Shape-aware multi-atlas segmentation

Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving fine structures.

Kahl, Fredrik,1972Chalmers University of Technology(Swepub:lu)math-fka (författare)
Landgren, MatildaLund University,Lunds universitet,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH(Swepub:lu)math-mtl (författare)
Larsson, ViktorLund University,Lunds universitet,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH(Swepub:lu)vi4846la (författare)
Ulén, JohannesLund University,Lunds universitet,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH(Swepub:lu)math-jsu (författare)
Chalmers University of TechnologyMatematikcentrum (creator_code:org_t)

Ingår i:Proceedings - International Conference on Pattern Recognition0, s. 1101-11061051-4651

Av författaren/redakt...: Alvén, Jennifer, ...; Kahl, Fredrik, 1 ...; Landgren, Matild ...; Larsson, Viktor; Ulén, Johannes

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datorseende och ...

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Medicinteknik; och Medicinsk bildbe ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.