Robust fast automatic skull stripping of MRI-T2 data

Srinivasan Rajagopalan, Ronald A. Karwoski, Richard Robb

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

3 Citations (Scopus)

Abstract

The efficacy of image processing and analysis on skull stripped MR images vis-à-vis the original images is well established. Additionally, compliance with the Health Insurance Portability and Accountability Act (HIPAA) requires neuroimage repositories to anonymise the images before sharing them. This makes the non-trivial skull stripping process all the more significant. While a number of optimal approaches exist to strip the skull from T1-weighted MR images to the best of our knowledge, there is no simple, robust, fast, parameter free and fully automatic technique to perform the same on T2-weighted images. This paper presents a strategy to fill this gap. It employs a fast parameterization of the T2 image intensity onto a standardized T1 intensity scale. The parametric "T1-like" image obtained via the transformation, which takes only a few seconds to compute, is subsequently processed by any of the many T1-based brain extraction techniques to derive the brain mask. Masking the original T2 image with this brain mask strips the skull. By standardizing the intensity of the parametric image, preset algorithm-specific parameters (if any) could be used across multiple datasets. The proposed scheme has been used in a number of phantom and clinical T2 brain datasets to successfully strip the skull.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
EditorsJ.M. Fitzpatrick, J.M. Reinhardt
Pages485-495
Number of pages11
Volume5747
EditionI
DOIs
StatePublished - 2005
EventMedical Imaging 2005 - Image Processing - San Diego, CA, United States
Duration: Feb 13 2005Feb 17 2005

Other

OtherMedical Imaging 2005 - Image Processing
CountryUnited States
CitySan Diego, CA
Period2/13/052/17/05

Fingerprint

Magnetic resonance imaging
Brain
Masks
Health insurance
Parameterization
Image analysis
Image processing

Keywords

  • Brain extraction
  • Parametric images
  • Skull stripping
  • T2 MRI
  • Thresholding
  • Watershed

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Rajagopalan, S., Karwoski, R. A., & Robb, R. (2005). Robust fast automatic skull stripping of MRI-T2 data. In J. M. Fitzpatrick, & J. M. Reinhardt (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE (I ed., Vol. 5747, pp. 485-495). [50] https://doi.org/10.1117/12.594651

Robust fast automatic skull stripping of MRI-T2 data. / Rajagopalan, Srinivasan; Karwoski, Ronald A.; Robb, Richard.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. ed. / J.M. Fitzpatrick; J.M. Reinhardt. Vol. 5747 I. ed. 2005. p. 485-495 50.

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

Rajagopalan, S, Karwoski, RA & Robb, R 2005, Robust fast automatic skull stripping of MRI-T2 data. in JM Fitzpatrick & JM Reinhardt (eds), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. I edn, vol. 5747, 50, pp. 485-495, Medical Imaging 2005 - Image Processing, San Diego, CA, United States, 2/13/05. https://doi.org/10.1117/12.594651
Rajagopalan S, Karwoski RA, Robb R. Robust fast automatic skull stripping of MRI-T2 data. In Fitzpatrick JM, Reinhardt JM, editors, Progress in Biomedical Optics and Imaging - Proceedings of SPIE. I ed. Vol. 5747. 2005. p. 485-495. 50 https://doi.org/10.1117/12.594651
Rajagopalan, Srinivasan ; Karwoski, Ronald A. ; Robb, Richard. / Robust fast automatic skull stripping of MRI-T2 data. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. editor / J.M. Fitzpatrick ; J.M. Reinhardt. Vol. 5747 I. ed. 2005. pp. 485-495
@inproceedings{d4d595ed785e4d6ca9e57cab8c22e512,
title = "Robust fast automatic skull stripping of MRI-T2 data",
abstract = "The efficacy of image processing and analysis on skull stripped MR images vis-{\`a}-vis the original images is well established. Additionally, compliance with the Health Insurance Portability and Accountability Act (HIPAA) requires neuroimage repositories to anonymise the images before sharing them. This makes the non-trivial skull stripping process all the more significant. While a number of optimal approaches exist to strip the skull from T1-weighted MR images to the best of our knowledge, there is no simple, robust, fast, parameter free and fully automatic technique to perform the same on T2-weighted images. This paper presents a strategy to fill this gap. It employs a fast parameterization of the T2 image intensity onto a standardized T1 intensity scale. The parametric {"}T1-like{"} image obtained via the transformation, which takes only a few seconds to compute, is subsequently processed by any of the many T1-based brain extraction techniques to derive the brain mask. Masking the original T2 image with this brain mask strips the skull. By standardizing the intensity of the parametric image, preset algorithm-specific parameters (if any) could be used across multiple datasets. The proposed scheme has been used in a number of phantom and clinical T2 brain datasets to successfully strip the skull.",
keywords = "Brain extraction, Parametric images, Skull stripping, T2 MRI, Thresholding, Watershed",
author = "Srinivasan Rajagopalan and Karwoski, {Ronald A.} and Richard Robb",
year = "2005",
doi = "10.1117/12.594651",
language = "English (US)",
volume = "5747",
pages = "485--495",
editor = "J.M. Fitzpatrick and J.M. Reinhardt",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
edition = "I",

}

TY - GEN

T1 - Robust fast automatic skull stripping of MRI-T2 data

AU - Rajagopalan, Srinivasan

AU - Karwoski, Ronald A.

AU - Robb, Richard

PY - 2005

Y1 - 2005

N2 - The efficacy of image processing and analysis on skull stripped MR images vis-à-vis the original images is well established. Additionally, compliance with the Health Insurance Portability and Accountability Act (HIPAA) requires neuroimage repositories to anonymise the images before sharing them. This makes the non-trivial skull stripping process all the more significant. While a number of optimal approaches exist to strip the skull from T1-weighted MR images to the best of our knowledge, there is no simple, robust, fast, parameter free and fully automatic technique to perform the same on T2-weighted images. This paper presents a strategy to fill this gap. It employs a fast parameterization of the T2 image intensity onto a standardized T1 intensity scale. The parametric "T1-like" image obtained via the transformation, which takes only a few seconds to compute, is subsequently processed by any of the many T1-based brain extraction techniques to derive the brain mask. Masking the original T2 image with this brain mask strips the skull. By standardizing the intensity of the parametric image, preset algorithm-specific parameters (if any) could be used across multiple datasets. The proposed scheme has been used in a number of phantom and clinical T2 brain datasets to successfully strip the skull.

AB - The efficacy of image processing and analysis on skull stripped MR images vis-à-vis the original images is well established. Additionally, compliance with the Health Insurance Portability and Accountability Act (HIPAA) requires neuroimage repositories to anonymise the images before sharing them. This makes the non-trivial skull stripping process all the more significant. While a number of optimal approaches exist to strip the skull from T1-weighted MR images to the best of our knowledge, there is no simple, robust, fast, parameter free and fully automatic technique to perform the same on T2-weighted images. This paper presents a strategy to fill this gap. It employs a fast parameterization of the T2 image intensity onto a standardized T1 intensity scale. The parametric "T1-like" image obtained via the transformation, which takes only a few seconds to compute, is subsequently processed by any of the many T1-based brain extraction techniques to derive the brain mask. Masking the original T2 image with this brain mask strips the skull. By standardizing the intensity of the parametric image, preset algorithm-specific parameters (if any) could be used across multiple datasets. The proposed scheme has been used in a number of phantom and clinical T2 brain datasets to successfully strip the skull.

KW - Brain extraction

KW - Parametric images

KW - Skull stripping

KW - T2 MRI

KW - Thresholding

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=23844459271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23844459271&partnerID=8YFLogxK

U2 - 10.1117/12.594651

DO - 10.1117/12.594651

M3 - Conference contribution

AN - SCOPUS:23844459271

VL - 5747

SP - 485

EP - 495

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

A2 - Fitzpatrick, J.M.

A2 - Reinhardt, J.M.

ER -