Medical Imaging Research Center
ESAT/PSI/MIC (MIC = Medical Image Computing) is since long active in the field of (bio)medical imaging research. One of its main strengths is its unique setting in the Medical Imaging Research Center (MIRC), an interdisciplinary research center with core location in the University Hospital Gasthuisberg. MIC aims to be a European top research group, reflected by an outstanding publication record and an extensive valorization with respect to international collaboration, acquired patents, spin-off creation and visibility in general.
WHAT do we do?
- MIC conducts application-driven research on quantitative image computing, including image reconstruction, segmentation, registration and visualization. Challenging applications are solved and validated in a clinical environment in collaboration with clinicians and biologists. These applications also serve as a basis to reveal the limits and shortcomings of the state-of-the-art in medical image computing. Based on this input, the research group gains a clearer insight into the field and investigates novel problem-solving hypotheses.
- MIC is involved in several education and training programs related to medical image computing.
- MIC contributes to the development of the personal skill and competences of its researchers and students in view of a professional career with responsibility.
- MIC continuously offers a modern research infrastructure (acquisition, hardware/software) and supporting funding to its researchers to be able to perform research in optimal conditions.
WHY do we do this?
The quality of life and the life expectancy have tremendously increased during the last decades. Biomedical imaging has certainly contributed to this progression. MIC participates in this process by continuously improving the usefulness of biomedical images for the benefit of the patient and society.
Medical imaging today plays a crucial role in all stages of the medical decision process, not only for early patient diagnosis and individualized therapy planning, but also for population screening, therapy outcome prediction and assessment, and also in translational pre-clinical and clinical research. Imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET) or 3D body scans, allow acquiring three-dimensional (3-D) images in a minimally invasive way. Different modalities are based on different physical properties and therefore provide complementary morphological, functional and molecular information.
However, recent innovations in imaging technology have created a tsunami of data, which is becoming a bottleneck in practice. At the same time, the rapid adoption of digital picture archiving and communication systems in the workflow makes that large databases of documented images are becoming available. These databases create new opportunities for multi-modal, multi-temporal, and multi-subject assessment, such as detecting changes over time in a single individual by comparing baseline and follow-up images or detecting pathological abnormalities by comparing patient images with images of control subjects.
HOW do we do this?
In order to optimally exploit this vast amount of imaging data, medical image computing, which is a branch of scientific computing, becomes indispensable. This research can be considered as the intersection of medical imaging, computer vision and machine learning.
Suitable anatomical and physiological models are constructed to incorporate and represent the available knowledge about the scene and the image formation. They need to be sufficiently flexible to account for image appearance variations, such as normal biological shape variability, pathological abnormalities and imaging variability. While they may be specified deterministically, our preference goes to a statistical representation learned from a representative ensemble of images during a training phase. These models can then be tuned to observations to extract and quantify relevant information from multiple sources and to predict missing information. The construction and exploitation of these models is the challenging mission of this research group.
MIC can take advantage of its unique position, i.e. the availability of a large image data base to construct models and to validate new methods; and the close proximity of clinical and biological experts to jointly define projects, solve problems and validate new methods.