3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images

by   Benjamin Hou, et al.

Limited capture range and the requirement to provide high quality initialisation for optimisation-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 initialisation is required. To find image transformations we utilise 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 initialisation problem and is suitable for real-time scenarios.


page 7

page 8

page 9


Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion

This paper aims to solve a fundamental problem in intensity-based 2D/3D ...

Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging

Accurately estimating and correcting the motion artifacts are crucial fo...

PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI

In this paper we present a novel method for the correction of motion art...

Self-Supervised Isotropic Superresolution Fetal Brain MRI

Superresolution T2-weighted fetal-brain magnetic-resonance imaging (FBMR...

Real-time Deep Registration With Geodesic Loss

With an aim to increase the capture range and accelerate the performance...

PCMC-T1: Free-breathing myocardial T1 mapping with Physically-Constrained Motion Correction

T1 mapping is a quantitative magnetic resonance imaging (qMRI) technique...

Please sign up or login with your details

Forgot password? Click here to reset