Abstract
In this paper, we propose a sampling-based shape segmen- tation method that builds upon a global shape and a local appearance model. It is suited for challenging problems where there is high uncer- tainty about the correct solution due to a low signal-to-noise ratio, clut- ter, occlusions or an erroneous model. Our method suits for segmentation tasks where the number of ob jects is not known a priori, or where the ob ject of interest is invisible and can only be inferred from other ob- jects in the image. The method was inspired by shape particle filtering from de Bruijne and Nielsen, but shows substantial improvements to it. The principal contributions of this paper are as follows: (i) We introduce statistically motivated importance weights that lead to better perfor- mance and facilitate the application to new problems. (ii) We adapt the static sequential Monte Carlo (SMC) algorithm to the problem of im- age segmentation, where the algorithm proves to sample efficiently from high-dimensional static spaces. (iii) We evaluate the static SMC sam- pler on shapes on a medical problem of high relevance: the automated quantification of aortic calcifications on X-ray radiographs for the prog- nosis and diagnosis of cardiovascular disease and mortality. Our results suggest that the static SMC sampler on shapes is more generic, robust, and accurate than shape particle filtering, while being computationally equally costly.