Progressive multi-atlas label fusion by dictionary evolution

Yantao Song, Guorong Wu, Khosro Bahrami, Quansen Sun, Dinggang Shen

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an atlas patch dictionary (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the corresponding anatomical labels of the atlas patches in the atlas label dictionary (in the label domain). However, due to the generally large gap between the patch appearance in the image domain and the patch structure in the label domain, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-by-layer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer static dictionary to the multi-layer dynamic dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer static dictionary.

Original languageEnglish
Pages (from-to)162-171
Number of pages10
JournalMedical Image Analysis
Volume36
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

Atlases
Glossaries
Labels
Fusion reactions
Labeling
Weights and Measures
Image segmentation

Keywords

  • Brain MRI
  • Hippocampus
  • Label fusion
  • Multi-atlas
  • Sparse representation

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Progressive multi-atlas label fusion by dictionary evolution. / Song, Yantao; Wu, Guorong; Bahrami, Khosro; Sun, Quansen; Shen, Dinggang.

In: Medical Image Analysis, Vol. 36, 01.02.2017, p. 162-171.

Research output: Contribution to journalArticle

Song, Yantao ; Wu, Guorong ; Bahrami, Khosro ; Sun, Quansen ; Shen, Dinggang. / Progressive multi-atlas label fusion by dictionary evolution. In: Medical Image Analysis. 2017 ; Vol. 36. pp. 162-171.
@article{3ae4a0fb9ad34ef683de8bb8517ad35c,
title = "Progressive multi-atlas label fusion by dictionary evolution",
abstract = "Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an atlas patch dictionary (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the corresponding anatomical labels of the atlas patches in the atlas label dictionary (in the label domain). However, due to the generally large gap between the patch appearance in the image domain and the patch structure in the label domain, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-by-layer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer static dictionary to the multi-layer dynamic dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer static dictionary.",
keywords = "Brain MRI, Hippocampus, Label fusion, Multi-atlas, Sparse representation",
author = "Yantao Song and Guorong Wu and Khosro Bahrami and Quansen Sun and Dinggang Shen",
year = "2017",
month = "2",
day = "1",
doi = "10.1016/j.media.2016.11.005",
language = "English",
volume = "36",
pages = "162--171",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - Progressive multi-atlas label fusion by dictionary evolution

AU - Song, Yantao

AU - Wu, Guorong

AU - Bahrami, Khosro

AU - Sun, Quansen

AU - Shen, Dinggang

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an atlas patch dictionary (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the corresponding anatomical labels of the atlas patches in the atlas label dictionary (in the label domain). However, due to the generally large gap between the patch appearance in the image domain and the patch structure in the label domain, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-by-layer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer static dictionary to the multi-layer dynamic dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer static dictionary.

AB - Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an atlas patch dictionary (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the corresponding anatomical labels of the atlas patches in the atlas label dictionary (in the label domain). However, due to the generally large gap between the patch appearance in the image domain and the patch structure in the label domain, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-by-layer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer static dictionary to the multi-layer dynamic dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer static dictionary.

KW - Brain MRI

KW - Hippocampus

KW - Label fusion

KW - Multi-atlas

KW - Sparse representation

UR - http://www.scopus.com/inward/record.url?scp=84999886607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84999886607&partnerID=8YFLogxK

U2 - 10.1016/j.media.2016.11.005

DO - 10.1016/j.media.2016.11.005

M3 - Article

C2 - 27914302

AN - SCOPUS:84999886607

VL - 36

SP - 162

EP - 171

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -