Purpose: To evaluate respiratory-triggered three-dimensional (3D) true steady-state free-precession (SSFP) projection magnetic resonance angiographic sequences with time-spatial labeling inversion pulse (Time-SLIP) fo...Purpose: To evaluate respiratory-triggered three-dimensional (3D) true steady-state free-precession (SSFP) projection magnetic resonance angiographic sequences with time-spatial labeling inversion pulse (Time-SLIP) for visualizing the hepatic arteries and to optimize the image acquisition protocol. Materials and Methods: A 1.5-T clinical magnetic resonance imager was used to perform abdominal magnetic resonance angiography (MRA) in 25 consecutive patients before transcatheter arterial chemoembolization or surgery. We compared two selective space-labeling inversion pulse (tag pulse) patterns (Patterns I and II, oblique and parallel tag pulses, respectively). Two experienced radiologists evaluated the number of hepatic arterial branches visible on the acquired MRA images, and the results were referenced with those on images from intra-arterial digital subtraction angiography. Results: Images were acquired from all patients. The two radiologists clearly visualized branches of the left and right hepatic arteries. More peripheral hepatic arterial branches were identified in MRA images captured by using tag pulse Pattern I than in those acquired by using Pattern II (P P > 0.05). Conclusion: Non-contrast-enhanced Time-SLIP hepatic MRA with true SSFP allowed selective visualization of peripheral hepatic vessels.展开更多
随着智能交通系统和共享出行服务的迅猛发展,人们对行程时间预测的需求日益增长,准确的行程时间预测已成为提升交通效率和优化用户体验的重要任务.传统的行程时间估计方法大多侧重于预测均值,提供点估计结果,忽略了复杂且动态变化的交...随着智能交通系统和共享出行服务的迅猛发展,人们对行程时间预测的需求日益增长,准确的行程时间预测已成为提升交通效率和优化用户体验的重要任务.传统的行程时间估计方法大多侧重于预测均值,提供点估计结果,忽略了复杂且动态变化的交通状况带来的不确定性.量化行程时间的不确定性以提供包含置信区间的结果,可以为用户和共享出行平台提供更全面可信的预测信息.但是,由于动态变化的路段通行时间分布以及多个路段通行时间不确定性的累积问题,难以准确量化行程时间的不确定性.为解决上述问题,提出了一种基于动态交通路况的行程时间预测与不确定性量化方法,设计了一个分布感知行程时间不确定性估计模型(Distribution Aware Travel Time Estimation,DATE),该模型包括路网板块化模块、全局分布感知器模块以及分布融合不确定性估计模块.该模型能在准确预测行程时间的同时,提供可靠的置信区间,全面量化不确定性.实验结果表明,DATE在两个真实数据集上的表现优于现有方法,且能有效提高行程时间预测的精度和可靠性,为智能交通系统提供更为可靠的决策支持.展开更多
文摘Purpose: To evaluate respiratory-triggered three-dimensional (3D) true steady-state free-precession (SSFP) projection magnetic resonance angiographic sequences with time-spatial labeling inversion pulse (Time-SLIP) for visualizing the hepatic arteries and to optimize the image acquisition protocol. Materials and Methods: A 1.5-T clinical magnetic resonance imager was used to perform abdominal magnetic resonance angiography (MRA) in 25 consecutive patients before transcatheter arterial chemoembolization or surgery. We compared two selective space-labeling inversion pulse (tag pulse) patterns (Patterns I and II, oblique and parallel tag pulses, respectively). Two experienced radiologists evaluated the number of hepatic arterial branches visible on the acquired MRA images, and the results were referenced with those on images from intra-arterial digital subtraction angiography. Results: Images were acquired from all patients. The two radiologists clearly visualized branches of the left and right hepatic arteries. More peripheral hepatic arterial branches were identified in MRA images captured by using tag pulse Pattern I than in those acquired by using Pattern II (P P > 0.05). Conclusion: Non-contrast-enhanced Time-SLIP hepatic MRA with true SSFP allowed selective visualization of peripheral hepatic vessels.
文摘随着智能交通系统和共享出行服务的迅猛发展,人们对行程时间预测的需求日益增长,准确的行程时间预测已成为提升交通效率和优化用户体验的重要任务.传统的行程时间估计方法大多侧重于预测均值,提供点估计结果,忽略了复杂且动态变化的交通状况带来的不确定性.量化行程时间的不确定性以提供包含置信区间的结果,可以为用户和共享出行平台提供更全面可信的预测信息.但是,由于动态变化的路段通行时间分布以及多个路段通行时间不确定性的累积问题,难以准确量化行程时间的不确定性.为解决上述问题,提出了一种基于动态交通路况的行程时间预测与不确定性量化方法,设计了一个分布感知行程时间不确定性估计模型(Distribution Aware Travel Time Estimation,DATE),该模型包括路网板块化模块、全局分布感知器模块以及分布融合不确定性估计模块.该模型能在准确预测行程时间的同时,提供可靠的置信区间,全面量化不确定性.实验结果表明,DATE在两个真实数据集上的表现优于现有方法,且能有效提高行程时间预测的精度和可靠性,为智能交通系统提供更为可靠的决策支持.
