Improving Robustness for Inter-Subject Medical Image Registration Using a Feature-Based Approach

Summary, in English

We propose new feature-based methods for rigid and affine image registration. These are compared to state-of-the-art intensity-based techniques as well as existing feature-based methods. On challenging datasets of brain MR and whole-body CT images, a significant improvement in terms of speed, robustness to outlier structures and dependence on initialization is shown.

• Författare: Linus Svärm; Olof Enqvist; Fredrik Kahl; Magnus Oskarsson
• Redaktör: Sebastien Ourselin; Jens Rittscher
• Avdelning/ar: Matematik LTH; Datateknik (CI); Mathematical Imaging Group; ELLIIT: the Linköping-Lund initiative on IT and mobile communication; eSSENCE: The e-Science Collaboration
• Publiceringsår: 2015
• Språk: Engelska
• Sidor: 824-828
• Publikation/Tidskrift/Serie: Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on
• Länkar: http://dx.doi.org/10.1109/ISBI.2015.7163998
• Dokumenttyp: Konferensbidrag
• Förlag: IEEE - Institute of Electrical and Electronics Engineers Inc.
• Ämne: Medical Biotechnology; Mathematics
• Nyckelord: Computer vision; image registration; medical image analysis; optimization
• Conference name: 2015 IEEE 12thInternational Symposium on Biomedical Imaging (ISBI)
• Conference date: 2015-04-16 - 2015-04-19
• Conference place: New York, United States
• Status: Published
• Forskningsgrupp: Mathematical Imaging Group