3D/2D registration methods for image-guided interventions
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. In image-guided minimally invasive surgery, the registration of pre- and intra-interventional data and instrument tracking provide surgeon with information about the current position of his instruments relative to the planned trajectory, nearby vulnerable structures and the ultimate target. In image-guided endoscopy, 3D virtual images of the anatomy and pathology are generated from pre-interventional images and registered to real-time live endoscopic images to provide augmented reality which enables display of anatomical structures that are hidden from the direct view by currently exposed tissues. In interventional radiology, registration of the pre-interventional image to the X-ray fluoroscopic or US image allows visualization of tools and blood flow in 3D which can greatly improve guidance and execution. In external beam radiotherapy, registration of planning CT images and daily-treatment images allow precise patient positioning, which is of utmost importance for exact dose delivery to the target and for avoiding irradiation of healthy critical tissue.
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.
Professor Franjo Pernuš
Dept. of Electrical Engineering
University of Ljubljana (UL)
Trzaska 25, 1000 Ljubljana
Franjo Pernus 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. Currently, Franjo Pernus is Associate Editor of the IEEE Transactions on Medical Imaging (2002-). In the past he was Associate Editor of Pattern Recognition Letters (2004-2006) and of Electrotechnical Review (1996-2008). He co-organized the 1st Workshop on Biomedical Image Registration (1999) and was Guest Co-Editor of the special issue on Biomedical Image Registration of the Image Vision Computing Journal. From 2002 to 2006 he was the Chair of Technical Committee 9 (Biomedical Image Analysis) of the International Association for Pattern Recognition and from 2004 to 2009 a member of the IEEE BISP Technical Committee (SP Society). From 1997 to 2001 he was the President of the Slovenian Pattern Recognition Society. Prof. Pernus is co-founder of Sensum, a company, which supplies machine vision solutions for the pharmaceutical industry.