Robust skull stripping using multiple MR image contrasts insensitive to pathology

Snehashis Roy, John A. Butman, Dzung L. Pham

Research output: Contribution to journalArticle

Abstract

Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed in the past, it is still an active area of research particularly in the context of brain pathology. Most stripping methods are validated on T1-w MR images of normal brains, especially because high resolution T1-w sequences are widely acquired and ground truth manual brain mask segmentations are publicly available for normal brains. However, different MR acquisition protocols can provide complementary information about the brain tissues, which can be exploited for better distinction between brain, cerebrospinal fluid, and unwanted tissues such as skull, dura, marrow, or fat. This is especially true in the presence of pathology, where hemorrhages or other types of lesions can have similar intensities as skull in a T1-w image. In this paper, we propose a sparse patch based Multi-cONtrast brain STRipping method (MONSTR)2, where non-local patch information from one or more atlases, which contain multiple MR sequences and reference delineations of brain masks, are combined to generate a target brain mask. We compared MONSTR with four state-of-the-art, publicly available methods: BEaST, SPECTRE, ROBEX, and OptiBET. We evaluated the performance of these methods on 6 datasets consisting of both healthy subjects and patients with various pathologies. Three datasets (ADNI, MRBrainS, NAMIC) are publicly available, consisting of 44 healthy volunteers and 10 patients with schizophrenia. Other three in-house datasets, comprising 87 subjects in total, consisted of patients with mild to severe traumatic brain injury, brain tumors, and various movement disorders. A combination of T1-w, T2-w were used to skull-strip these datasets. We show significant improvement in stripping over the competing methods on both healthy and pathological brains. We also show that our multi-contrast framework is robust and maintains accurate performance across different types of acquisitions and scanners, even when using normal brains as atlases to strip pathological brains, demonstrating that our algorithm is applicable even when reference segmentations of pathological brains are not available to be used as atlases.

Original languageEnglish (US)
Pages (from-to)132-147
Number of pages16
JournalNeuroImage
Volume146
DOIs
StatePublished - Feb 1 2017
Externally publishedYes

Fingerprint

Skull
Magnetic Resonance Spectroscopy
Pathology
Brain
Atlases
Masks
Healthy Volunteers
Movement Disorders
Brain Neoplasms
Cerebrospinal Fluid
Schizophrenia
Bone Marrow
Fats
Hemorrhage

Keywords

  • Atlas
  • Brain extraction
  • Non-local
  • Patches
  • Segmentation
  • Skull stripping
  • Sparsity

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Robust skull stripping using multiple MR image contrasts insensitive to pathology. / Roy, Snehashis; Butman, John A.; Pham, Dzung L.

In: NeuroImage, Vol. 146, 01.02.2017, p. 132-147.

Research output: Contribution to journalArticle

Roy, Snehashis ; Butman, John A. ; Pham, Dzung L. / Robust skull stripping using multiple MR image contrasts insensitive to pathology. In: NeuroImage. 2017 ; Vol. 146. pp. 132-147.
@article{45345d7eb1d648dc965f222d9577eca4,
title = "Robust skull stripping using multiple MR image contrasts insensitive to pathology",
abstract = "Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed in the past, it is still an active area of research particularly in the context of brain pathology. Most stripping methods are validated on T1-w MR images of normal brains, especially because high resolution T1-w sequences are widely acquired and ground truth manual brain mask segmentations are publicly available for normal brains. However, different MR acquisition protocols can provide complementary information about the brain tissues, which can be exploited for better distinction between brain, cerebrospinal fluid, and unwanted tissues such as skull, dura, marrow, or fat. This is especially true in the presence of pathology, where hemorrhages or other types of lesions can have similar intensities as skull in a T1-w image. In this paper, we propose a sparse patch based Multi-cONtrast brain STRipping method (MONSTR)2, where non-local patch information from one or more atlases, which contain multiple MR sequences and reference delineations of brain masks, are combined to generate a target brain mask. We compared MONSTR with four state-of-the-art, publicly available methods: BEaST, SPECTRE, ROBEX, and OptiBET. We evaluated the performance of these methods on 6 datasets consisting of both healthy subjects and patients with various pathologies. Three datasets (ADNI, MRBrainS, NAMIC) are publicly available, consisting of 44 healthy volunteers and 10 patients with schizophrenia. Other three in-house datasets, comprising 87 subjects in total, consisted of patients with mild to severe traumatic brain injury, brain tumors, and various movement disorders. A combination of T1-w, T2-w were used to skull-strip these datasets. We show significant improvement in stripping over the competing methods on both healthy and pathological brains. We also show that our multi-contrast framework is robust and maintains accurate performance across different types of acquisitions and scanners, even when using normal brains as atlases to strip pathological brains, demonstrating that our algorithm is applicable even when reference segmentations of pathological brains are not available to be used as atlases.",
keywords = "Atlas, Brain extraction, Non-local, Patches, Segmentation, Skull stripping, Sparsity",
author = "Snehashis Roy and Butman, {John A.} and Pham, {Dzung L.}",
year = "2017",
month = "2",
day = "1",
doi = "10.1016/j.neuroimage.2016.11.017",
language = "English (US)",
volume = "146",
pages = "132--147",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Robust skull stripping using multiple MR image contrasts insensitive to pathology

AU - Roy, Snehashis

AU - Butman, John A.

AU - Pham, Dzung L.

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed in the past, it is still an active area of research particularly in the context of brain pathology. Most stripping methods are validated on T1-w MR images of normal brains, especially because high resolution T1-w sequences are widely acquired and ground truth manual brain mask segmentations are publicly available for normal brains. However, different MR acquisition protocols can provide complementary information about the brain tissues, which can be exploited for better distinction between brain, cerebrospinal fluid, and unwanted tissues such as skull, dura, marrow, or fat. This is especially true in the presence of pathology, where hemorrhages or other types of lesions can have similar intensities as skull in a T1-w image. In this paper, we propose a sparse patch based Multi-cONtrast brain STRipping method (MONSTR)2, where non-local patch information from one or more atlases, which contain multiple MR sequences and reference delineations of brain masks, are combined to generate a target brain mask. We compared MONSTR with four state-of-the-art, publicly available methods: BEaST, SPECTRE, ROBEX, and OptiBET. We evaluated the performance of these methods on 6 datasets consisting of both healthy subjects and patients with various pathologies. Three datasets (ADNI, MRBrainS, NAMIC) are publicly available, consisting of 44 healthy volunteers and 10 patients with schizophrenia. Other three in-house datasets, comprising 87 subjects in total, consisted of patients with mild to severe traumatic brain injury, brain tumors, and various movement disorders. A combination of T1-w, T2-w were used to skull-strip these datasets. We show significant improvement in stripping over the competing methods on both healthy and pathological brains. We also show that our multi-contrast framework is robust and maintains accurate performance across different types of acquisitions and scanners, even when using normal brains as atlases to strip pathological brains, demonstrating that our algorithm is applicable even when reference segmentations of pathological brains are not available to be used as atlases.

AB - Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed in the past, it is still an active area of research particularly in the context of brain pathology. Most stripping methods are validated on T1-w MR images of normal brains, especially because high resolution T1-w sequences are widely acquired and ground truth manual brain mask segmentations are publicly available for normal brains. However, different MR acquisition protocols can provide complementary information about the brain tissues, which can be exploited for better distinction between brain, cerebrospinal fluid, and unwanted tissues such as skull, dura, marrow, or fat. This is especially true in the presence of pathology, where hemorrhages or other types of lesions can have similar intensities as skull in a T1-w image. In this paper, we propose a sparse patch based Multi-cONtrast brain STRipping method (MONSTR)2, where non-local patch information from one or more atlases, which contain multiple MR sequences and reference delineations of brain masks, are combined to generate a target brain mask. We compared MONSTR with four state-of-the-art, publicly available methods: BEaST, SPECTRE, ROBEX, and OptiBET. We evaluated the performance of these methods on 6 datasets consisting of both healthy subjects and patients with various pathologies. Three datasets (ADNI, MRBrainS, NAMIC) are publicly available, consisting of 44 healthy volunteers and 10 patients with schizophrenia. Other three in-house datasets, comprising 87 subjects in total, consisted of patients with mild to severe traumatic brain injury, brain tumors, and various movement disorders. A combination of T1-w, T2-w were used to skull-strip these datasets. We show significant improvement in stripping over the competing methods on both healthy and pathological brains. We also show that our multi-contrast framework is robust and maintains accurate performance across different types of acquisitions and scanners, even when using normal brains as atlases to strip pathological brains, demonstrating that our algorithm is applicable even when reference segmentations of pathological brains are not available to be used as atlases.

KW - Atlas

KW - Brain extraction

KW - Non-local

KW - Patches

KW - Segmentation

KW - Skull stripping

KW - Sparsity

UR - http://www.scopus.com/inward/record.url?scp=84999885073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84999885073&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2016.11.017

DO - 10.1016/j.neuroimage.2016.11.017

M3 - Article

VL - 146

SP - 132

EP - 147

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -