BIRNet: Brain image registration using dual-supervised fully convolutional networks

Jingfan Fan, Xiaohuan Cao, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Ground-truth guidance using deformation fields obtained by an existing registration method; and (2) Image dissimilarity guidance using the difference between the images after registration. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.

Original languageEnglish
Pages (from-to)193-206
Number of pages14
JournalMedical Image Analysis
Volume54
DOIs
Publication statusPublished - 2019 May 1

Fingerprint

Image registration
Brain
Learning
Efficiency
Experiments
Datasets

Keywords

  • Brain MR image
  • Convolutional neural networks
  • Hierarchical registration
  • Image registration

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

BIRNet : Brain image registration using dual-supervised fully convolutional networks. / Fan, Jingfan; Cao, Xiaohuan; Yap, Pew Thian; Shen, Dinggang.

In: Medical Image Analysis, Vol. 54, 01.05.2019, p. 193-206.

Research output: Contribution to journalArticle

Fan, Jingfan ; Cao, Xiaohuan ; Yap, Pew Thian ; Shen, Dinggang. / BIRNet : Brain image registration using dual-supervised fully convolutional networks. In: Medical Image Analysis. 2019 ; Vol. 54. pp. 193-206.
@article{966fbdb7493c49a2ba9095ea0a2027ca,
title = "BIRNet: Brain image registration using dual-supervised fully convolutional networks",
abstract = "In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Ground-truth guidance using deformation fields obtained by an existing registration method; and (2) Image dissimilarity guidance using the difference between the images after registration. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.",
keywords = "Brain MR image, Convolutional neural networks, Hierarchical registration, Image registration",
author = "Jingfan Fan and Xiaohuan Cao and Yap, {Pew Thian} and Dinggang Shen",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.media.2019.03.006",
language = "English",
volume = "54",
pages = "193--206",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - BIRNet

T2 - Brain image registration using dual-supervised fully convolutional networks

AU - Fan, Jingfan

AU - Cao, Xiaohuan

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2019/5/1

Y1 - 2019/5/1

N2 - In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Ground-truth guidance using deformation fields obtained by an existing registration method; and (2) Image dissimilarity guidance using the difference between the images after registration. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.

AB - In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Ground-truth guidance using deformation fields obtained by an existing registration method; and (2) Image dissimilarity guidance using the difference between the images after registration. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.

KW - Brain MR image

KW - Convolutional neural networks

KW - Hierarchical registration

KW - Image registration

UR - http://www.scopus.com/inward/record.url?scp=85063570767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063570767&partnerID=8YFLogxK

U2 - 10.1016/j.media.2019.03.006

DO - 10.1016/j.media.2019.03.006

M3 - Article

C2 - 30939419

AN - SCOPUS:85063570767

VL - 54

SP - 193

EP - 206

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -