Supervoxel classification forests for estimating pairwise image correspondences. (March 2017)

• Record Type: Journal Article
• Authors: Kanavati, Fahdi; Tong, Tong; Misawa, Kazunari; Fujiwara, Michitaka; Mori, Kensaku; Rueckert, Daniel; Glocker, Ben
• Is Part Of: Pattern recognition. Volume 63(2017:Mar.)
• Page Start: 561
• Page End: 569
• Publication Date: 2017-03
• Subjects: Random forests -- Unsupervised learning -- Image correspondences -- Supervoxels; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.09.026
• Languages: English
• ISSNs: 0031-3203

Abstract

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. Highlights: A method for using random forests to estimate image correspondences is proposed. The method does not rely on the availability of manual label annotations. Labels for training are obtained via the use of supervoxels. The efficient method is effective at providing an estimate of image correspondences.