Multi-modal automatic registration : A parallel multi-resolution approach applied to PET-MRI

Automatic registration of small animal Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) data represents a difficult problem in terms of convergence speed, accuracy and success rate. In fact, most existing registration methods are developed and applied to human brain volumes but these are not as effective for small animal data because of the lack of intensity information in the images and often the large anisotropy in voxel dimensions (very small in-plane resolution and large slice thickness). This master thesis focuses on multi-modal automatic registration techniques and their limitations, especially applied to PET-MRI registration. In the main article of this master thesis, we propose a new registration measure that combines multi-resolution in parallel (in the same energy function) instead of a classic sequential multi-resolution, which influence the procedure of the registration as well. By combining low and high resolution levels of images, we can gain from the low noise sensitivity and aperture at coarse levels and higher contrast and details at higher levels, which helps convergence accuracy and speed. The paper shows that our new approach is therefore an automatic, robust and efficient registration algorithm with a high success rate. We also present in this document some implementation details on the tool which was created by the author of this thesis based on the classic registration and the new approach described in this thesis.;Keywords: PET ; MRI ; Registration ; Similarity measure ; Multi-resolution ; Multi-modal ; NMI.