Atlas-free Brain Tissue Segmentation Using a Single T1-weighted MRI Acquisition

Kober, Tobias and Roche, Alexis and Esteban Sanz-Dranguet, Oscar and Gorthi, Subrahmanyam and Rives, Delphine and Bach-Cuadra, Meritxell and Meuli, Reto and Krueger, Gunnar (2012). Atlas-free Brain Tissue Segmentation Using a Single T1-weighted MRI Acquisition. In: "20th Annual Meeting and Exhibition of the International Society for Magnetic Resonance in Medicine", 05/05/2012 - 11/05/2012, Melbourne, Australia. p. 753.

Description

Title: Atlas-free Brain Tissue Segmentation Using a Single T1-weighted MRI Acquisition
Author/s:
  • Kober, Tobias
  • Roche, Alexis
  • Esteban Sanz-Dranguet, Oscar
  • Gorthi, Subrahmanyam
  • Rives, Delphine
  • Bach-Cuadra, Meritxell
  • Meuli, Reto
  • Krueger, Gunnar
Item Type: Presentation at Congress or Conference (Article)
Event Title: 20th Annual Meeting and Exhibition of the International Society for Magnetic Resonance in Medicine
Event Dates: 05/05/2012 - 11/05/2012
Event Location: Melbourne, Australia
Title of Book: Proceedings of the international society for magnetic resonance in medicine
Date: May 2012
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería Electrónica
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Many studies investigating the aging brain or disease-induced brain alterations rely on accurate and reproducible brain tissue segmentation. Being a preliminary processing step prior to the segmentation, reliableskull-stripping the removal ofnon-brain tissue is also crucial for all later image assessment. Typically, segmentation algorithms rely on an atlas i.e. pre-segmented template data. Brain morphology, however, differs considerably depending on age, sex and race. In addition, diseased brains may deviate significantly from the atlas information typically gained from healthy volunteers. The imposed prior atlas information can thus lead to degradation of segmentation results. The recently introduced MP2RAGE sequence provides a bias-free T1 contrast with heavily reduced T2*- and PD-weighting compared to the standard MP-RAGE [1]. To this end, it acquires two image volumes at different inversion times in one acquisition, combining them to a uniform, i.e. homogenous image. In this work, we exploit the advantageous contrast properties of the MP2RAGE and combine it with a Dixon (i.e. fat-water separation) approach. The information gained by the additional fat image of the head considerably improves the skull-stripping outcome [2]. In conjunction with the pure T1 contrast of the MP2RAGE uniform image, we achieve robust skull-stripping and brain tissue segmentation without the use of an atlas

More information

Item ID: 19796
DC Identifier: http://oa.upm.es/19796/
OAI Identifier: oai:oa.upm.es:19796
Deposited by: Memoria Investigacion
Deposited on: 21 Sep 2013 07:33
Last Modified: 21 Apr 2016 21:16
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM