Groupwise image registration tackles biases that can potentially arise from inappropriate template selection. It typically involves simultaneous registration of a cohort of images to a common space that is not specified a priori. Existing groupwise registration methods are computationally complex and are only effective for image populations without large anatomical variations. In this paper, we propose a deep learning framework to rapidly estimate large deformations between images to significantly reduce structural variability. Specifically, we employ a multi-level graph coarsening method to agglomerate similar images into clusters, each represented by an exemplar image. We then use a deep learning framework to predict the initial deformations between images. Warping with the estimated deformations brings the images closer in the image manifold and their alignment can be further refined using conventional groupwise registration algorithms. We evaluated the effectiveness of our method in groupwise registration of MR brain images and compared it against state-of-the-art groupwise registration methods. Experimental results indicate that deformation initialization enables groupwise registration to converge significantly faster with competitive accuracy, therefore facilitates large-scale imaging studies.
Bibliographical noteFunding Information:
This work was supported in part by NIH grants (EB006733, EB008374, MH100217, AG053867).
© 2019 Ahmad, Fan, Dong, Cao, Yap and Shen.
- Brain templates
- Convolutional neural network
- Deep learning
- Graph coarsening
- Groupwise registration
ASJC Scopus subject areas
- Neuroscience (miscellaneous)
- Biomedical Engineering
- Computer Science Applications