NET : A framework for the vectorization and examination of network data
The Network Extraction Tool (NET) is especially designed for high-throughput semi-automated analysis of biological datasets containing networks of very large sizes. The framework starts with the segmentation of the image and then proceeds to vectorization using methodologies from optical character recognition. After a series of steps to clean and improve the quality of the extracted data the framework produces a graph in which the network is represented only by its nodes and neighborhood-relations. The networks extracted by NET are comparable to manually extracted networks with regards to their quality but take significantly less time to generate. NET provides tools for some statistical analysis of the network properties, such as the number of nodes or total network length, and other more complex metrics can be calculated by importing the vectorized network to specialized network analysis packages. Parallel to NET, the Graph-edit-GUI (GeGUI ) facilitates manual correction of pseudo-2D networks which may contain artifacts or pseudo-junctions due to branches crossing each other.