Glandular tissue pattern analysis through multimodal MRI-mammography registration

Breast cancer is the most common cancer among women worldwide. Several studies have shown that the combination of the different medical image modalities, such as the x-ray mammography and the magnetic resonance imaging (MRI), leads to a more accurate diagnosis. The aim of this thesis is double, on the one hand, to evaluate the similarity between the information obtained from x-ray mammography and from MRI images and, on the other hand, to propose new registration algorithms to perform the correlation between the two image modalities. The problem includes from the biomechanical model construction, obtained from the MRI volume, the mechanical deformation, which is performed during the mammographic acquisition, the x-ray beam simulation traversing the breast in order to obtain the image (pseudo-mammogram) and the registration process to improve the similarity between the real and the synthetic images ​
​L'accés als continguts d'aquesta tesi queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: