Supervoxel classification forests for estimating pairwise image correspondences

Kanavati F, Tong T, Misawa K, Fujiwara M, Mori K, Rueckert D, Glocker B (2017)

Publication Type: Journal article

Publication year: 2017

Journal

Pattern Recognition Elsevier

Book Volume: 63

Pages Range: 561-569

DOI: 10.1016/j.patcog.2016.09.026

Abstract

This article presents a general method for estimating pairwise image correspondences, which is a fundamental problem in image analysis. The method consists of over-segmenting a pair of images into supervoxels. A forest classifier is then trained on one of the images, the source, by using supervoxel indices as voxel-wise class labels. Applying the forest on the other image, the target, yields a supervoxel labelling, which is then regularised using majority voting within the boundaries of the target's supervoxels. This yields semi-dense correspondences in a fully automatic, unsupervised, efficient and robust manner. The advantage of our approach is that no prior information or manual annotations are required, making it suitable as a general initialisation component for various medical imaging tasks that require coarse correspondences, such as atlas/patch-based segmentation, registration, and atlas construction. We demonstrate the effectiveness of our approach in two different applications: a) initialisation of longitudinal registration on spine CT data of 96 patients, and b) atlas-based image segmentation using 150 abdominal CT images. Comparison to state-of-the-art methods demonstrate the potential of supervoxel classification forests for estimating image correspondences.

Involved external institutions

Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB) Aichi Cancer Center Research Institute JP Japan (JP) Nagoya University Hospital / 名古屋大学医学部附属病院 JP Japan (JP) Nagoya University / 名古屋大学 JP Japan (JP)

How to cite

APA:

Kanavati, F., Tong, T., Misawa, K., Fujiwara, M., Mori, K., Rueckert, D., & Glocker, B. (2017). Supervoxel classification forests for estimating pairwise image correspondences. Pattern Recognition, 63, 561-569. https://doi.org/10.1016/j.patcog.2016.09.026

MLA:

Kanavati, Fandi, et al. "Supervoxel classification forests for estimating pairwise image correspondences." Pattern Recognition 63 (2017): 561-569.

BibTeX: Download