For diagnosing patients with ischemic cerebrovascular disease, non-invasive count-based method with (15)O(2) and H (2) (15) O positron-emission tomography (PET) data is widely used to measure asymmetric increases in o...
详细信息
For diagnosing patients with ischemic cerebrovascular disease, non-invasive count-based method with (15)O(2) and H (2) (15) O positron-emission tomography (PET) data is widely used to measure asymmetric increases in oxygen extraction fraction (OEF). For shortening study time, we have proposed dual-tracer autoradiographic (DARG) protocol in which (15)O(2) gas and C(15)O(2) gas are sequentially administrated within short period. In this paper, we evaluated feasibility of the non-invasive count-based method with the DARG protocol. Twenty-three patients [67.8 +/- A 9.9 (mean +/- A SD) years] with chronic unilateral brain infarction were examined by the use of measurements of asymmetric OEF elevation. As DARG protocol, (15)O(2) and C(15)O(2) gases were inhaled with 5-min interval and dynamic PET data were acquired for 8 min. Quantitative OEF (qOEF) image was computed with PET data and arterial input function. Ratio image of (15)O(2) and C(15)O(2) phases of PET data was computed as count-based OEF (cbOEF) image. The asymmetric indices (AI) of qOEF (qOEF-AI) and cbOEF (cbOEF-AI) were obtained from regions of interest symmetric placed on left and right sides of cerebral hemisphere. To optimize the summation time of PET data for the cbOEF image, qOEF and cbOEF images with various summation times were compared. Image quality of cbOEF image was better than that of qOEF image. The best correlation coefficient of 0.94 was obtained when the cbOEF image was calculated from 0 to 180 s of (15)O(2) summed image and 340 to 440 s of C(15)O(2) summed image. Using the appropriate summation time, we obtained the cbOEF image with good correlation with qOEF image, which suggests non-invasive cbOEF image can be used for evaluating the degree of misery perfusion in patients with chronic unilateral brain infarction. The count-based method with DARG protocol has a potential to dramatically reduce the examination time of (15)O PET study.
Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)ar...
详细信息
Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.
暂无评论