IGT logo

National Center for Image Guided Therapy

The Publication Database hosted by SPL

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

Source Code for the Paper Titled: Efficient and Robust Model-to-Image Alignment using 3D Scale-Invariant Features

Institution:
Surgical Planning Laboratory, Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
Publication Date:
Nov-2012
Citation:
SPL 2012 Nov;
Links:
http://www.na-mic.org/publications/item/view/2308
Keywords:
Feature-based Alignment, 3D scale-invariant feature, orientation assignment, Feature Descriptor, probabilistic model, image alignment, Magnetic resonance images, computed tomography
Appears in Collections:
SPL, Download Data, NAC
Sponsors:
P41 RR013218/RR/NCRR NIH HHS/United States
P41 EB015902/EB/NIBIB NIH HHS/United States
R01 HD057963/HD/NICHD NIH HHS/United States
R01 CA138419/CA/NCI NIH HHS/United States
Generated Citation:
Toews M., Wells III W.M. Source Code for the Paper Titled: Efficient and Robust Model-to-Image Alignment using 3D Scale-Invariant Features. SPL 2012 Nov;
Downloaded: 1097 times. [view map]
Export citation:
Google Scholar: link

This paper presents feature-based alignment (FBA), a general method for efficient and robust model-to-image alignment. Volumetric images, e.g. CT scans of the human body, are modeled probabilistically as a collage of 3D scale-invariant image features within a normalized reference space. Features are incorporated as a latent random variable and marginalized out in computing a maximum a-posteriori alignment solution. The model is learned from features extracted in pre-aligned training images, then fit to features extracted from a new image to identify a globally optimal locally linear alignment solution. Novel techniques are presented for determining local feature orientation and efficiently encoding feature intensity in 3D. Experiments involving difficult magnetic resonance (MR) images of the human brain demonstrate FBA achieves alignment accuracy similar to widely-used registration methods, while requiring a fraction of the memory and computation resources and offering a more robust, globally optimal solution. Experiments on CT human body scans demonstrate FBA as an effective system for automatic human body alignment where other alignment methods break down.
Related Article.

Additional Material
3 Files (26MB)
Toews-featExtract-fig.jpg (210.918kB) Toews-featExtract1.4.zip (25MB)

Updates to version 1.1


Toews-featExtract1.1.zip (745kB)