目的探讨磁共振弥散加权成像信号特征在直肠癌浆膜层侵犯的应用。方法对53例直肠癌磁共振成像资料进行回顾性分析,根据术后病理切片标本将患者分为T2期与T3期2组。评估直肠肿瘤的信号强度比值(relative signal inten⁃sity,rSI)、直肠肿...目的探讨磁共振弥散加权成像信号特征在直肠癌浆膜层侵犯的应用。方法对53例直肠癌磁共振成像资料进行回顾性分析,根据术后病理切片标本将患者分为T2期与T3期2组。评估直肠肿瘤的信号强度比值(relative signal inten⁃sity,rSI)、直肠肿瘤的边界模糊、边缘欠光整及表面扩散系数与直肠浆膜层受侵犯的相关性。结果T2期组33例,T3期组20例。两组患者的直肠肿瘤rSI、直肠肿瘤边缘欠光整等方面差异有统计学意义(P<0.05)。受试者工作特征曲线分析结果显示,rSI、联合(rSI+边缘欠光整)诊断直肠癌浆膜层侵犯的敏感度和特异度分别为100%和57.6%、90%和66.7%,曲线下面积分别为0.826及0.903。结论rSI联合边缘欠光整与直肠癌浆膜层侵犯有相关性,对临床评估患者病情、指导临床治疗有一定的参考价值。展开更多
In this paper,we concentrate on a reconfigurable intelligent surface(RIS)-aided mobile edge computing(MEC)system to improve the offload efficiency with moving user equipments(UEs).We aim to minimize the energy consump...In this paper,we concentrate on a reconfigurable intelligent surface(RIS)-aided mobile edge computing(MEC)system to improve the offload efficiency with moving user equipments(UEs).We aim to minimize the energy consumption of all UEs by jointly optimizing the discrete phase shift of RIS,UEs’transmitting power,computing resources allocation,and the UEs’task offloading strategies for local computing and offloading.The formulated problem is a sequential decision making across multiple coherent time slots.Furthermore,the mobility of UEs brings uncertainties into the decision-making process.To cope with this challenging problem,the deep reinforcement learning-based Soft Actor-Critic(SAC)algorithm is first proposed to effectively optimize the discrete phase of RIS and the UEs’task offloading strategies.Then,the transmitting power and computing resource allocation can be determined based on the action.Numerical results demonstrate that the proposed algorithm can be trained more stably and perform approximately 14%lower than the deep deterministic policy gradient benchmark in terms of energy consumption.展开更多
文摘目的探讨磁共振弥散加权成像信号特征在直肠癌浆膜层侵犯的应用。方法对53例直肠癌磁共振成像资料进行回顾性分析,根据术后病理切片标本将患者分为T2期与T3期2组。评估直肠肿瘤的信号强度比值(relative signal inten⁃sity,rSI)、直肠肿瘤的边界模糊、边缘欠光整及表面扩散系数与直肠浆膜层受侵犯的相关性。结果T2期组33例,T3期组20例。两组患者的直肠肿瘤rSI、直肠肿瘤边缘欠光整等方面差异有统计学意义(P<0.05)。受试者工作特征曲线分析结果显示,rSI、联合(rSI+边缘欠光整)诊断直肠癌浆膜层侵犯的敏感度和特异度分别为100%和57.6%、90%和66.7%,曲线下面积分别为0.826及0.903。结论rSI联合边缘欠光整与直肠癌浆膜层侵犯有相关性,对临床评估患者病情、指导临床治疗有一定的参考价值。
基金supported by the National Natural Science Foundation of China(No.62101277 and No.U20B2039)the Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu(No.BK20212001)。
文摘In this paper,we concentrate on a reconfigurable intelligent surface(RIS)-aided mobile edge computing(MEC)system to improve the offload efficiency with moving user equipments(UEs).We aim to minimize the energy consumption of all UEs by jointly optimizing the discrete phase shift of RIS,UEs’transmitting power,computing resources allocation,and the UEs’task offloading strategies for local computing and offloading.The formulated problem is a sequential decision making across multiple coherent time slots.Furthermore,the mobility of UEs brings uncertainties into the decision-making process.To cope with this challenging problem,the deep reinforcement learning-based Soft Actor-Critic(SAC)algorithm is first proposed to effectively optimize the discrete phase of RIS and the UEs’task offloading strategies.Then,the transmitting power and computing resource allocation can be determined based on the action.Numerical results demonstrate that the proposed algorithm can be trained more stably and perform approximately 14%lower than the deep deterministic policy gradient benchmark in terms of energy consumption.
