Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion

Xiaoying Tang, Kwame Kutten, Can Ceritoglu, Susumu Mori, Michael I. Miller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose and validate a fully automated pipeline for simultaneous skull-stripping and lateral ventricle segmentation using T1-weighted images. The pipeline is built upon a segmentation algorithm entitled fast multi-atlas likelihood-fusion (MALF) which utilizes multiple T1 atlases that have been pre-segmented into six whole-brain labels-the gray matter, the white matter, the cerebrospinal fluid, the lateral ventricles, the skull, and the background of the entire image. This algorithm, MALF, was designed for estimating brain anatomical structures in the framework of coordinate changes via large diffeomorphisms. In the proposed pipeline, we use a variant of MALF to estimate those six whole-brain labels in the test T1-weighted image. The three tissue labels (gray matter, white matter, and cerebrospinal fluid) and the lateral ventricles are then grouped together to form a binary brain mask to which we apply morphological smoothing so as to create the final mask for brain extraction. For computational purposes, all input images to MALF are down-sampled by a factor of two. In addition, small deformations are used for the changes of coordinates. This substantially reduces the computational complexity, hence we use the term "fast MALF". The skull-stripping performance is qualitatively evaluated on a total of 486 brain scans from a longitudinal study on Alzheimer dementia. Quantitative error analysis is carried out on 36 scans for evaluating the accuracy of the pipeline in segmenting the lateral ventricle. The volumes of the automated lateral ventricle segmentations, obtained from the proposed pipeline, are compared across three different clinical groups. The ventricle volumes from our pipeline are found to be sensitive to the diagnosis.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015: Image Processing
PublisherSPIE
Volume9413
ISBN (Print)9781628415032
DOIs
StatePublished - 2015
EventMedical Imaging 2015: Image Processing - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Other

OtherMedical Imaging 2015: Image Processing
CountryUnited States
CityOrlando
Period2/24/152/26/15

Fingerprint

skull
Atlases
Lateral Ventricles
stripping
Skull
brain
Brain
Fusion reactions
Pipelines
fusion
cerebrospinal fluid
Cerebrospinal fluid
Labels
Masks
Cerebrospinal Fluid
masks
error analysis
smoothing
Error analysis
Longitudinal Studies

Keywords

  • Alzheimer's disease
  • lateral ventricle
  • likelihood-fusion
  • multi-atlas
  • segmentation
  • Skull-stripping

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Tang, X., Kutten, K., Ceritoglu, C., Mori, S., & Miller, M. I. (2015). Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion. In Medical Imaging 2015: Image Processing (Vol. 9413). [94130W] SPIE. https://doi.org/10.1117/12.2080830

Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion. / Tang, Xiaoying; Kutten, Kwame; Ceritoglu, Can; Mori, Susumu; Miller, Michael I.

Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015. 94130W.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tang, X, Kutten, K, Ceritoglu, C, Mori, S & Miller, MI 2015, Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion. in Medical Imaging 2015: Image Processing. vol. 9413, 94130W, SPIE, Medical Imaging 2015: Image Processing, Orlando, United States, 2/24/15. https://doi.org/10.1117/12.2080830
Tang X, Kutten K, Ceritoglu C, Mori S, Miller MI. Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion. In Medical Imaging 2015: Image Processing. Vol. 9413. SPIE. 2015. 94130W https://doi.org/10.1117/12.2080830
Tang, Xiaoying ; Kutten, Kwame ; Ceritoglu, Can ; Mori, Susumu ; Miller, Michael I. / Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion. Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015.
@inproceedings{01f7ae16ed4b4345ba96f9ee326c079c,
title = "Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion",
abstract = "In this paper, we propose and validate a fully automated pipeline for simultaneous skull-stripping and lateral ventricle segmentation using T1-weighted images. The pipeline is built upon a segmentation algorithm entitled fast multi-atlas likelihood-fusion (MALF) which utilizes multiple T1 atlases that have been pre-segmented into six whole-brain labels-the gray matter, the white matter, the cerebrospinal fluid, the lateral ventricles, the skull, and the background of the entire image. This algorithm, MALF, was designed for estimating brain anatomical structures in the framework of coordinate changes via large diffeomorphisms. In the proposed pipeline, we use a variant of MALF to estimate those six whole-brain labels in the test T1-weighted image. The three tissue labels (gray matter, white matter, and cerebrospinal fluid) and the lateral ventricles are then grouped together to form a binary brain mask to which we apply morphological smoothing so as to create the final mask for brain extraction. For computational purposes, all input images to MALF are down-sampled by a factor of two. In addition, small deformations are used for the changes of coordinates. This substantially reduces the computational complexity, hence we use the term {"}fast MALF{"}. The skull-stripping performance is qualitatively evaluated on a total of 486 brain scans from a longitudinal study on Alzheimer dementia. Quantitative error analysis is carried out on 36 scans for evaluating the accuracy of the pipeline in segmenting the lateral ventricle. The volumes of the automated lateral ventricle segmentations, obtained from the proposed pipeline, are compared across three different clinical groups. The ventricle volumes from our pipeline are found to be sensitive to the diagnosis.",
keywords = "Alzheimer's disease, lateral ventricle, likelihood-fusion, multi-atlas, segmentation, Skull-stripping",
author = "Xiaoying Tang and Kwame Kutten and Can Ceritoglu and Susumu Mori and Miller, {Michael I.}",
year = "2015",
doi = "10.1117/12.2080830",
language = "English (US)",
isbn = "9781628415032",
volume = "9413",
booktitle = "Medical Imaging 2015: Image Processing",
publisher = "SPIE",

}

TY - GEN

T1 - Simultaneous skull-stripping and lateral ventricle segmentation via fast multi-atlas likelihood fusion

AU - Tang, Xiaoying

AU - Kutten, Kwame

AU - Ceritoglu, Can

AU - Mori, Susumu

AU - Miller, Michael I.

PY - 2015

Y1 - 2015

N2 - In this paper, we propose and validate a fully automated pipeline for simultaneous skull-stripping and lateral ventricle segmentation using T1-weighted images. The pipeline is built upon a segmentation algorithm entitled fast multi-atlas likelihood-fusion (MALF) which utilizes multiple T1 atlases that have been pre-segmented into six whole-brain labels-the gray matter, the white matter, the cerebrospinal fluid, the lateral ventricles, the skull, and the background of the entire image. This algorithm, MALF, was designed for estimating brain anatomical structures in the framework of coordinate changes via large diffeomorphisms. In the proposed pipeline, we use a variant of MALF to estimate those six whole-brain labels in the test T1-weighted image. The three tissue labels (gray matter, white matter, and cerebrospinal fluid) and the lateral ventricles are then grouped together to form a binary brain mask to which we apply morphological smoothing so as to create the final mask for brain extraction. For computational purposes, all input images to MALF are down-sampled by a factor of two. In addition, small deformations are used for the changes of coordinates. This substantially reduces the computational complexity, hence we use the term "fast MALF". The skull-stripping performance is qualitatively evaluated on a total of 486 brain scans from a longitudinal study on Alzheimer dementia. Quantitative error analysis is carried out on 36 scans for evaluating the accuracy of the pipeline in segmenting the lateral ventricle. The volumes of the automated lateral ventricle segmentations, obtained from the proposed pipeline, are compared across three different clinical groups. The ventricle volumes from our pipeline are found to be sensitive to the diagnosis.

AB - In this paper, we propose and validate a fully automated pipeline for simultaneous skull-stripping and lateral ventricle segmentation using T1-weighted images. The pipeline is built upon a segmentation algorithm entitled fast multi-atlas likelihood-fusion (MALF) which utilizes multiple T1 atlases that have been pre-segmented into six whole-brain labels-the gray matter, the white matter, the cerebrospinal fluid, the lateral ventricles, the skull, and the background of the entire image. This algorithm, MALF, was designed for estimating brain anatomical structures in the framework of coordinate changes via large diffeomorphisms. In the proposed pipeline, we use a variant of MALF to estimate those six whole-brain labels in the test T1-weighted image. The three tissue labels (gray matter, white matter, and cerebrospinal fluid) and the lateral ventricles are then grouped together to form a binary brain mask to which we apply morphological smoothing so as to create the final mask for brain extraction. For computational purposes, all input images to MALF are down-sampled by a factor of two. In addition, small deformations are used for the changes of coordinates. This substantially reduces the computational complexity, hence we use the term "fast MALF". The skull-stripping performance is qualitatively evaluated on a total of 486 brain scans from a longitudinal study on Alzheimer dementia. Quantitative error analysis is carried out on 36 scans for evaluating the accuracy of the pipeline in segmenting the lateral ventricle. The volumes of the automated lateral ventricle segmentations, obtained from the proposed pipeline, are compared across three different clinical groups. The ventricle volumes from our pipeline are found to be sensitive to the diagnosis.

KW - Alzheimer's disease

KW - lateral ventricle

KW - likelihood-fusion

KW - multi-atlas

KW - segmentation

KW - Skull-stripping

UR - http://www.scopus.com/inward/record.url?scp=84943414224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943414224&partnerID=8YFLogxK

U2 - 10.1117/12.2080830

DO - 10.1117/12.2080830

M3 - Conference contribution

AN - SCOPUS:84943414224

SN - 9781628415032

VL - 9413

BT - Medical Imaging 2015: Image Processing

PB - SPIE

ER -