Abstract
Groupwise registration aligns a set of images to a common space. It can however be inefficient and ineffective when dealing with datasets with significant anatomical variations. To mitigate these problems, we propose a groupwise registration framework based on hierarchical multi-level and multi-resolution shrinkage of a graph set. First, to deal with datasets with complex inhomogeneous image distributions, we divide the images hierarchically into multiple clusters. Since the images in each cluster have similar appearances, they can be registered effectively. Second, we employ a multi-resolution strategy to reduce computational cost. Experimental results on two public datasets show that our proposed method yields state-of-the-art registration accuracy with significantly reduced computational time.
Highlights
The most intuitive means of aligning a population of images to a common space is by registering them to a pre-selected template
A common limitation of these methods is that the registration accuracy of the images to the tentative group mean image might be affected by potentially large anatomical differences
We evaluated the performance of our method using two public datasets: (1) LONI LPBA40 dataset consisting of brain images of normal young adults, and (2) Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset with significant anatomical variations
Summary
The most intuitive means of aligning a population of images to a common space is by registering them to a pre-selected template. Wang[13] used image features to guide groupwise registration for better accuracy These methods are computational demanding, limiting their application to large datasets. The accuracy of this method is limited by the blurriness of the tentative group mean image To address this issue, Wu et al.[14] proposed a method to improve the sharpness of the group mean image by using patch-based weighted averaging. A common limitation of these methods is that the registration accuracy of the images to the tentative group mean image might be affected by potentially large anatomical differences. Using a method called HUGS, Ying et al.[8] represented image manifold using a graph, and cast groupwise registration as a dynamic graph shrinkage problem.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
