Biomedical imaging registration trends and applications

Abstract

Data registration, i.e., the process of transforming a dataset so that the entities represented are properly adjusted to the homologous entities represented in a second dataset, has been a topic of huge research in various scientific fields. In Computational Vision, such transformation is commonly used on static images, but also on image sequences, and is usually known as image registration. For example, in medicine, computational methods of image registration have been assuming an essential role in supporting enhanced diagnosis, the fusion of information conveyed in images acquired by different techniques, the follow-up of organs and pathologies, in computer-assisted surgery, etc. Thus, the computational registration of images has been a remarkable tool for clinicians and researchers since, after the truthful registration of the data involved, tasks such as image analysis, comparison of a given clinical case with previously studied ones, the automatic identification of regions of interest and information fusion, are facilitated and can be performed automatically and without subjectivity. During this presentation, the topic of image registration is going to be introduced, automatic computational methodologies to register images and image sequences are going to be described, and application cases involving static images, image sequences and images acquired by different techniques are going to be presented and discussed.