Abstract | ||
---|---|---|
In this paper, we propose a novel framework for computing single or multiple atlases (templates) from a large population of images. Unlike many existing methods, our proposed approach is distinguished by its emphasis on the sharpness of the computed atlases and the requirement of rotational invariance. In particular, we argue that sharp atlas images that retain crucial and important anatomical features with high fidelity are more useful for many medical imaging applications when compared with the blurry and fuzzy atlas images computed by most existing methods. The geometric notion that underlies our approach is the idea of manifold learning in a quotient space, the quotient space of the image space by the rotations. We present an extension of the existing manifold learning approach to quotient spaces by using invariant metrics, and utilizing the manifold structure for partitioning the images into more homogeneous sub-collections, each of which can be represented by a single atlas image. Specifically, we propose a three-step algorithm. First, we partition the input images into subgroups using unsupervised or semi-supervised learning methods on manifolds. Then we formulate a convex optimization problem in each subgroup to locate the atlases and determine the crucial neighbors that are used in the realization step to form the template images. We have evaluated our algorithm using whole brain MR volumes from OASIS database. Experimental results demonstrate that the atlases computed using the proposed algorithm not only discover the brain structural changes in different age groups but also preserve important structural details and generally enjoy better image quality. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/TMI.2013.2239654 | IEEE Trans. Med. Imaging |
Keywords | Field | DocType |
manifold learning approach,image quality,invariant metrics,oasis database,unsupervised learning methods,three-step algorithm,manifolds,convex optimization problem,computed atlas,rotational invariance,semi-supervised learning,convex programming,single atlas image,medical imaging applications,biomedical mri,optimization,atlas construction,template image,brain,semisupervised learning methods,image population,heterogeneous brain mr image collection,multiple atlas construction,unsupervised learning,brain structural changes,geometry,image space,medical image processing,quotient space,whole brain mr volumes,measurement,neuroimaging,magnetic resonance imaging,semi supervised learning,algorithms,artificial intelligence,statistics,clustering algorithms | Rotational invariance,Computer vision,Population,Computer science,Quotient,Image quality,Quotient space (topology),Unsupervised learning,Artificial intelligence,Nonlinear dimensionality reduction,Manifold | Journal |
Volume | Issue | ISSN |
32 | 3 | 1558-254X |
Citations | PageRank | References |
2 | 0.39 | 21 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuchen Xie | 1 | 57 | 3.08 |
Jeffrey Ho | 2 | 2190 | 101.78 |
B.C. Vemuri | 3 | 4208 | 536.42 |