Hierarchical and symmetric infant image registration by robust longitudinal-example-guided correspondence detection

Yao Wu, Guorong Wu, Li Wang, Brent C. Munsell, Qian Wang, Weili Lin, Qianjin Feng, Wufan Chen, Dinggang Shen

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Purpose: To investigate anatomical differences across individual subjects, or longitudinal changes in early brain development, it is important to perform accurate image registration. However, due to fast brain development and dynamic tissue appearance changes, it is very difficult to align infant brain images acquired from birth to 1-yr-old. Methods: To solve this challenging problem, a novel image registration method is proposed to align two infant brain images, regardless of age at acquisition. The main idea is to utilize the growth trajectories, or spatial-temporal correspondences, learned from a set of longitudinal training images, for guiding the registration of two different time-point images with different image appearances. Specifically, in the training stage, an intrinsic growth trajectory is first estimated for each training subject using the longitudinal images. To register two new infant images with potentially a large age gap, the corresponding images patches between each new image and its respective training images with similar age are identified. Finally, the registration between the two new images can be assisted by the learned growth trajectories from one time point to another time point that have been established in the training stage. To further improve registration accuracy, the proposed method is combined with a hierarchical and symmetric registration framework that can iteratively add new key points in both images to steer the estimation of the deformation between the two infant brain images under registration. Results: To evaluate image registration accuracy, the proposed method is used to align 24 infant subjects at five different time points (2-week-old, 3-month-old, 6-month-old, 9-month-old, and 12- month-old). Compared to the state-of-the-art methods, the proposed method demonstrated superior registration performance. Conclusions: The proposed method addresses the difficulties in the infant brain registration and produces better results compared to existing state-of-the-art registration methods.

Original languageEnglish
Pages (from-to)4174-4189
Number of pages16
JournalMedical Physics
Volume42
Issue number7
DOIs
Publication statusPublished - 2015 Jul 1

Fingerprint

Brain
Growth
Individuality
Parturition

Keywords

  • correspondence detection
  • hierarchical and symmetric registration
  • infant brain registration

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Hierarchical and symmetric infant image registration by robust longitudinal-example-guided correspondence detection. / Wu, Yao; Wu, Guorong; Wang, Li; Munsell, Brent C.; Wang, Qian; Lin, Weili; Feng, Qianjin; Chen, Wufan; Shen, Dinggang.

In: Medical Physics, Vol. 42, No. 7, 01.07.2015, p. 4174-4189.

Research output: Contribution to journalArticle

Wu, Yao ; Wu, Guorong ; Wang, Li ; Munsell, Brent C. ; Wang, Qian ; Lin, Weili ; Feng, Qianjin ; Chen, Wufan ; Shen, Dinggang. / Hierarchical and symmetric infant image registration by robust longitudinal-example-guided correspondence detection. In: Medical Physics. 2015 ; Vol. 42, No. 7. pp. 4174-4189.
@article{7e2c815c4c5e46eca89bc3ca9ca748f0,
title = "Hierarchical and symmetric infant image registration by robust longitudinal-example-guided correspondence detection",
abstract = "Purpose: To investigate anatomical differences across individual subjects, or longitudinal changes in early brain development, it is important to perform accurate image registration. However, due to fast brain development and dynamic tissue appearance changes, it is very difficult to align infant brain images acquired from birth to 1-yr-old. Methods: To solve this challenging problem, a novel image registration method is proposed to align two infant brain images, regardless of age at acquisition. The main idea is to utilize the growth trajectories, or spatial-temporal correspondences, learned from a set of longitudinal training images, for guiding the registration of two different time-point images with different image appearances. Specifically, in the training stage, an intrinsic growth trajectory is first estimated for each training subject using the longitudinal images. To register two new infant images with potentially a large age gap, the corresponding images patches between each new image and its respective training images with similar age are identified. Finally, the registration between the two new images can be assisted by the learned growth trajectories from one time point to another time point that have been established in the training stage. To further improve registration accuracy, the proposed method is combined with a hierarchical and symmetric registration framework that can iteratively add new key points in both images to steer the estimation of the deformation between the two infant brain images under registration. Results: To evaluate image registration accuracy, the proposed method is used to align 24 infant subjects at five different time points (2-week-old, 3-month-old, 6-month-old, 9-month-old, and 12- month-old). Compared to the state-of-the-art methods, the proposed method demonstrated superior registration performance. Conclusions: The proposed method addresses the difficulties in the infant brain registration and produces better results compared to existing state-of-the-art registration methods.",
keywords = "correspondence detection, hierarchical and symmetric registration, infant brain registration",
author = "Yao Wu and Guorong Wu and Li Wang and Munsell, {Brent C.} and Qian Wang and Weili Lin and Qianjin Feng and Wufan Chen and Dinggang Shen",
year = "2015",
month = "7",
day = "1",
doi = "10.1118/1.4922393",
language = "English",
volume = "42",
pages = "4174--4189",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "7",

}

TY - JOUR

T1 - Hierarchical and symmetric infant image registration by robust longitudinal-example-guided correspondence detection

AU - Wu, Yao

AU - Wu, Guorong

AU - Wang, Li

AU - Munsell, Brent C.

AU - Wang, Qian

AU - Lin, Weili

AU - Feng, Qianjin

AU - Chen, Wufan

AU - Shen, Dinggang

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Purpose: To investigate anatomical differences across individual subjects, or longitudinal changes in early brain development, it is important to perform accurate image registration. However, due to fast brain development and dynamic tissue appearance changes, it is very difficult to align infant brain images acquired from birth to 1-yr-old. Methods: To solve this challenging problem, a novel image registration method is proposed to align two infant brain images, regardless of age at acquisition. The main idea is to utilize the growth trajectories, or spatial-temporal correspondences, learned from a set of longitudinal training images, for guiding the registration of two different time-point images with different image appearances. Specifically, in the training stage, an intrinsic growth trajectory is first estimated for each training subject using the longitudinal images. To register two new infant images with potentially a large age gap, the corresponding images patches between each new image and its respective training images with similar age are identified. Finally, the registration between the two new images can be assisted by the learned growth trajectories from one time point to another time point that have been established in the training stage. To further improve registration accuracy, the proposed method is combined with a hierarchical and symmetric registration framework that can iteratively add new key points in both images to steer the estimation of the deformation between the two infant brain images under registration. Results: To evaluate image registration accuracy, the proposed method is used to align 24 infant subjects at five different time points (2-week-old, 3-month-old, 6-month-old, 9-month-old, and 12- month-old). Compared to the state-of-the-art methods, the proposed method demonstrated superior registration performance. Conclusions: The proposed method addresses the difficulties in the infant brain registration and produces better results compared to existing state-of-the-art registration methods.

AB - Purpose: To investigate anatomical differences across individual subjects, or longitudinal changes in early brain development, it is important to perform accurate image registration. However, due to fast brain development and dynamic tissue appearance changes, it is very difficult to align infant brain images acquired from birth to 1-yr-old. Methods: To solve this challenging problem, a novel image registration method is proposed to align two infant brain images, regardless of age at acquisition. The main idea is to utilize the growth trajectories, or spatial-temporal correspondences, learned from a set of longitudinal training images, for guiding the registration of two different time-point images with different image appearances. Specifically, in the training stage, an intrinsic growth trajectory is first estimated for each training subject using the longitudinal images. To register two new infant images with potentially a large age gap, the corresponding images patches between each new image and its respective training images with similar age are identified. Finally, the registration between the two new images can be assisted by the learned growth trajectories from one time point to another time point that have been established in the training stage. To further improve registration accuracy, the proposed method is combined with a hierarchical and symmetric registration framework that can iteratively add new key points in both images to steer the estimation of the deformation between the two infant brain images under registration. Results: To evaluate image registration accuracy, the proposed method is used to align 24 infant subjects at five different time points (2-week-old, 3-month-old, 6-month-old, 9-month-old, and 12- month-old). Compared to the state-of-the-art methods, the proposed method demonstrated superior registration performance. Conclusions: The proposed method addresses the difficulties in the infant brain registration and produces better results compared to existing state-of-the-art registration methods.

KW - correspondence detection

KW - hierarchical and symmetric registration

KW - infant brain registration

UR - http://www.scopus.com/inward/record.url?scp=84934991413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84934991413&partnerID=8YFLogxK

U2 - 10.1118/1.4922393

DO - 10.1118/1.4922393

M3 - Article

VL - 42

SP - 4174

EP - 4189

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 7

ER -