Mobile CrowdSensing(MCS)is a promising sensing paradigm that recruits users to cooperatively perform sensing tasks.Recently,unmanned aerial vehicles(UAVs)as the powerful sensing devices are used to replace user partic...Mobile CrowdSensing(MCS)is a promising sensing paradigm that recruits users to cooperatively perform sensing tasks.Recently,unmanned aerial vehicles(UAVs)as the powerful sensing devices are used to replace user participation and carry out some special tasks,such as epidemic monitoring and earthquakes rescue.In this paper,we focus on scheduling UAVs to sense the task Point-of-Interests(PoIs)with different frequency coverage requirements.To accomplish the sensing task,the scheduling strategy needs to consider the coverage requirement,geographic fairness and energy charging simultaneously.We consider the complex interaction among UAVs and propose a grouping multi-agent deep reinforcement learning approach(G-MADDPG)to schedule UAVs distributively.G-MADDPG groups all UAVs into some teams by a distance-based clustering algorithm(DCA),then it regards each team as an agent.In this way,G-MADDPG solves the problem that the training time of traditional MADDPG is too long to converge when the number of UAVs is large,and the trade-off between training time and result accuracy could be controlled flexibly by adjusting the number of teams.Extensive simulation results show that our scheduling strategy has better performance compared with three baselines and is flexible in balancing training time and result accuracy.展开更多
OBJECTIVES:The objectives of this study were to investigate the clinical application of^(18)F-fluorodeoxyglucose positron emission tomography/computed tomography(^(18)F-FDG-PET/CT)combined with CT angiography(CTA)fusi...OBJECTIVES:The objectives of this study were to investigate the clinical application of^(18)F-fluorodeoxyglucose positron emission tomography/computed tomography(^(18)F-FDG-PET/CT)combined with CT angiography(CTA)fusion images at diagnosis and assessment in large-vessel vasculitis(LVV).MATERIALS AND METHODS:Forty-six patients with LVV who underwent both^(18)F-FDG-PET/CT and CTA procedures were studied in the Second Hospital of Harbin Medical University from September 2019 to June 2022,and the clinical disease activity of patients was judged by the Physician Global Assessment.Clinical data,acute-phase reactants(APRs),and imaging data were collected.Meanwhile,the APRS must be obtained within 1 week of^(18)F-FDG-PET/CT.^(18)F-FDG-PET/CT was primarily used to evaluate LVV activity,while CTA was primarily used to observe morphological changes in arteries,including arterial wall thickening,narrowing,and corresponding complications.PET/CT images were evaluated by two nuclear medicine physicians,both of them unaware of the patients’laboratory tests and clinical signs.Two nuclear medicine specialists evaluated the PET/CT images and PET/CTA images,who were blinded to the patients’information.The concordance of two physicians in the LVV visual grading scale was studied by calculating the Cohen’s kappa index(k)which evaluates the power of concordance.The paired t-test was used to analyze the differences between PET/CTA images and PET/CT images.RESULTS:The sensitivity and specificity of the semi-quantitative analysis to assess LVV activity was 94.1%and 93.1%,respectively,when a cutoff of the mean SUVmax/SUVmeanliver of 1.15.It was found that the images obtained after delayed phase were clearer and the contrast between the arterial wall and the lumen was higher in 19 patients.We also concluded that PET/CTA examinations were able to detect more lesion sites compared to PET/CT examinations in 28 patients(P<0.001),especially for patients with long-term treatment,and the interpretation of PET/CTA images took less time than PET/CT images(P<0.001),ultimately achieving a shorter time,more comprehensive and accurate interpretation.CONCLUSION:Although^(18)F-FDG-PET/CT can assess the activity of LVV,it is poor at observing morphological changes in arteries.The use of^(18)F-FDG-PET/CTA imaging scans in LVV can accurately assess disease activity while at the same time providing a comprehensive,accurate,and efficient determination of disease severity,allowing patients to receive comprehensive diagnostic information from PET/CTA examination.展开更多
基金supported by the Innovation Capacity Construction Project of Jilin Development and Reform Commission(2020C017-2)Science and Technology Development Plan Project of Jilin Province(20210201082GX)。
文摘Mobile CrowdSensing(MCS)is a promising sensing paradigm that recruits users to cooperatively perform sensing tasks.Recently,unmanned aerial vehicles(UAVs)as the powerful sensing devices are used to replace user participation and carry out some special tasks,such as epidemic monitoring and earthquakes rescue.In this paper,we focus on scheduling UAVs to sense the task Point-of-Interests(PoIs)with different frequency coverage requirements.To accomplish the sensing task,the scheduling strategy needs to consider the coverage requirement,geographic fairness and energy charging simultaneously.We consider the complex interaction among UAVs and propose a grouping multi-agent deep reinforcement learning approach(G-MADDPG)to schedule UAVs distributively.G-MADDPG groups all UAVs into some teams by a distance-based clustering algorithm(DCA),then it regards each team as an agent.In this way,G-MADDPG solves the problem that the training time of traditional MADDPG is too long to converge when the number of UAVs is large,and the trade-off between training time and result accuracy could be controlled flexibly by adjusting the number of teams.Extensive simulation results show that our scheduling strategy has better performance compared with three baselines and is flexible in balancing training time and result accuracy.
文摘OBJECTIVES:The objectives of this study were to investigate the clinical application of^(18)F-fluorodeoxyglucose positron emission tomography/computed tomography(^(18)F-FDG-PET/CT)combined with CT angiography(CTA)fusion images at diagnosis and assessment in large-vessel vasculitis(LVV).MATERIALS AND METHODS:Forty-six patients with LVV who underwent both^(18)F-FDG-PET/CT and CTA procedures were studied in the Second Hospital of Harbin Medical University from September 2019 to June 2022,and the clinical disease activity of patients was judged by the Physician Global Assessment.Clinical data,acute-phase reactants(APRs),and imaging data were collected.Meanwhile,the APRS must be obtained within 1 week of^(18)F-FDG-PET/CT.^(18)F-FDG-PET/CT was primarily used to evaluate LVV activity,while CTA was primarily used to observe morphological changes in arteries,including arterial wall thickening,narrowing,and corresponding complications.PET/CT images were evaluated by two nuclear medicine physicians,both of them unaware of the patients’laboratory tests and clinical signs.Two nuclear medicine specialists evaluated the PET/CT images and PET/CTA images,who were blinded to the patients’information.The concordance of two physicians in the LVV visual grading scale was studied by calculating the Cohen’s kappa index(k)which evaluates the power of concordance.The paired t-test was used to analyze the differences between PET/CTA images and PET/CT images.RESULTS:The sensitivity and specificity of the semi-quantitative analysis to assess LVV activity was 94.1%and 93.1%,respectively,when a cutoff of the mean SUVmax/SUVmeanliver of 1.15.It was found that the images obtained after delayed phase were clearer and the contrast between the arterial wall and the lumen was higher in 19 patients.We also concluded that PET/CTA examinations were able to detect more lesion sites compared to PET/CT examinations in 28 patients(P<0.001),especially for patients with long-term treatment,and the interpretation of PET/CTA images took less time than PET/CT images(P<0.001),ultimately achieving a shorter time,more comprehensive and accurate interpretation.CONCLUSION:Although^(18)F-FDG-PET/CT can assess the activity of LVV,it is poor at observing morphological changes in arteries.The use of^(18)F-FDG-PET/CTA imaging scans in LVV can accurately assess disease activity while at the same time providing a comprehensive,accurate,and efficient determination of disease severity,allowing patients to receive comprehensive diagnostic information from PET/CTA examination.
