3D Reconstruction of Medical Images from Slices Automatically Landmarked with Growing Neural Models

In this study, we utilise a novel approach to segment out the ventricular system in a series of high resolution T1-weighted MR images. We present a brain ventricles fast reconstruction method. The method is based on the processing of brain sections and establishing a fixed number of landmarks onto those sections to reconstruct the ventricles 3D surface. Automated landmark extraction is accomplished through the use of the self-organising network, the growing neural gas (GNG), which is able to topographically map the low dimensionality of the network to the high dimensionality of the contour manifold without requiring a priori knowledge of the input space structure. Moreover, our GNG landmark method is tolerant to noise and eliminates outliers. Our method accelerates the classical surface reconstruction and filtering processes. The proposed method offers higher accuracy compared to methods with similar efficiency as Voxel Grid.

The role of geographical proximity in the establishment and development of science parks – evidence from Nanjing, China

The emergence of science parks is a relatively new phenomenon in China. Apart from the widely debated topics of university–industry linkages, collaboration among firms and spontaneous/policy-driven science parks, the development of science parks in China also has several distinguishing characteristics, such as their ambiguous linkage with urban expansion and their hierarchical structuring pattern. This paper attempts to discuss the motivation and efficiency of spatial proximity in science park development and to explore the role of universities in science parks, the function of science parks as a government project and a case study of location choice by on-site firms. The qualitative analysis, based on in-depth interviews with tenant firm managers and district-level government officers in Jiangning, Nanjing, is used as a basis for discussion.