Inflammatory Bowel diseases (IBDs) constitute on of the largest healthcare problems in the Western World, affecting over 1 million European citizens alone, 700,000 of whom suffer from Crohn’s disease. Grading of Crohn’s disease severity is important to determine treatment strategy and to quantify the response to treatment. Colonoscopy in combination with the assessment of biopsy samples is considered the reference standard for diagnosis of all IBD. However, the procedure is invasive and requires extensive bowel preparation, which is considered very burdensome by most patients. Moreover, it only gives information on superficial abnormalities.
The VIGOR++ project aims to create a multiscale, personalised GI tract model, which facilitates improved detection of Crohn’s disease and drives an accurate index of Crohn’s disease severity. VIGOR++ will acquire laboratory, MRI, colonoscopy and microscopy (histopathology) data in order to develop the targeted ICT tools. A novel integration of existing models is employed to predict features on the molecular to cellular scale (microscopy/colonoscopy) from descriptive properties at the organ to patient scales (MRI/laboratory). Effectively, this would render the standard methods (colonoscopy/biopsy) superfluous. The tools sustain early diagnosis, improved therapy planning and a better quality of life for patients. The clinical benefit is demonstrated by an assessment of the tools’ performance to predict Crohn’s disease status. Moreover, a preliminary study will be performed in which the effect of therapy is evaluated using the VIGOR++ tools.
The consortium harbours leading groups in abdominal radiology, medical image analysis, modelling, scientific visualisation, gastroenterology and commercial diffusion. Importantly, it has solid plans for the commercialisation of the generated innovations.
The goal of our part of the project is to develop interactive visualization techniques that improve the technical possibilities for bowel examination. Additionally, we support our partners with our existing competences in the area of automatic segmentation of medical image data.