Medical Imaging (MiLab)



Principal Researcher:


Today Medical Imaging expands beyond the simple visualization and inspection of anatomic structures. Involving a large set of image modalities medical imaging provides meaningful structural, anatomical and functional information about human organs that serves to guide intervention procedures, plan surgeries and help the follow-up of patient diseases.


Key issues of robust medical imaging analysis are represented by the following Computer Vision techniques:

a) Deformable models with their profound roots in estimation theory, optimization, and physics-based dynamical systems, represent a powerful approach to the general problem of image segmentation, image registration and 3D reconstruction.

b) Advanced machine learning techniques as ECOC, adaboost, active labeling, co-training, etc. provide robust tools to learn and extract image features for straightforward tissue characterization, as well as combined with deformable models allow to capture and describe the variability of biological shapes in medical images.


In our group we consider different imaging modalities of coronary, cardiac and intestine fields: intravascular ultrasound images, angiography, tagged magnetic resonance imaging, computed tomography and wireless capsule endoscopic images in order to extract important diagnostic and therapeutic knowledge and propose robust solution to the problems of accurate segmentation, shape modelling, image simulation, labelling, reconstructing, multimodal image fusion, tissue characterization and dynamic analysis of human organs.