research

Stent-Graft Motion Analysis

In this project at Ecole Centrale de Paris, and Hospital Henri Mondor Paris, we work on the analysis of the movements of stent-grafts close to the heart. We want to know how they deform, where the risks for the patients, who will live with the implant over decades, are, and how stent-grafts can be improved.

Autonomous Model Building

The autonomous building of models and the learning of structures and behavior from un-annotated data is a way to cope with the vast and growing amount of medical imaging modalities, and with the rich information they provide. Autonomous learning might be a key to this data, and could enable clinicians to utilize and explore the information in an intuitive manner.

Model Maps 

Model maps and the special case of shape maps are a way of viewing data from a behavioral point of view. They organize observations according to joint modelling properties, and allow insights in the functional organization, and generation mechanisms. [download code]

Functional Brain Imaging

We are working on functional brain imaging, and try to develop ways to extract, represent, structure, and interpret information from these observations. This is work together with Dimitris Samaras and Jean Honorio at Stony Brooks University, and Rita Goldstein at Brookhaven National Laboratory.

Rheumatoid Arthritis Quantification

We work on the automatic quantification of erosion development and joint space narrowing during the course of rheumatoid arthritis (RA). The work is aimed at a more precise monitoring of RA during therapy and during multi center clinical trials. The work resulted in the RAquantify package, that allows for the automatic RA assessment in a clinical context. A first experience regarding joint space width measurement has been published recently in Radiology [paper], and a comperative study was reported in the Journal of Rheumatology [paper].