The Lübeck research area "Artificial Intelligence in Medical Image Processing“ develops adaptive medical image processing methods to support medical diagnostics and therapy. In hybrid image processing systems, methods of artificial intelligence are combined with conventional medical image processing methods and visualization techniques to facilitate medical support.
The main research focus is on machine learning methods and deep neural networks for the automatic analysis and recognition of different disease patterns, lesions, biomarkers, organs, tissues, etc. in medical images and image sequences. The researchers are also investigating the possibilities for image-based prediction of individual disease progression and personalized risk assessment to support therapy decision making using machine learning methods.
Further research and development fields of the research area are:
A concrete example is presented in the software demonstration on AI-based tumor segmentation. This involves the pixel-level precise annotation, also called segmentation, of brain tumors in spatial 3D MRI image sequences, which can be automated reliably and time-efficiently through the use of AI methods. Deep Learning-based image analysis can automatically determine essential parameters of the brain tumor such as its volume, position and intensity values, which form the basis for a quantitative evaluation and assessment of the tumor’s development.
The research area is part of the DFKI branch in Lübeck, which is supported by the state of Schleswig-Holstein.