Spatio-angular consistent construction of neonatal diffusion MRI atlases

Behrouz Saghafi, Jaeil Kim, Geng Chen, Feng Shi, Weili Lin, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Atlases constructed using diffusion-weighted imaging are important tools for studying human brain development. Atlas construction is in general a two-step process involving spatial registration and fusion of individual images. The focus of most studies so far has been on improving the accuracy of registration while image fusion is commonly performed using simple averaging, often resulting in fuzzy atlases. In this article, we propose a patch-based method for diffusion-weighted (DW) atlas construction. Unlike other atlases that are based on the diffusion tensor model, our atlas is model-free and generated directly from the diffusion-weighted images. Instead of independently generating an atlas for each gradient direction and hence neglecting angular image correlation, we propose to construct the atlas by jointly considering DW images of neighboring gradient directions. We employ a group regularization framework where local patches of angularly neighboring images are constrained for consistent spatio-angular atlas reconstruction. Experimental results confirm that our atlas, constructed for neonatal data, reveals more structural details with higher fractional anisotropy than the atlas generated without angular consistency as well as the average atlas. Also the normalization of test subjects to the proposed atlas results in better alignment of brain structures.

Original languageEnglish
JournalHuman Brain Mapping
DOIs
Publication statusAccepted/In press - 2017

Fingerprint

Diffusion Magnetic Resonance Imaging
Atlases
Anisotropy
Brain
Human Development

Keywords

  • Diffusion MRI
  • Multi-task learning
  • Neonatal brain atlases
  • Sparse representation
  • Spatio-angular consistency

ASJC Scopus subject areas

  • Anatomy
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology

Cite this

Spatio-angular consistent construction of neonatal diffusion MRI atlases. / Saghafi, Behrouz; Kim, Jaeil; Chen, Geng; Shi, Feng; Lin, Weili; Yap, Pew Thian; Shen, Dinggang.

In: Human Brain Mapping, 2017.

Research output: Contribution to journalArticle

Saghafi, Behrouz ; Kim, Jaeil ; Chen, Geng ; Shi, Feng ; Lin, Weili ; Yap, Pew Thian ; Shen, Dinggang. / Spatio-angular consistent construction of neonatal diffusion MRI atlases. In: Human Brain Mapping. 2017.
@article{4247ab8949b945b29bd2b99e6c12aa8e,
title = "Spatio-angular consistent construction of neonatal diffusion MRI atlases",
abstract = "Atlases constructed using diffusion-weighted imaging are important tools for studying human brain development. Atlas construction is in general a two-step process involving spatial registration and fusion of individual images. The focus of most studies so far has been on improving the accuracy of registration while image fusion is commonly performed using simple averaging, often resulting in fuzzy atlases. In this article, we propose a patch-based method for diffusion-weighted (DW) atlas construction. Unlike other atlases that are based on the diffusion tensor model, our atlas is model-free and generated directly from the diffusion-weighted images. Instead of independently generating an atlas for each gradient direction and hence neglecting angular image correlation, we propose to construct the atlas by jointly considering DW images of neighboring gradient directions. We employ a group regularization framework where local patches of angularly neighboring images are constrained for consistent spatio-angular atlas reconstruction. Experimental results confirm that our atlas, constructed for neonatal data, reveals more structural details with higher fractional anisotropy than the atlas generated without angular consistency as well as the average atlas. Also the normalization of test subjects to the proposed atlas results in better alignment of brain structures.",
keywords = "Diffusion MRI, Multi-task learning, Neonatal brain atlases, Sparse representation, Spatio-angular consistency",
author = "Behrouz Saghafi and Jaeil Kim and Geng Chen and Feng Shi and Weili Lin and Yap, {Pew Thian} and Dinggang Shen",
year = "2017",
doi = "10.1002/hbm.23583",
language = "English",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",

}

TY - JOUR

T1 - Spatio-angular consistent construction of neonatal diffusion MRI atlases

AU - Saghafi, Behrouz

AU - Kim, Jaeil

AU - Chen, Geng

AU - Shi, Feng

AU - Lin, Weili

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2017

Y1 - 2017

N2 - Atlases constructed using diffusion-weighted imaging are important tools for studying human brain development. Atlas construction is in general a two-step process involving spatial registration and fusion of individual images. The focus of most studies so far has been on improving the accuracy of registration while image fusion is commonly performed using simple averaging, often resulting in fuzzy atlases. In this article, we propose a patch-based method for diffusion-weighted (DW) atlas construction. Unlike other atlases that are based on the diffusion tensor model, our atlas is model-free and generated directly from the diffusion-weighted images. Instead of independently generating an atlas for each gradient direction and hence neglecting angular image correlation, we propose to construct the atlas by jointly considering DW images of neighboring gradient directions. We employ a group regularization framework where local patches of angularly neighboring images are constrained for consistent spatio-angular atlas reconstruction. Experimental results confirm that our atlas, constructed for neonatal data, reveals more structural details with higher fractional anisotropy than the atlas generated without angular consistency as well as the average atlas. Also the normalization of test subjects to the proposed atlas results in better alignment of brain structures.

AB - Atlases constructed using diffusion-weighted imaging are important tools for studying human brain development. Atlas construction is in general a two-step process involving spatial registration and fusion of individual images. The focus of most studies so far has been on improving the accuracy of registration while image fusion is commonly performed using simple averaging, often resulting in fuzzy atlases. In this article, we propose a patch-based method for diffusion-weighted (DW) atlas construction. Unlike other atlases that are based on the diffusion tensor model, our atlas is model-free and generated directly from the diffusion-weighted images. Instead of independently generating an atlas for each gradient direction and hence neglecting angular image correlation, we propose to construct the atlas by jointly considering DW images of neighboring gradient directions. We employ a group regularization framework where local patches of angularly neighboring images are constrained for consistent spatio-angular atlas reconstruction. Experimental results confirm that our atlas, constructed for neonatal data, reveals more structural details with higher fractional anisotropy than the atlas generated without angular consistency as well as the average atlas. Also the normalization of test subjects to the proposed atlas results in better alignment of brain structures.

KW - Diffusion MRI

KW - Multi-task learning

KW - Neonatal brain atlases

KW - Sparse representation

KW - Spatio-angular consistency

UR - http://www.scopus.com/inward/record.url?scp=85016503414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016503414&partnerID=8YFLogxK

U2 - 10.1002/hbm.23583

DO - 10.1002/hbm.23583

M3 - Article

C2 - 28345171

AN - SCOPUS:85016503414

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

ER -