devices under X‐ray irradiation with different fluence. Notably, the carrier transport capacity is enhanced when the X‐ray fluence is between 1.2 × 1017 and 1.8 × 1017 photons, as evidenced by improved optoelectronic properties and reduced trap state density. Conversely, a larger X‐ray fluence of 3.6 × 1017 photons causes unrepaired decomposition of the MAPbBr3 single crystals and severe degradation of their carrier transport capacity. These findings provide valuable insights for the application of hybrid lead perovskite single crystals in X‐ray detection, emphasizing the importance of optimizing X‐ray fluence levels for sustained device performance. [ABSTRACT FROM AUTHOR]

Ultrahigh‐resolution X‐ray detection has always been a goal pursued in industrial inspection and medical diagnosis. However, the resolution of the corresponding image generally suffers from serious light scattering and crosstalk. Here, a low‐temperature thermoplastic scintillator ink of [Bmmim]2MnCl4 (Bmmim = 1‐butyl‐2,3‐dimethylimidazolium) is designed, achieving an astonishing spatial resolution of over 22 lp mm−1 (≥22.5 µm). A customized X‐ray imaging can be realized with the as‐explored [Bmmim]2MnCl4 scintillator to the targets through brushing feasibly exhibiting a high adhesion and processability thanks to the superior rheological properties. It is demonstrated that the coordination number determines the melting point of the corresponding scintillator, and an appropriate melting point (323 K) endows a superior viscosity of the sample as print ink. Accordingly, the as‐explored scintillator not only exhibits a high light output with 3.63 times of the commercial Bi4Ge3O12 (10 000 photons MeV−1) under steady‐state X‐ray illumination but also performs excellent recyclability even after 100 re‐uses. This work brings a new perspective for solving the problems of light scattering and light crosstalk for X‐ray imaging, as well as promoting the development of scintillator ink for recycling utilization. [ABSTRACT FROM AUTHOR]

X-ray and γ-ray detection have been extensively studied and applied in medical imaging, security inspection, homeland security, non-destructive testing and other various fields. Perovskite materials have become excellent candidates for radiation detector devices due to their high radiation absorption coefficient, high carrier mobility-lifetime product and defect tolerance. The solution method offers significant advantages in the preparation of perovskite materials. It is a cost-effective approach that can be carried out at low temperatures or under ambient conditions. Additionally, it is also easier to implement for industrial production. This method plays a crucial role in optimizing the material system and achieving the preparation of high quality and large area crystal materials in the future. This paper analyzes the effects of crystal growth and material composition on radiation detection performance, focusing on the solution preparation of perovskite materials. The study aims to improve radiation detection performance by optimizing crystal growth quality and device structure design. Additionally, it also summarises the challenges faced by perovskite materials in the field of radiation detection and suggests future research directions. The results of this study are expected to serve as a reference for the industrialization of perovskite materials in the field of radiation detection. [ABSTRACT FROM AUTHOR]

This paper focuses on the intelligent detection of prohibited items in X‐ray images during the security checking process. An intelligent semantic segmentation model of prohibited items in X‐ray images is proposed based on the attention‐based object localization method. Based on the pre‐trained CNN classification framework, the attention mechanism can map the high‐layer semantic information of objects into the input space, while generating energy saliency maps to locate the prohibited items. In order to make the obtained attention maps discriminative, the lateral and contrastive inhibition strategies are introduced and combined together which can highlight the responses of activated neurons. Under the guidance of attention responses, two traditional image segmentation algorithms are employed to achieve the semantic segmentation results for the prohibited items detection in X‐ray images. The proposed semantic segmentation model relies on weakly supervised learning mechanism, and only depends on the category labels of prohibited items, which greatly avoids the work cost of data semantic annotation. The experimental results based on the public SIXray baseline and the self‐built X‐ray image database demonstrate the proposed method can achieve about 65% IoU localization precise averagely. In addition, comparison experiments were carried out with the state‐of‐the‐arts and ablation experiments to verify the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

X‐ray detectors utilizing 2D/3D heterodimensional perovskites have achieved great success. However, the labile nature of halide perovskites generally results in structures with random orientations and interfaces, which in turn increases the dark noise of X‐ray detectors, hindering their use in low‐dose X‐ray detection. Here, it is shown that both anisotropy and ultralow dark current can be achieved in self‐powered X‐ray detectors using well‐oriented 2D/3D heterodimensional perovskite crystals (HPCs). A halide diffusion‐promoted welding approach is devised to create the oriented HPCs, enabling two distinct configurations: A lateral orientation where the inorganic frameworks of the two phases are perpendicular, and a vertical orientation with parallel inorganic slabs. The different crystalline orientations produce unique anisotropic X‐ray detecting performance of 2D/3D HPCs, with a large anisotropic ratio of 4. Moreover, a self‐powered X‐ray detector using vertical HPC exhibits a greatly suppressed dark current density of 0.17 nA cm−2 and a low detection limit of 77 nGyair s−1, enabling high‐resolution X‐ray imaging. In contrast, the lateral devices show higher X‐ray sensitivity (1850 µC Gyair−1cm−2) at zero bias. This work reveals the interplay between crystalline orientation and X‐ray detection performance, opening new possibilities for developing low‐cost, low‐noise X‐ray detectors. [ABSTRACT FROM AUTHOR]

Solution grown metal halide perovskites (MHPs) are a class of low-cost, direct conversion semiconducting materials with the potential to meet the need for large areas, high stopping power, and high sensitivity x-ray detectors. While polycrystalline MHP thin films have shown significant potential for meeting this need, their efficiencies for detecting x rays are limited by their thickness. This article presents an MHP variant, methylammonium lead tribromide (MAPB) in the form of 3D polycrystalline mosaic wafers with relatively high hole transport properties that demonstrated stable sensitivity during irradiation. An expedited and efficient detector fabrication method that did not include polishing or sintering was evaluated, and a radiograph of a brass key was produced using electron collection from the resulting wafer. However, a high dose rate was required due to very low sensitivity values. The effects of surface inhomogeneity and radiation damage were investigated as explanatory factors, and these phenomena were further characterized through IV measurements, current response as a function of electric field and x-ray dose rate, and alpha particle irradiation. The results indicated that although compromising surface quality for fabrication efficiency was the primary hindrance to the x-ray detection performance of 3D polycrystalline MAPB, stable performance could still be achieved under reasonable dose rates. [ABSTRACT FROM AUTHOR]

The strategy of bandgap regulation is important for X-ray detection, but has not been reported for 1D Pb halide perovskite materials. In this work, three such materials, 1, 2 and 3, with a tunable bandgap, were fabricated for application in X-ray detection. 3 shows high sensitivity, far superior to commercial X-ray detectors. [ABSTRACT FROM AUTHOR]

Lead‐free halide perovskite‐based X‐ray scintillators with high light yield (LY) and low detection limit (LOD) have become a growing subject of research interest due to their promising application in a wide range of areas, from security to healthcare. Herein, a modified hot injection method is employed to synthesize Mn(II)‐doped Cs2NaBiCl6 double perovskite nanocrystals (DPNCs) and to examine their scintillating properties for application in X‐ray imaging and detection. The Mn(II)‐doped Cs2NaBiCl6 DPNCs exhibit a broad orange photoluminescence (PL) band at 586 nm with a PL quantum yield of 10.6%, attributed to the 4T2g(4G) → 6A1g(6S) transition of Mn2+. Temperature‐dependent PL and time‐resolved PL spectra of 4.04% Mn(II)‐doped Cs2NaBiCl6 demonstrate that the orange emission intensity initially reaches a maximum and subsequently decreases, while the decay lifetimes monotonically decrease with increasing temperature. This inconsistency can be due to the effect of the [MnCl6]4− octahedra and electron‐phonon coupling at elevated temperatures. Further, 0.05 mm thick Cs2NaBiCl6:4.04%Mn@poly(methyl methacrylate) scintillator film is synthesized with an LY of 28,350 photons MeV−1 and a LOD of 45.2 nGyair s−1. Additionally, this film demonstrates good X‐ray imaging performance with a spatial resolution of 14.76 line pairs (lp) mm−1 and shows exceptional stability under prolonged X‐ray exposure. [ABSTRACT FROM AUTHOR]

Objectives: Artificial intelligence (AI) has tremendous potential to help radiologists in daily clinical routine. However, a seamless, standardized, and time-efficient way of integrating AI into the radiology workflow is often lacking. This constrains the full potential of this technology. To address this, we developed a new reporting pipeline that enables automated pre-population of structured reports with results provided by AI tools. Methods: Findings from a commercially available AI tool for chest X-ray pathology detection were sent to an IHE-MRRT-compliant structured reporting (SR) platform as DICOM SR elements and used to automatically pre-populate a chest X-ray SR template. Pre-populated AI results could be validated, altered, or deleted by radiologists accessing the SR template. We assessed the performance of this newly developed AI to SR pipeline by comparing reporting times and subjective report quality to reports created as free-text and conventional structured reports. Results: Chest X-ray reports with the new pipeline could be created in significantly less time than free-text reports and conventional structured reports (mean reporting times: 66.8 s vs. 85.6 s and 85.8 s, respectively; both p < 0.001). Reports created with the pipeline were rated significantly higher quality on a 5-point Likert scale than free-text reports (p < 0.001). Conclusion: The AI to SR pipeline offers a standardized, time-efficient way to integrate AI-generated findings into the reporting workflow as parts of structured reports and has the potential to improve clinical AI integration and further increase synergy between AI and SR in the future. Critical relevance statement: With the AI-to-structured reporting pipeline, chest X-ray reports can be created in a standardized, time-efficient, and high-quality manner. The pipeline has the potential to improve AI integration into daily clinical routine, which may facilitate utilization of the benefits of AI to the fullest. Key points: • A pipeline was developed for automated transfer of AI results into structured reports. • Pipeline chest X-ray reporting is faster than free-text or conventional structured reports. • Report quality was also rated higher for reports created with the pipeline. • The pipeline offers efficient, standardized AI integration into the clinical workflow. [ABSTRACT FROM AUTHOR]

Dion–Jacobson (DJ) double perovskites have emerged as environmentally friendly candidates for X‐ray detection, owing to their prominent optoelectronic performance and highlighted structural rigidity. Despite considerable efforts, the exploration of polar DJ‐type double perovskites for self‐powered X‐ray detection remains scarce. Herein, by introducing a diamine spacer to increase the structural rigidity, the study has successfully designed a new polar 2D DJ‐type double perovskite of (HIA)2AgBiBr8 (1, HIA = histamine), and centimeter‐size crystals are successfully obtained for effective X‐ray detection. Structurally, 1 features the quantum‐confined motif comprised of the directionally arranged inorganic perovskite sheets and alternating organic spacing cations, which endows a large mobility‐lifetime (µτ) product up to 1.23 × 10−3 cm2 V−1 on the par with typical X‐ray sensing candidates (MAPbI3 wafers, µτ = 2 × 10−3 cm2 V−1). This attribute gives rise to a high sensitivity of 118 µCGyair−1 cm−2 to X‐ray illumination. Moreover, based on its polar structure, bulk photovoltaic effect with the photovoltage of ≈0.45 V is obtained in 1, which affords the driving source toward the self‐powered X‐ray photodetection. This work highlights the potential of DJ‐type double perovskites in high‐energy ray detection and opens avenues for exploring new functionalities of DJ double perovskites as smart photoelectric candidates. [ABSTRACT FROM AUTHOR]

Background: This study aimed to evaluate the impact of an AI-assisted fracture detection program on radiology residents' performance in pediatric and adult trauma patients and assess its implications for residency training. Methods: This study, conducted retrospectively, included 200 radiographs from participants aged 1 to 95 years (mean age: 40.7 ± 24.5 years), encompassing various body regions. Among these, 50% (100/200) displayed at least one fracture, totaling one hundred thirty-five fractures, assessed by four radiology residents with different experience levels. A machine learning algorithm was employed for fracture detection, and the ground truth was established by consensus among two experienced senior radiologists. Fracture detection accuracy, reporting time, and confidence were evaluated with and without AI support. Results: Radiology residents' sensitivity for fracture detection improved significantly with AI support (58% without AI vs. 77% with AI, p < 0.001), while specificity showed minor improvements (77% without AI vs. 79% with AI, p = 0.0653). AI stand-alone performance achieved a sensitivity of 93% with a specificity of 77%. AI support for fracture detection significantly reduced interpretation time for radiology residents by an average of approximately 2.6 s (p = 0.0156) and increased resident confidence in the findings (p = 0.0013). Conclusion: AI support significantly enhanced fracture detection sensitivity among radiology residents, particularly benefiting less experienced radiologists. It does not compromise specificity and reduces interpretation time, contributing to improved efficiency. This study underscores AI's potential in radiology, emphasizing its role in training and interpretation improvement. [ABSTRACT FROM AUTHOR]

Given that defect detection in weld X-ray images is a critical aspect of pressure vessel manufacturing and inspection, accurate differentiation of the type, distribution, number, and area of defects in the images serves as the foundation for judging weld quality, and the segmentation method of defects in digital X-ray images is the core technology for differentiating defects. Based on the publicly available weld seam dataset GDX-ray, this paper proposes a complete technique for fault segmentation in X-ray pictures of pressure vessel welds. The key works are as follows: (1) To address the problem of a lack of defect samples and imbalanced distribution inside GDX-ray, a DA-DCGAN based on a two-channel attention mechanism is devised to increase sample data. (2) A convolutional block attention mechanism is incorporated into the coding layer to boost the accuracy of small-scale defect identification. The proposed MAU-Net defect semantic segmentation network uses multi-scale even convolution to enhance large-scale features. The proposed method can mask electrostatic interference and non-defect-class parts in the actual weld X-ray images, achieve an average segmentation accuracy of 84.75% for the GDX-ray dataset, segment and accurately rate the valid defects with a correct rating rate of 95%, and thus realize practical value in engineering. [ABSTRACT FROM AUTHOR]

Musculoskeletal conditions affect an estimated 1.7 billion people worldwide, causing intense pain and disability. These conditions lead to 30 million emergency room visits yearly, and the numbers are only increasing. However, diagnosing musculoskeletal issues can be challenging, especially in emergencies where quick decisions are necessary. Deep learning (DL) has shown promise in various medical applications. However, previous methods had poor performance and a lack of transparency in detecting shoulder abnormalities on X-ray images due to a lack of training data and better representation of features. This often resulted in overfitting, poor generalisation, and potential bias in decision-making. To address these issues, a new trustworthy DL framework has been proposed to detect shoulder abnormalities (such as fractures, deformities, and arthritis) using X-ray images. The framework consists of two parts: same-domain transfer learning (TL) to mitigate imageNet mismatch and feature fusion to reduce error rates and improve trust in the final result. Same-domain TL involves training pre-trained models on a large number of labelled X-ray images from various body parts and fine-tuning them on the target dataset of shoulder X-ray images. Feature fusion combines the extracted features with seven DL models to train several ML classifiers. The proposed framework achieved an excellent accuracy rate of 99.2%, F1Score of 99.2%, and Cohen's kappa of 98.5%. Furthermore, the accuracy of the results was validated using three visualisation tools, including gradient-based class activation heat map (Grad CAM), activation visualisation, and locally interpretable model-independent explanations (LIME). The proposed framework outperformed previous DL methods and three orthopaedic surgeons invited to classify the test set, who obtained an average accuracy of 79.1%. The proposed framework has proven effective and robust, improving generalisation and increasing trust in the final results. [ABSTRACT FROM AUTHOR]

Three‐dimensional (3D) organic–inorganic hybrid perovskites (OIHPs) have achieved tremendous success in direct X‐ray detection due to their high absorption coefficient and excellent carrier transport. However, owing to the centrosymmetry of classic 3D structures, these reported X‐ray detectors mostly require external electrical fields to run, resulting in bulky overall circuitry, high energy consumption, and operational instability. Herein, we first report the unprecedented radiation photovoltage in 3D OIHP for efficient self‐driven X‐ray detection. Specifically, the 3D polar OIHP MhyPbBr3 (1, Mhy=methylhydrazine) shows an intrinsic radiation photovoltage (0.47 V) and large mobility‐lifetime product (1.1×10−3 cm2 V−1) under X‐ray irradiation. Strikingly, these excellent physical characteristics endow 1 with sensitive self‐driven X‐ray detection performance, showing a considerable sensitivity of 220 μC Gy−1 cm−2, which surpasses those of most self‐driven X‐ray detectors. This work first explores highly sensitive self‐driven X‐ray detection in 3D polar OIHPs, shedding light on future practical applications. [ABSTRACT FROM AUTHOR]

Three‐dimensional (3D) organic–inorganic hybrid perovskites (OIHPs) have achieved tremendous success in direct X‐ray detection due to their high absorption coefficient and excellent carrier transport. However, owing to the centrosymmetry of classic 3D structures, these reported X‐ray detectors mostly require external electrical fields to run, resulting in bulky overall circuitry, high energy consumption, and operational instability. Herein, we first report the unprecedented radiation photovoltage in 3D OIHP for efficient self‐driven X‐ray detection. Specifically, the 3D polar OIHP MhyPbBr3 (1, Mhy=methylhydrazine) shows an intrinsic radiation photovoltage (0.47 V) and large mobility‐lifetime product (1.1×10−3 cm2 V−1) under X‐ray irradiation. Strikingly, these excellent physical characteristics endow 1 with sensitive self‐driven X‐ray detection performance, showing a considerable sensitivity of 220 μC Gy−1 cm−2, which surpasses those of most self‐driven X‐ray detectors. This work first explores highly sensitive self‐driven X‐ray detection in 3D polar OIHPs, shedding light on future practical applications. [ABSTRACT FROM AUTHOR]

Low‐dimensional organic–inorganic metal halides (OIMHs) have emerged as promising light emitters due to their broadband emission originating from self‐trapped excitons (STE), especially for Cu‐based OIMHs. Herein, Cu(I)‐based OIMH with a structure of (TPP)2Cu4I6·2DMSO (TPP stays for tetraphenylphosphonium, and DMSO – for dimethyl sulfoxide) has been synthesized, both in form of single crystals and as a microcrystalline powder. This compound exhibits a broadband green emission with a peak at 515 nm and a full width at half‐maximum of 78 nm, and a near‐unity photoluminescence quantum yield of 99.5%. Experimental data supported by theoretical calculations indicate that the STE emission is responsible for the green emission with a long lifetime of 2.53 µs. Down‐conversion light‐emitting device with a high luminous efficiency of 50 lm W−1 based on this compound have been fabricated, and white light has also been achieved with a high color rendering index of 96.7. Moreover, green emissive (TPP)2Cu4I6·2DMSO is utilized in scintillators for X‐ray detection and imaging, and as a luminescent ink for encryption applications. [ABSTRACT FROM AUTHOR]

This study proposes a wrapper‐based technique to improve the classification performance of chest infection (including COVID‐19) detection using X‐rays. Deep features were extracted using pretrained deep learning models. Ten optimization techniques, including poor and rich optimization, path finder algorithm, Henry gas solubility optimization, Harris hawks optimization, atom search optimization, manta‐ray foraging optimization, equilibrium optimizer, slime mold algorithm, generalized normal distribution optimization, and marine predator algorithm, were used to determine the optimal features using a support vector machine. Moreover, a network selection technique was used to select the deep learning models. An online chest infection detection X‐ray scan dataset was used to validate the proposed approach. The results suggest that the proposed wrapper‐based automatic deep learning network selection and feature optimization framework has a high classification rate of 97.7%. The comparative analysis further validates the credibility of the framework in COVID‐19 and other chest infection classifications, suggesting that the proposed approach can help doctors in clinical practice. [ABSTRACT FROM AUTHOR]

Buckwheat is a typical medicinal and edible crop with high nutritional value, and the application of appropriate fertilizer can improve the quality of buckwheat starch. The changes of internal structure and physicochemical characteristics of common buckwheat grain starch under low, medium, and high fertilization levels are investigated. With increasing fertilizer amount, the volume proportion is increased, while the granule size distribution is reduced significantly. All of the common buckwheat starch samples show a typical A‐type pattern in X‐ray diffraction detection. Furthermore, with the increase of fertilization level, the amylose content, retrogradation, and the ratio of 1045/1022 cm−1 reduce and then raise, but the relative crystallinity, the ratio of 1022/995 cm−1, light transmittance, solubility, and swelling power increase and then decrease. In comparison to other fertilization levels, common buckwheat starch at the medium level has greater pasting temperatures and gelatinization enthalpy but lower pasting viscosities. These results indicate the medium fertilization level of 180 (N), 115.2 (P), and 84.6 (K) kg h−1 m−2 is more suitable for buckwheat starch quality, which can give information for buckwheat cultivation. [ABSTRACT FROM AUTHOR]

Organic materials show good mechanical flexibility, easy processing, and large‐area manufacturing, while weak X‐ray absorption and low sensitivity for X‐ray scintillator media. As seen originally, this is a synergistic result of the lack of heavy elements in the molecule that can effectively truncate X‐rays and the massive dissipation of triplet excitons produced by molecular ionization. Herein, cocrystal with phosphorescence enhancement is found to be brilliant in addressing the shortcomings of organic scintillators. The results show that heavy atoms can be easily introduce into the donor unit of organic cocrystal to satisfy the X‐ray absorption and effectively activate the triplet excitons via promoting intersystem crossing (ISC). Moreover, the rational structural design of the acceptor molecule can achieve coupling with the donor for inhibiting the non‐radiative loss of the triplet exciton. Finally, the preferred PNPA (4,4′‐Dibromobiphenyl and N‐phenylnaphthalen‐2‐amine) cocrystals achieve record X‐ray‐induce exciton utilization and emit bright phosphorescent light. Meanwhile, the related device shows durable radiation stability, spatial resolution (>11 lp mm−1), low detection limit (<0.6 µGyair s−1), and effective dynamic imaging application. Hence, it is believed the organic cocrystal‐designed principle can provide guidance to develop advanced sensitive X‐ray scintillators in the future. [ABSTRACT FROM AUTHOR]

In this paper, an overview of wide-bandgap (WBG) semiconductors for radiation detection applications is given. The recent advancements in the fabrication of high-quality wafers have enabled remarkable WBG semiconductor device applications. The most common 4H-SiC, GaN, and β-Ga2O3 devices used for radiation detection are described. The 4H-SiC and GaN devices have already achieved exceptional results in the detection of alpha particles and neutrons, thermal neutrons in particular. While β-Ga2O3 devices have not yet reached the same level of technological maturity (compared to 4H-SiC and GaN), their current achievements for X-ray detection indicate great potential and promising prospects for future applications. [ABSTRACT FROM AUTHOR]

The automatic classification of X-ray detections is a necessary step in extracting astrophysical information from compiled catalogues of astrophysical sources. Classification is useful for the study of individual objects, statistics for population studies, as well as for anomaly detection, that is, the identification of new unexplored phenomena, including transients and spectrally extreme sources. Despite the importance of this task, classification remains challenging in X-ray astronomy due to the lack of optical counterparts and representative training sets. We develop an alternative methodology that employs an unsupervised machine learning approach to provide probabilistic classes to Chandra Source Catalog sources with a limited number of labelled sources, and without ancillary information from optical and infrared catalogues. We provide a catalogue of probabilistic classes for 8756 sources, comprising a total of 14 507 detections, and demonstrate the success of the method at identifying emission from young stellar objects, as well as distinguishing between small- and large-scale compact accretors with a significant level of confidence. We investigate the consistency between the distribution of features among classified objects and well-established astrophysical hypotheses such as the unified active galactic nucleus model. This provides interpretability to the probabilistic classifier. Code and tables are available publicly through GitHub. We provide a web playground for readers to explore our final classification at https://umlcaxs-playground.streamlit.app. [ABSTRACT FROM AUTHOR]

2D Dion–Jacobson (DJ) perovskites recently have attracted extensive attention for X‐ray detection owing to their structural rigidity and environmental stability. The chemical incorporation of π‐conjugation aromatic spacing cations into DJ phase perovskites will increase the rigidity of cation and electron cloud density between adjacent inorganic slabs, thus facilitating structural rigidity and charge transport. However, it is still a challenge to synthesize high‐quality single crystals of DJ phase perovskite with aromatic spacers for detecting X‐ray applications. Here, a new DJ phase perovskite by introducing π‐conjugated aromatic cation spacer, (4ABA)PbI4 (1, 4ABA = 4‐aminobenzylamine), eliminating the van der Waals gap is designed. High‐quality single crystals of 1 are grown via the facile solution method, exhibiting high resistivity (1.97 × 1011 Ω cm), low trap density (3.36 × 109 cm−3), and large carrier mobility‐lifetime product (1.03 × 10−3 cm2 V−1) under X‐ray illumination. Such remarkable physical characteristics endow single crystal 1 detector with high‐performance X‐ray detection including a high sensitivity of 572 µC Gyair−1cm−2, an ultralow detection limit of 7.50 nGyair s−1 and exceptional radiation stability. The X‐ray detection limit of 1 is over 700 times lower than that of routine medical diagnosis (5500 nGyair s−1), demonstrating potential applications in medical examination. [ABSTRACT FROM AUTHOR]

Recent developments in x-ray image based pulmonary nodule detection have achieved remarkable results. However, existing methods are focused on transferring off-the-shelf coarse-grained classification models and fine-grained detection models rather than developing a dedicated framework optimized for nodule detection. In this paper, we propose PN-DetX, which as we know is the first dedicated pulmonary nodule detection framework. PN-DetX incorporates feature fusion and self-attention into x-ray based pulmonary nodule detection tasks, achieving improved detection performance. Specifically, PN-DetX adopts CSPDarknet backbone to extract features, and utilizes feature augmentation module to fuse features from different levels followed by context aggregation module to aggregate semantic information. To evaluate the efficacy of our method, we collect a LA rge-scale P ulmonary NO dule D etection dataset, LAPNOD, comprising 2954 x-ray images along with expert-annotated ground truths. As we know, this is the first large-scale chest x-ray pulmonary nodule detection dataset. Experiments demonstrates that our method outperforms baseline by 3.8% mAP and 5.1% AP 0.5. The generality of our approach is also evaluated on the publicly available dataset NODE21. We aspire for our method to serve as an inspiration for future research in the field of pulmonary nodule detection. The dataset and codes will be made in public. [ABSTRACT FROM AUTHOR]

In the domain of AI-driven healthcare, deep learning models have markedly advanced pneumonia diagnosis through X-ray image analysis, thus indicating a significant stride in the efficacy of medical decision systems. This paper presents a novel approach utilizing a deep convolutional neural network that effectively amalgamates the strengths of EfficientNetB0 and DenseNet121, and it is enhanced by a suite of attention mechanisms for refined pneumonia image classification. Leveraging pre-trained models, our network employs multi-head, self-attention modules for meticulous feature extraction from X-ray images. The model's integration and processing efficiency are further augmented by a channel-attention-based feature fusion strategy, one that is complemented by a residual block and an attention-augmented feature enhancement and dynamic pooling strategy. Our used dataset, which comprises a comprehensive collection of chest X-ray images, represents both healthy individuals and those affected by pneumonia, and it serves as the foundation for this research. This study delves deep into the algorithms, architectural details, and operational intricacies of the proposed model. The empirical outcomes of our model are noteworthy, with an exceptional performance marked by an accuracy of 95.19%, a precision of 98.38%, a recall of 93.84%, an F1 score of 96.06%, a specificity of 97.43%, and an AUC of 0.9564 on the test dataset. These results not only affirm the model's high diagnostic accuracy, but also highlight its promising potential for real-world clinical deployment. [ABSTRACT FROM AUTHOR]

X-ray inspections of contraband are widely used to maintain public transportation safety and protect life and property when people travel. To improve detection accuracy and reduce the probability of missed and false detection, a contraband detection algorithm YOLOv8s-DCN-EMA-IPIO* based on YOLOv8s is proposed. Firstly, the super-resolution reconstruction method based on the SRGAN network enhances the original data set, which is more conducive to model training. Secondly, DCNv2 (deformable convolution net v2) is introduced in the backbone network and merged with the C2f layer to improve the ability of the feature extraction and robustness of the model. Then, an EMA (efficient multi-scale attention) mechanism is proposed to suppress the interference of complex background noise and occlusion overlap in the detection process. Finally, the IPIO (improved pigeon-inspired optimization), which is based on the cross-mutation strategy, is employed to maximize the convolutional neural network's learning rate to derive the optimal group's weight information and ultimately improve the model's detection and recognition accuracy. The experimental results show that on the self-built data set, the mAP (mean average precision) of the improved model YOLOv8s-DCN-EMA-IPIO* is 73.43%, 3.98% higher than that of the original model YOLOv8s, and the FPS is 95, meeting the deployment requirements of both high precision and real-time. [ABSTRACT FROM AUTHOR]