Multimodal - Data fusion of multimodal information using advanced signal processing, segmentation and registration techniques

From 01-01-2007 to 31-12-2012

Description

In medical image analysis and signal processing there is an ever growing demand for the integration of different heterogeneous sources since they provide us with complementary information [Biagioni01]. In this project we will study techniques for the combination of EEG (electro-encephalography, 4 up to 20 channels) and other polygraphic signals (ECG, EOG, EMG, respiration, saturation), 3D magnetic resonance images (MRI) and 2D ultrasound images (US). We will focus on the image and signal processing techniques. The medical support will be limited to the provision of data and feedback. It is not our aim to fully validate the results clinically (although this might be the case in a follow up project). One of the main issues is the difference in dimensionality of the different heterogeneous sources we want to fuse. To this end we will develop new algorithms for: multi-linear decomposition of multi-channel EEG signals, 3D Canonical Correlation Analysis (CCA) with other polygraphic signals and segmentation and quantification (through textural and geometrical parameters) of 2D and 3D images. The combined expertise of the applying research groups in these domains is highly complementary. An important innovation is that we will provide feedback from the classifier resulting from this data fusion to the image and signal processing algorithms. To realize this, an intense cooperation between the research groups is essential.

Team

• Sabine Van Huffel, Co-promoter
• Paul Govaert, Co-promoter (External)
• Wilfried Philips, Promoter (External)

Financing

Funding: FWO - Research Foundation - Flanders

Program/Grant Type: FWO Research Grant - FWO Research Grant