No abstract

No abstract

Biomedicine has seen tremendous advances in the field of image acquisition. The generation of digital images of high information content has become so straightforward and efficient that the volume of images accumulating in biomedical disciplines is posing significant challenges. Until now, conventional image analysis solutions are generally pixel-based and limited in the amount of information that they extract. However, a software system enabling the complex analysis of biomedical images should not impose restrictions on detection, classification and quantification of structures, but rather allow unlimited freedom to answer exhaustively all conceivable questions about the interactions and relationships between structures. Crucial to this is the precise and robust segmentation of relevant structures in digital micrographs. This challenge involves bringing structure, morphology and context into play. Based on the Definiens Cognition Network Technology, solutions have been deployed for use in biomedicine. The technology is object-oriented, multi-scale, context-driven and knowledge-based. Images are interpreted on the properties of networked image objects, which results in numerous advantages. This approach enables users to bring in detailed expert knowledge and enables complex analyses to be performed with unprecedented accuracy, even on poor quality data or for structures exhibiting heterogeneous properties or variable phenotypes. Extracted structures are the basis for detailed morphometric, structural and relational measurements which can be exported for each individual structure. These data can be used for decision support or correlated against experimental or molecular data, thus bridging classical biomedicine with molecular biology. An overview of the technology is provided with examples from different biomedical applications.

Background: Detailed image analysis still is a considerable bottleneck for many cellular assays, and automated solutions to the problem are desirable. However, dealing with the complexity and variability of structures in cellular images makes detailed and reliable analysis a nontrivial task. Methods: Therefore, based on the object‐oriented image analysis approach, a novel image analysis technology, a flexible and reliable system for image analysis in cellular assays was developed. It contains a library of predefined, adaptable modules, each of them developed for a specific analysis task. The system can be configured easily by combining appropriate modules and adapting them interactively to the specific image data, if necessary. By representing cells and sub cellular structures within a network of interlinked image objects, a large number of parameters can be derived that describe shape, intensity, and relevant structural and relational aspects of any chosen class of structures. Results: Thus, multi‐parameter analysis and multiplexing are supported. A sample application based on this approach demonstrates that GFP signals can be distinguished based on their properties and the relative location within the cell. © 2006 International Society for Analytical Cytology