Title | ||
---|---|---|
Spatially aware patch-based segmentation (SAPS): an alternative patch-based segmentation framework |
Abstract | ||
---|---|---|
Patch-based segmentation has been shown to be successful in a range of label propagation applications. Performing patch-based segmentation can be seen as a k-nearest neighbour problem as the labelling of each voxel is determined according to the distances to its most similar patches. However, the reliance on a good affine registration given the use of limited search windows is a potential weakness. This paper presents a novel alternative framework which combines the use of kNN search structures such as ball trees and a spatially weighted label fusion scheme to search patches in large regional areas to overcome the problem of limited search windows. Our proposed framework (SAPS) provides an improvement in the Dice metric of the results compared to that of existing patch-based segmentation frameworks. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-36620-8_10 | MCV |
Keywords | Field | DocType |
spatially weighted label fusion,k-nearest neighbour problem,proposed framework,ball tree,label propagation application,patch-based segmentation framework,novel alternative framework,knn search structure,spatially aware patch-based segmentation,alternative patch-based segmentation framework,patch-based segmentation,limited search windows,spatial | Voxel,Nearest neighbour search,Affine transformation,Scale-space segmentation,Pattern recognition,Label propagation,Segmentation,Artificial intelligence,Fusion scheme,Dice,Geography | Conference |
Citations | PageRank | References |
8 | 0.63 | 6 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zehan Wang | 1 | 369 | 11.51 |
Robin Wolz | 2 | 661 | 34.42 |
Tong Tong | 3 | 8 | 0.63 |
Daniel Rueckert | 4 | 9338 | 637.58 |