Histopathological image analysis is essential for diagnosis of malignant lesions. But even for experienced pathologists the diagnosis process is not trivial. Diagnostic concordance between specialists is on average only 75% and there is a lack of pathologists in many parts of the world. These limitations motivate the development of Computer-Aided Diagnosis (CAD) systems based on automated image analysis algorithms. Being a second opinion system, CAD systems shall reduce the workload of specialists, improve the diagnosis efficiency, and contribute to cost reduction. Furthermore, automated image analysis is a big data analysis tool that is of high interest for biomedical researchers.
The company TissueGnostics (TG) develops and offers In-Vitro Diagnostics (IVD)-compliant CAD systems for histological image analysis, which allow for quantification of multiple markers and cellular characteristics in tissues samples on the single cell level.
The Medical University of Vienna has a special focus on precision medicine and big data analysis. I. Ellinger and G. Dorffner are interested in using and further developing automated image analysis in their ongoing and future research projects with the ultimate aim to identify new biomarkers, better understand specific diseases and advance personalized medicine.
The partners collaborate in EU- and national funded research projects and develop deep learning-based algorithms for image classification and segmentation.