Cognition Network Technology – A Novel Multimodal Image Analysis Technique for Automatic Identification and Quantification of Biological Image Contents

Abstract

Detailed knowledge about the morphology of a biological system gives valuable and precious information about its functions and dynamics. Improvements in imaging technologies enable users to acquire thousands of images of different modalities with different resolutions from biological systems. Such images show subcellular structures, cells, cell groups, tissue, organs and organisms. On the other hand, image data are of high value only if they can be transformed into valuable knowledge. Therefore, the problem of automatic information extraction from such images has become a prime priority in academic and industrial biomedical research and development. The Definiens Cognition Network Technology (CNT) solves that problem by simulating human cognition processes using knowledge-based and context-dependent processing. It is represented in its entirety by the image data, image processing methods, image derived layers, and image objects and their definitions in a unified model. CNT incorporates elements from semantic networks, description logics and functional programming. We applied this technology to imagery of different magnification, resolution and different modalities such as electron micrographs, optical microscopy and modalities in the area of radiology. Using a unified approach with a scale- and problem-invariant processing and knowledge model is a prerequisite for studying complex hierarchical systems such as biological systems.