We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1-weighted magnetic resonance images. DeepNAT is an end-to-end learning-based approach to brain segmentation that jointly learns an abstract feature representation and a multi-class classification. We propose a 3D patch-based approach, where we do not only predict the center voxel of ...

Random distortions naturally affect images taken through atmospheric turbulence or wavy water. They pose new 3D recovery problems. Distortions are caused by the volumetric field of turbulent air or the 3D shape of water waves. We show methods that recover these 3D distorting media. Moreover, it is possible to triangulate objects beyond the refracting medium. Applications include sensing and stu...

Purpose: Precise delineation of organs at risk is a crucial task in radiotherapy treatment planning when aiming at delivering high dose to the tumour while sparing healthy tissues. In recent years algorithms showed high performance and the possibility to automate this task for many organs. However, for some organs precise delineation remains challenging, even for human experts. One of them is t...

In a single-hop network with multiple relays, selecting a single node to aid in the transmission between a source and a destination outperforms both traditional orthogonal transmissions and distributed space-time codes. The usage of multiple hops will further improve the wireless communication. This paper presents an energy efficient selection of cooperative nodes with respect to their geograph...

Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. f...

ÐRecursive Diagonal Torus (RDT), a class of interconnection network is proposed for massively parallel computers with up to 2 nodes. By making the best use of a recursively structured diagonal mesh (torus) connection, the RDT has a smaller diameter (e.g., it is 11 for 2 nodes) with a smaller number of links per node (i.e., 8 links per node) than those of the hypercube. A simple routing algorith...

HLP (hub location problem) tries to find locations of hub facilities and assignment of nodes to extended facilities. Hubs are facilities to collect, arrange, and distribute commodities in telecommunication networks, cargo delivery systems, etc. Hubs are very crucial and their inaccessibility impresses on network whole levels. In this paper, first, total reliability of the network is defined bas...

This paper aims to propose a three-dimensional (3D) point process that can be employed generally deploy unmanned aerial vehicles (UAVs) in large-scale 3D cellular network and tractably analyze the fundamental network-wide performances of network. The proposed is devised based on 2D marked Poisson which each its random mark uniquely correspond projection altitude process, respectively. We study ...