Titre : 3D/2D registration methods for image-guided interventions
Conférencier : Prof. Franjo Pernuš, dépt. de Génie électrique, Université de Ljubljana, Slovénie
Date : jeudi 11 septembre, 2014
Heure : 9h30
Lieu : salle L-3816 du Pavillon Lassonde de l'École Polytechnique de Montréal
Résumé :
Image registration is one of the enabling technologies for image-guided radiation therapy, image-guided radiosurgery, and image-guided minimally invasive therapy which includes a wide variety of therapies in surgery, endoscopy, and interventional radiology. Registration is concerned with bringing the pre-interventional data (patient's images or models of anatomical structures obtained from these images by segmentation and treatment plan) and intra-interventional data (patient's images, position of tools, radiation fields) into the same coordinate frame. Currently the pre-interventional data are 3D CT, MR or cone-beam CT images, while the intra-interventional data are usually 2D projective X-ray (fluoroscopy) or ultrasound images. With respect to data dimensionality, the registration is thus 3D to 2D (3D/2D).
All the above mentioned medical specialties benefit from 3D/2D image registration through easier and better guidance of an intervention, leading to reduced invasiveness and/or increased accuracy. A number of 3D/2D image registrations have been proposed in the past. In this talk, 3D/2D rigid registration methods, proposed for registering a 3D CT and/or MR image to one or more X-ray images, will be reviewed systematically according to the dimensionality of the space where registration is performed and the data on which registration is based.
Courte biographie :
Franjo Pernuš received the Diploma, M.S., and Ph.D. degrees in Electrical Engineering from the University of Ljubljana, Ljubljana, Slovenia, in 1976, 1979, and 1991, respectively. In 1981 he received the Government of Canada Award for Foreign Nationals and spent a year at McGill University, Montreal, Canada. Since 1976 he is with the Department of Electrical Engineering, University of Ljubljana, where he is currently Professor and Head of the Imaging Technologies Lab. His research interests are in biomedical image processing and analysis, computer vision, and the applications of image processing and analysis techniques to various biomedical and industrial problems. He is (co)author of over 150 refereed scientific articles on biomedical image processing and computer vision and has supervised 7 PhD students.
