BACKGROUND The risk of gastric cancer increases in patients with Helicobacter pylori-associated chronic atrophic gastritis(CAG).X-ray examination can evaluate the condition of the stomach,and it can be used for gastri...BACKGROUND The risk of gastric cancer increases in patients with Helicobacter pylori-associated chronic atrophic gastritis(CAG).X-ray examination can evaluate the condition of the stomach,and it can be used for gastric cancer mass screening.However,skilled doctors for interpretation of X-ray examination are decreasing due to the diverse of inspections.AIM To evaluate the effectiveness of stomach regions that are automatically estimated by a deep learning-based model for CAG detection.METHODS We used 815 gastric X-ray images(GXIs)obtained from 815 subjects.The ground truth of this study was the diagnostic results in X-ray and endoscopic examinations.For a part of GXIs for training,the stomach regions are manually annotated.A model for automatic estimation of the stomach regions is trained with the GXIs.For the rest of them,the stomach regions are automatically estimated.Finally,a model for automatic CAG detection is trained with all GXIs for training.RESULTS In the case that the stomach regions were manually annotated for only 10 GXIs and 30 GXIs,the harmonic mean of sensitivity and specificity of CAG detection were 0.955±0.002 and 0.963±0.004,respectively.CONCLUSION By estimating stomach regions automatically,our method contributes to the reduction of the workload of manual annotation and the accurate detection of the CAG.展开更多
Nuclear radiation detectors are critical to transient nuclear reaction imaging,medical diagnostic imaging,security checks,industry inspection,and so forth,with many potential uses limited by scintillator dimensions.Cu...Nuclear radiation detectors are critical to transient nuclear reaction imaging,medical diagnostic imaging,security checks,industry inspection,and so forth,with many potential uses limited by scintillator dimensions.Current scintillator crystals are limited by the long-standing issues of hetero-crystalline formation and consequently inferior crystal dimensions and quality.Particularly,the hybrid organic-inorganic perovskites(HOIPs)exhibit scintillation capability under X-ray and fast neutrons within a single framework,owing to the presence of heavy elements and high hydrogen density groups,respectively.However,the achievement of high-performance and large-area imaging by HOIPs scintillators is impeded by the crystal growth technology.Herein,we propose an optimal crystal growth strategy and obtain an inch-sized high-quality(PEA)2PbBr4 single crystals(SCs)with a record dimension of 4.60 cm×3.80 cm×0.19 cm.Their application as synergistic scintillators in high-energy rays and charged particles detection are investigated,which exhibit high light yield(38600 photons MeV^(-1))and ultra-fast decay times that are 4.89,27.98,and 3.84 ns under the 375-nm laser,γ-ray,andαparticles,respectively.Moreover,the(PEA)2PbBr4 SCs demonstrate a remarkably high spatial resolution of 23.2 lp mm×1(at MTF=20%)for X-ray and 2.00 lp mm^(-1)for fast neutrons,surpassing the reported perovskites scintillators.展开更多
文摘BACKGROUND The risk of gastric cancer increases in patients with Helicobacter pylori-associated chronic atrophic gastritis(CAG).X-ray examination can evaluate the condition of the stomach,and it can be used for gastric cancer mass screening.However,skilled doctors for interpretation of X-ray examination are decreasing due to the diverse of inspections.AIM To evaluate the effectiveness of stomach regions that are automatically estimated by a deep learning-based model for CAG detection.METHODS We used 815 gastric X-ray images(GXIs)obtained from 815 subjects.The ground truth of this study was the diagnostic results in X-ray and endoscopic examinations.For a part of GXIs for training,the stomach regions are manually annotated.A model for automatic estimation of the stomach regions is trained with the GXIs.For the rest of them,the stomach regions are automatically estimated.Finally,a model for automatic CAG detection is trained with all GXIs for training.RESULTS In the case that the stomach regions were manually annotated for only 10 GXIs and 30 GXIs,the harmonic mean of sensitivity and specificity of CAG detection were 0.955±0.002 and 0.963±0.004,respectively.CONCLUSION By estimating stomach regions automatically,our method contributes to the reduction of the workload of manual annotation and the accurate detection of the CAG.
基金National Natural Science Foundation of China,Grant/Award Numbers:12205016,12305205,62304171Guangdong Basic and Applied Basic Research Fund,Grant/Award Number:2023A1515030084+4 种基金Open Project Program of Wuhan National Laboratory for Optoelectronics,Grant/Award Number:2022WNLOKF004Qin Chuangyuan Innovation and Entrepreneurship Project,Grant/Award Number:QCYRCXM-2022-316Fund of Innovation Centre for Radiation Application,Grant/Award Number:KFZC2023020902Fundamental Research Funds for the Central Universities,Grant/Award Number:ZYTS24056China Postdoctoral Science Foundation,Grant/Award Number:2022M722500。
文摘Nuclear radiation detectors are critical to transient nuclear reaction imaging,medical diagnostic imaging,security checks,industry inspection,and so forth,with many potential uses limited by scintillator dimensions.Current scintillator crystals are limited by the long-standing issues of hetero-crystalline formation and consequently inferior crystal dimensions and quality.Particularly,the hybrid organic-inorganic perovskites(HOIPs)exhibit scintillation capability under X-ray and fast neutrons within a single framework,owing to the presence of heavy elements and high hydrogen density groups,respectively.However,the achievement of high-performance and large-area imaging by HOIPs scintillators is impeded by the crystal growth technology.Herein,we propose an optimal crystal growth strategy and obtain an inch-sized high-quality(PEA)2PbBr4 single crystals(SCs)with a record dimension of 4.60 cm×3.80 cm×0.19 cm.Their application as synergistic scintillators in high-energy rays and charged particles detection are investigated,which exhibit high light yield(38600 photons MeV^(-1))and ultra-fast decay times that are 4.89,27.98,and 3.84 ns under the 375-nm laser,γ-ray,andαparticles,respectively.Moreover,the(PEA)2PbBr4 SCs demonstrate a remarkably high spatial resolution of 23.2 lp mm×1(at MTF=20%)for X-ray and 2.00 lp mm^(-1)for fast neutrons,surpassing the reported perovskites scintillators.
