Tissue Phenomics for prognostic biomarker discovery in low- and intermediate-risk prostate cancer.

Tissue Phenomics is the discipline of mining tissue images to identify patterns that are related to clinical outcome providing potential prognostic and predictive value. This involves the discovery process from assay development, image analysis, and data mining to the final interpretation and validation of the findings. Importantly, this process is not linear but allows backward steps and optimization loops over multiple sub-processes. We provide a detailed description of the Tissue Phenomics methodology while exemplifying each step on the application of prostate cancer recurrence prediction. In particular, we automatically identified tissue-based biomarkers having significant prognostic value for low- and intermediate-risk prostate cancer patients (Gleason scores 6-7b) after radical prostatectomy. We found that promising phenes were related to CD8(+) and CD68(+) cells in the microenvironment of cancerous glands in combination with the local micro-vascularization. Recurrence prediction based on the selected phenes yielded accuracies up to 83% thereby clearly outperforming prediction based on the Gleason score. Moreover, we compared different machine learning algorithms to combine the most relevant phenes resulting in increased accuracies of 88% for tumor progression prediction. These findings will be of potential use for future prognostic tests for prostate cancer patients and provide a proof-of-principle of the Tissue Phenomics approach.

Automated analysis and detailed quantification of biomedical images using Definiens Cognition Network Technology.

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.

Object-oriented image analysis for high content screening: detailed quantification of cells and sub cellular structures with the Cellenger software.

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.