Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation

Snehashis Roy, Qing He, Elizabeth Sweeney, Aaron Carass, Daniel S. Reich, Jerry Ladd Prince, Dzung L. Pham

Research output: Contribution to journalArticle

Abstract

Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.

Original languageEnglish (US)
Article number7114201
Pages (from-to)1598-1609
Number of pages12
JournalIEEE Journal of Biomedical and Health Informatics
Volume19
Issue number5
DOIs
StatePublished - Sep 1 2015

Fingerprint

Atlases
Glossaries
Magnetic resonance imaging
Brain
Learning
Tissue
Magnetic resonance
Magnetic Resonance Spectroscopy
Biomarkers
Normal Pressure Hydrocephalus
Aging of materials
Multiple Sclerosis
Disease Progression
Anatomy
Healthy Volunteers

Keywords

  • brain
  • dictionary
  • histogram matching
  • magnetic resonance imaging (MRI)
  • patches
  • segmentation
  • sparsity

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation. / Roy, Snehashis; He, Qing; Sweeney, Elizabeth; Carass, Aaron; Reich, Daniel S.; Prince, Jerry Ladd; Pham, Dzung L.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 19, No. 5, 7114201, 01.09.2015, p. 1598-1609.

Research output: Contribution to journalArticle

Roy, Snehashis ; He, Qing ; Sweeney, Elizabeth ; Carass, Aaron ; Reich, Daniel S. ; Prince, Jerry Ladd ; Pham, Dzung L. / Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation. In: IEEE Journal of Biomedical and Health Informatics. 2015 ; Vol. 19, No. 5. pp. 1598-1609.
@article{959070cdac9e41639656674f644fdc8d,
title = "Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation",
abstract = "Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.",
keywords = "brain, dictionary, histogram matching, magnetic resonance imaging (MRI), patches, segmentation, sparsity",
author = "Snehashis Roy and Qing He and Elizabeth Sweeney and Aaron Carass and Reich, {Daniel S.} and Prince, {Jerry Ladd} and Pham, {Dzung L.}",
year = "2015",
month = "9",
day = "1",
doi = "10.1109/JBHI.2015.2439242",
language = "English (US)",
volume = "19",
pages = "1598--1609",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation

AU - Roy, Snehashis

AU - He, Qing

AU - Sweeney, Elizabeth

AU - Carass, Aaron

AU - Reich, Daniel S.

AU - Prince, Jerry Ladd

AU - Pham, Dzung L.

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.

AB - Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.

KW - brain

KW - dictionary

KW - histogram matching

KW - magnetic resonance imaging (MRI)

KW - patches

KW - segmentation

KW - sparsity

UR - http://www.scopus.com/inward/record.url?scp=84940979990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940979990&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2015.2439242

DO - 10.1109/JBHI.2015.2439242

M3 - Article

VL - 19

SP - 1598

EP - 1609

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 5

M1 - 7114201

ER -