3D reconstruction in canonical co-ordinate space from arbitrarily oriented 2D images

File Description SizeFormat 
08295121.pdfPublished version3.92 MBAdobe PDFDownload
Title: 3D reconstruction in canonical co-ordinate space from arbitrarily oriented 2D images
Author(s): Hou, B
Khanal, B
Alansary, A
McDonagh, S
Davidson, A
Rutherford, M
Hajnal, J
Rueckert, D
Glocker, B
Kainz, B
Item Type: Journal Article
Abstract: Limited capture range, and the requirement to provide high quality initialization for optimization-based 2D/3D image registration methods, can significantly degrade the performance of 3D image reconstruction and motion compensation pipelines. Challenging clinical imaging scenarios, which contain significant subject motion such as fetal in-utero imaging, complicate the 3D image and volume reconstruction process. In this paper we present a learning based image registration method capable of predicting 3D rigid transformations of arbitrarily oriented 2D image slices, with respect to a learned canonical atlas co-ordinate system. Only image slice intensity information is used to perform registration and canonical alignment, no spatial transform initialization is required. To find image transformations we utilize a Convolutional Neural Network (CNN) architecture to learn the regression function capable of mapping 2D image slices to a 3D canonical atlas space. We extensively evaluate the effectiveness of our approach quantitatively on simulated Magnetic Resonance Imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline. Our learning based registration achieves an average spatial prediction error of 7 mm on simulated data and produces qualitatively improved reconstructions for heavily moving fetuses with gestational ages of approximately 20 weeks. Our model provides a general and computationally efficient solution to the 2D/3D registration initialization problem and is suitable for real-time scenarios.
Publication Date: 1-Aug-2018
Date of Acceptance: 23-Jan-2018
URI: http://hdl.handle.net/10044/1/56337
DOI: https://dx.doi.org/10.1109/TMI.2018.2798801
ISSN: 0278-0062
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 1737
End Page: 1750
Journal / Book Title: IEEE Transactions on Medical Imaging
Volume: 37
Issue: 8
Sponsor/Funder: Engineering & Physical Science Research Council (E
Wellcome Trust
Engineering and Physical Sciences Research Council (EPSRC)
Engineering & Physical Science Research Council (EPSRC)
Wellcome Trust/EPSRC
Wellcome Trust
Engineering & Physical Science Research Council (E
Nvidia
Funder's Grant Number: RTJ5557761-1
PO :RTJ5557761-1
EP/N024494/1
EP/N024494/1
NS/A000025/1
RTJ5557761
RTJ5557761-1
Nvidia Hardware donation
Copyright Statement: © 2018 The Author(s). This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/.
Keywords: cs.CV
cs.CV
08 Information And Computing Sciences
09 Engineering
Nuclear Medicine & Medical Imaging
Publication Status: Published
Online Publication Date: 2018-02-19
Appears in Collections:Faculty of Engineering
Computing



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons