Automated image analysis and quantification

Main challenge is to make the translation between what is required in clinical practice and life-sciences on the one hand, and the recent technological developments on the other hand. How do you teach a computer “to see with the prior experience of a human, and with the accuracy of a machine?”

The Division of Image Processing, in Dutch abbreviated as the LKEB (Laboratorium voor Klinische en Experimentele Beeldverwerking), is a computer science research group within the Department of Radiology, LUMC. The director of LKEB is Prof. Boudewijn P.F. Lelieveldt PhD.  We perform fundamental and applied research towards fully automated quantification of biomedical imaging data. Our methodological research focuses on artificial intelligence and machine learning technologies such as deep learning, with a focus on medical imaging and omics applications. We combine these with general computer science methods and mathematical modeling. Our work encompasses segmentation, classification, image registration, quantification, validation, medical visualization, radiomics and dimensionality reduction.

To bring our research results close to a clinical end-user we develop high quality software. We aim to impact the healthcare system by bringing research results close to the clinic, through collaboration with clinicians as well as with industry. Our scientific programmers therefore work through a formalized Software Development Process (SDP), often in close collaboration with medical software and device industry. This has led to a number of commercially successful clinical software packages, and spinoff to a number of large medical imaging vendors. We also host and maintain open source image registration software packages such as Mass, Vesselmass, elastix and Cytosplore.