Automatic hippocampus segmentation of 7.0Tesla MR images by combining multiple atlases and auto-context models

Minjeong Kim, Guorong Wu, Wei Li, Li Wang, Young Don Son, Zang Hee Cho, Dinggang Shen

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

In many neuroscience and clinical studies, accurate measurement of hippocampus is very important to reveal the inter-subject anatomical differences or the subtle intra-subject longitudinal changes due to aging or dementia. Although many automatic segmentation methods have been developed, their performances are still challenged by the poor image contrast of hippocampus in the MR images acquired especially from 1.5 or 3.0Tesla (T) scanners. With the recent advance of imaging technology, 7.0T scanner provides much higher image contrast and resolution for hippocampus study. However, the previous methods developed for segmentation of hippocampus from 1.5T or 3.0T images do not work for the 7.0T images, due to different levels of imaging contrast and texture information. In this paper, we present a learning-based algorithm for automatic segmentation of hippocampi from 7.0T images, by taking advantages of the state-of-the-art multi-atlas framework and also the auto-context model (ACM). Specifically, ACM is performed in each atlas domain to iteratively construct sequences of location-adaptive classifiers by integrating both image appearance and local context features. Due to the plenty texture information in 7.0T images, more advanced texture features are also extracted and incorporated into the ACM during the training stage. Then, under the multi-atlas segmentation framework, multiple sequences of ACM-based classifiers are trained for all atlases to incorporate the anatomical variability. In the application stage, for a new image, its hippocampus segmentation can be achieved by fusing the labeling results from all atlases, each of which is obtained by applying the atlas-specific ACM-based classifiers. Experimental results on twenty 7.0T images with the voxel size of 0.35×0.35×0.35mm3 show very promising hippocampus segmentations (in terms of Dice overlap ratio 89.1±0.020), indicating high applicability for the future clinical and neuroscience studies.

Original languageEnglish
Pages (from-to)335-345
Number of pages11
JournalNeuroImage
Volume83
DOIs
Publication statusPublished - 2013 Dec 1

Fingerprint

Atlases
Hippocampus
Neurosciences
Dementia
Learning
Technology

Keywords

  • 7.0T MRI
  • Auto-context model
  • Automatic hippocampus segmentation
  • Label fusion
  • Multiple atlases based segmentation

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Automatic hippocampus segmentation of 7.0Tesla MR images by combining multiple atlases and auto-context models. / Kim, Minjeong; Wu, Guorong; Li, Wei; Wang, Li; Son, Young Don; Cho, Zang Hee; Shen, Dinggang.

In: NeuroImage, Vol. 83, 01.12.2013, p. 335-345.

Research output: Contribution to journalArticle

Kim, Minjeong ; Wu, Guorong ; Li, Wei ; Wang, Li ; Son, Young Don ; Cho, Zang Hee ; Shen, Dinggang. / Automatic hippocampus segmentation of 7.0Tesla MR images by combining multiple atlases and auto-context models. In: NeuroImage. 2013 ; Vol. 83. pp. 335-345.
@article{34dc5de8a4da4fd4bdf36afcf9da89bb,
title = "Automatic hippocampus segmentation of 7.0Tesla MR images by combining multiple atlases and auto-context models",
abstract = "In many neuroscience and clinical studies, accurate measurement of hippocampus is very important to reveal the inter-subject anatomical differences or the subtle intra-subject longitudinal changes due to aging or dementia. Although many automatic segmentation methods have been developed, their performances are still challenged by the poor image contrast of hippocampus in the MR images acquired especially from 1.5 or 3.0Tesla (T) scanners. With the recent advance of imaging technology, 7.0T scanner provides much higher image contrast and resolution for hippocampus study. However, the previous methods developed for segmentation of hippocampus from 1.5T or 3.0T images do not work for the 7.0T images, due to different levels of imaging contrast and texture information. In this paper, we present a learning-based algorithm for automatic segmentation of hippocampi from 7.0T images, by taking advantages of the state-of-the-art multi-atlas framework and also the auto-context model (ACM). Specifically, ACM is performed in each atlas domain to iteratively construct sequences of location-adaptive classifiers by integrating both image appearance and local context features. Due to the plenty texture information in 7.0T images, more advanced texture features are also extracted and incorporated into the ACM during the training stage. Then, under the multi-atlas segmentation framework, multiple sequences of ACM-based classifiers are trained for all atlases to incorporate the anatomical variability. In the application stage, for a new image, its hippocampus segmentation can be achieved by fusing the labeling results from all atlases, each of which is obtained by applying the atlas-specific ACM-based classifiers. Experimental results on twenty 7.0T images with the voxel size of 0.35×0.35×0.35mm3 show very promising hippocampus segmentations (in terms of Dice overlap ratio 89.1±0.020), indicating high applicability for the future clinical and neuroscience studies.",
keywords = "7.0T MRI, Auto-context model, Automatic hippocampus segmentation, Label fusion, Multiple atlases based segmentation",
author = "Minjeong Kim and Guorong Wu and Wei Li and Li Wang and Son, {Young Don} and Cho, {Zang Hee} and Dinggang Shen",
year = "2013",
month = "12",
day = "1",
doi = "10.1016/j.neuroimage.2013.06.006",
language = "English",
volume = "83",
pages = "335--345",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Automatic hippocampus segmentation of 7.0Tesla MR images by combining multiple atlases and auto-context models

AU - Kim, Minjeong

AU - Wu, Guorong

AU - Li, Wei

AU - Wang, Li

AU - Son, Young Don

AU - Cho, Zang Hee

AU - Shen, Dinggang

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In many neuroscience and clinical studies, accurate measurement of hippocampus is very important to reveal the inter-subject anatomical differences or the subtle intra-subject longitudinal changes due to aging or dementia. Although many automatic segmentation methods have been developed, their performances are still challenged by the poor image contrast of hippocampus in the MR images acquired especially from 1.5 or 3.0Tesla (T) scanners. With the recent advance of imaging technology, 7.0T scanner provides much higher image contrast and resolution for hippocampus study. However, the previous methods developed for segmentation of hippocampus from 1.5T or 3.0T images do not work for the 7.0T images, due to different levels of imaging contrast and texture information. In this paper, we present a learning-based algorithm for automatic segmentation of hippocampi from 7.0T images, by taking advantages of the state-of-the-art multi-atlas framework and also the auto-context model (ACM). Specifically, ACM is performed in each atlas domain to iteratively construct sequences of location-adaptive classifiers by integrating both image appearance and local context features. Due to the plenty texture information in 7.0T images, more advanced texture features are also extracted and incorporated into the ACM during the training stage. Then, under the multi-atlas segmentation framework, multiple sequences of ACM-based classifiers are trained for all atlases to incorporate the anatomical variability. In the application stage, for a new image, its hippocampus segmentation can be achieved by fusing the labeling results from all atlases, each of which is obtained by applying the atlas-specific ACM-based classifiers. Experimental results on twenty 7.0T images with the voxel size of 0.35×0.35×0.35mm3 show very promising hippocampus segmentations (in terms of Dice overlap ratio 89.1±0.020), indicating high applicability for the future clinical and neuroscience studies.

AB - In many neuroscience and clinical studies, accurate measurement of hippocampus is very important to reveal the inter-subject anatomical differences or the subtle intra-subject longitudinal changes due to aging or dementia. Although many automatic segmentation methods have been developed, their performances are still challenged by the poor image contrast of hippocampus in the MR images acquired especially from 1.5 or 3.0Tesla (T) scanners. With the recent advance of imaging technology, 7.0T scanner provides much higher image contrast and resolution for hippocampus study. However, the previous methods developed for segmentation of hippocampus from 1.5T or 3.0T images do not work for the 7.0T images, due to different levels of imaging contrast and texture information. In this paper, we present a learning-based algorithm for automatic segmentation of hippocampi from 7.0T images, by taking advantages of the state-of-the-art multi-atlas framework and also the auto-context model (ACM). Specifically, ACM is performed in each atlas domain to iteratively construct sequences of location-adaptive classifiers by integrating both image appearance and local context features. Due to the plenty texture information in 7.0T images, more advanced texture features are also extracted and incorporated into the ACM during the training stage. Then, under the multi-atlas segmentation framework, multiple sequences of ACM-based classifiers are trained for all atlases to incorporate the anatomical variability. In the application stage, for a new image, its hippocampus segmentation can be achieved by fusing the labeling results from all atlases, each of which is obtained by applying the atlas-specific ACM-based classifiers. Experimental results on twenty 7.0T images with the voxel size of 0.35×0.35×0.35mm3 show very promising hippocampus segmentations (in terms of Dice overlap ratio 89.1±0.020), indicating high applicability for the future clinical and neuroscience studies.

KW - 7.0T MRI

KW - Auto-context model

KW - Automatic hippocampus segmentation

KW - Label fusion

KW - Multiple atlases based segmentation

UR - http://www.scopus.com/inward/record.url?scp=84880956855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880956855&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2013.06.006

DO - 10.1016/j.neuroimage.2013.06.006

M3 - Article

C2 - 23769921

AN - SCOPUS:84880956855

VL - 83

SP - 335

EP - 345

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -