Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Shape-aware label fusion for multi-atlas frameworks

Alvén, Jennifer ; Kahl, Fredrik LU ; Landgren, Matilda LU ; Larsson, Viktor LU ; Ulén, Johannes LU and Enqvist, Olof LU (2019) In Pattern Recognition Letters 124. p.109-117
Abstract

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 multi-atlas 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... (More)

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 multi-atlas 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 topology and fine structures.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Medical image segmentation, Multi-atlas label fusion, Shape models
in
Pattern Recognition Letters
volume
124
pages
109 - 117
publisher
Elsevier
external identifiers
  • scopus:85049772223
ISSN
0167-8655
DOI
10.1016/j.patrec.2018.07.008
language
English
LU publication?
yes
id
1ee915f2-45a0-4b70-ab38-b4c3d7c8eca0
date added to LUP
2018-09-26 14:55:02
date last changed
2022-09-06 09:57:22
@article{1ee915f2-45a0-4b70-ab38-b4c3d7c8eca0,
  abstract     = {{<p>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 multi-atlas 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 topology and fine structures.</p>}},
  author       = {{Alvén, Jennifer and Kahl, Fredrik and Landgren, Matilda and Larsson, Viktor and Ulén, Johannes and Enqvist, Olof}},
  issn         = {{0167-8655}},
  keywords     = {{Medical image segmentation; Multi-atlas label fusion; Shape models}},
  language     = {{eng}},
  pages        = {{109--117}},
  publisher    = {{Elsevier}},
  series       = {{Pattern Recognition Letters}},
  title        = {{Shape-aware label fusion for multi-atlas frameworks}},
  url          = {{http://dx.doi.org/10.1016/j.patrec.2018.07.008}},
  doi          = {{10.1016/j.patrec.2018.07.008}},
  volume       = {{124}},
  year         = {{2019}},
}