Medical imaging examination on patients usually involves more than one imaging modalities, such as Computed Tomography (CT), Magnetic Resonance (MR) and Positron Emission Tomography(PET) imaging. Multimodal imaging allows examiners to benefit from the advantage of each modalities. For example, for Abdominal Aortic Aneurysm, CT imaging shows calcium deposits in the aorta clearly while MR imaging distinguishes thrombus and soft tissues better.1 Analysing and segmenting both CT and MR images to combine the results will greatly help radiologists and doctors to treat the disease. In this work, we present methods on using deep neural network models to perform such multi-modal medical image segmentation.
As CT image and MR image of the abdominal area cannot be well registered due to non-affine deformations, a naive approach is to train CT and MR segmentation network separately. However, such approach is time-consuming and resource-inefficient. We propose a new approach to fuse the high-level part of the CT and MR network together, hypothesizing that neurons recognizing the high level concepts of Aortic Aneurysm can be shared across multiple modalities. Such network is able to be trained end-to-end with non-registered CT and MR image using shorter training time. Moreover network fusion allows a shared representation of Aorta in both CT and MR images to be learnt. Through experiments we discovered that for parts of Aorta showing similar aneurysm conditions, their neural presentations in neural network has shorter distances. Such distances on the feature level is helpful for registering CT and MR image.
Mobile Ad-Hoc Networks (MANETs), that do not rely on pre-existing infrastructure and that can adapt rapidly to
changes in their environment, are coming into increasingly wide use in military applications. At the same time, the large
computing power and memory available today even for small, mobile devices, allows us to build extremely large,
sophisticated and complex networks. Such networks, however, and the software controlling them are potentially
vulnerable to catastrophic failures because of their size and complexity. Biological networks have many of these same
characteristics and are potentially subject to the same problems. But in successful organisms, these biological networks
do in fact function well so that the organism can survive. In this paper, we present a MANET architecture developed
based on a feature, called homeostasis, widely observed in biological networks but not ordinarily seen in computer
networks. This feature allows the network to switch to an alternate mode of operation under stress or attack and then
return to the original mode of operation after the problem has been resolved. We explore the potential benefits such an
architecture has, principally in terms of the ability to survive radical changes in its environment using an illustrative