Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

Efficient Laplace Approximation for Bayesian Registration Uncertainty Quantification

Institution:
1Computer Science and Engineering Department, Lehigh University, Bethlehem, PA, USA.
2Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA, USA.
Publication Date:
Sep-2018
Journal:
Med Image Comput Comput Assist Interv
Volume Number:
20
Issue Number:
Pt1
Pages:
880-8
Citation:
Int Conf Med Image Comput Comput Assist Interv. 2017 Sep;21(Pt1):880-8.
PubMed ID:
31134217
PMCID:
PMC6533616
Appears in Collections:
NAC, NCIGT, SPL
Sponsors:
P41 EB015898/EB/NIBIB NIH HHS/United States
P41 EB015902/EB/NIBIB NIH HHS/United States
Generated Citation:
Wang J., Wells W.M., Golland P., Zhang M. Efficient Laplace Approximation for Bayesian Registration Uncertainty Quantification. Int Conf Med Image Comput Comput Assist Interv. 2017 Sep;21(Pt1):880-8. PMID: 31134217. PMCID: PMC6533616.
Downloaded: 42 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

This paper presents a novel approach to modeling the pos terior distribution in image registration that is computationally efficient for large deformation diffeomorphic metric mapping (LDDMM). We develop a Laplace approximation of Bayesian registration models entirely in a bandlimited space that fully describes the properties of diffeomorphic transformations. In contrast to current methods, we compute the inverse Hessian at the mode of the posterior distribution of diffeomorphisms directly in the low dimensional frequency domain. This dramatically reduces the computational complexity of approximating posterior marginals in the high dimensional imaging space. Experimental results show that our method is significantly faster than the state-of-the-art diffeomorphic image registration uncertainty quantification algorithms, while producing comparable results. The efficiency of our method strengthens the feasibility in prospective clinical applications, e.g., real- time image-guided navigation for brain surgery.