Fast Geodesic Regression for Population-Based Image Analysis.

Med Image Comput Comput Assist Interv 2017 Sep 4;10433:317-325. Epub 2017 Sep 4.

Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, USA.

Geodesic regression on images enables studies of brain development and degeneration, disease progression, and tumor growth. The high-dimensional nature of image data presents significant computational challenges for the current regression approaches and prohibits large scale studies. In this paper, we present a fast geodesic regression method that dramatically decreases the computational cost of the inference procedure while maintaining prediction accuracy. We employ an efficient low dimensional representation of diffeomorphic transformations derived from the image data and characterize the regressed trajectory in the space of diffeomorphisms by its initial conditions, i.e., an initial image template and an initial velocity field computed as a weighted average of pairwise diffeomorphic image registration results. This construction is achieved by using a first-order approximation of pairwise distances between images. We demonstrate the efficiency of our model on a set of 3D brain MRI scans from the OASIS dataset and show that it is dramatically faster than the state-of-the-art regression methods while producing equally good regression results on the large subject cohort.

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-319-66182-7_37DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5786174PMC
September 2017
1 Read

Publication Analysis

Top Keywords

geodesic regression
12
fast geodesic
8
image data
8
regression
6
image
5
diffeomorphic image
4
computational cost
4
decreases computational
4
cost inference
4
image registration
4
average pairwise
4
maintaining prediction
4
procedure maintaining
4
dramatically decreases
4
inference procedure
4
pairwise diffeomorphic
4
construction achieved
4
first-order approximation
4
scale studies
4
large scale
4

References

(Supplied by CrossRef)

VI Arnol’d et al.
Ann. Inst. Fourier 1966

MF Beg et al.
Int. J. Comput. Vision 2005

BC Davis et al.
Int. J. Comput. Vision 2010

S Durrleman et al.
2009

J Hinkle et al.
J. Math. Imaging Vis. 2014

Y Hong et al.
2012

Y Hong et al.
2012

MI Miller et al.
J. Math. Imaging Vis. 2006

M Niethammer et al.
2011

Similar Publications