23:T492,In November 2012 EEFIT launched its first ever return mission to an earthquake affected site. The L’Aquila Earthquake site was chosen as this is a recent European event of interest to the UK and European earthquake engineering community. The main aims of this return mission were to document the earthquake recovery process and this paper presents an overview of the post-disaster emergency phase and transition to reconstruction in the Aquila area after the earthquake. It takes an earthquake engineering perspective, highlighting areas mainly of interest to the fields of structural/seismic engineering and reconstruction management. Within the paper, reference is made to published literature, but also to data collected in the field during the return mission that would not otherwise have been available. The paper presents some specific observations and lessons learned from the L’Aquila return mission. However, in light of current international efforts in conducting return missions, the paper ends with some reflections on the value that return missions can provide to the field of earthquake engineering in general, based on the EEFIT L’Aquila experience.24:T4db,X-ray computed tomography (CT) reconstructs cross-sectional images from projection data. However, ionizing X-ray radiation associated with CT scanning might induce cancer and genetic damage and raises public concerns. Therefore, the reduction of radiation dose has attracted major attention. Few-view CT image reconstruction is an important topic to reduce the radiation dose. Recently, data-driven algorithms have shown great potential to solve the few-view CT problem. In this paper, we develop a dual network architecture (DNA) for reconstructing images directly from sinograms. In the proposed DNA method, a point-wise fully-connected layer learns the backprojection process requesting significantly less memory than the prior art and with O(C×N×N_C) parameters where N and N_c denote the dimension of reconstructed images and number of projections respectively. C is an adjustable parameter that can be set as low as 1. Our experimental results demonstrate that DNA produces a competitive performance over the other state-of-the-art methods.Interestingly, natural images can be used to pre-train DNA to avoid overfitting when the amount of real patient images is limited.

#	Concept	H-Index	Publications	Citations
1	Health Sciences	3	3	121
2	Engineering	2	2	93
3	Medicine	2	2	63
4	Civil Engineering	1	1	35
5	Brachytherapy	1	1	48

	Year	Citations

About

Top Concepts