16765

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

Amir Alansary, Bernhard Kainz, Martin Rajchl, Maria Murgasova, Mellisa Damodaram, David F.A. Lloyd, Alice Davidson, Steven G. McDonagh, Mary Rutherford, Joseph V. Hajnal, Daniel Rueckert
Biomedical Image Analysis Group, Department of Computing, Imperial College London, UK
arXiv:1611.07289 [cs.CV], (22 Nov 2016)

@article{alansary2016patchtovolume,

   title={PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI},

   author={Alansary, Amir and Kainz, Bernhard and Rajchl, Martin and Murgasova, Maria and Damodaram, Mellisa and Lloyd, David F.A. and Davidson, Alice and McDonagh, Steven G. and Rutherford, Mary and Hajnal, Joseph V. and Rueckert, Daniel},

   year={2016},

   month={nov},

   archivePrefix={"arXiv"},

   primaryClass={cs.CV}

}

In this paper we present a novel method for the correction of motion artifacts that are present in fetal Magnetic Resonance Imaging (MRI) scans of the whole uterus. Contrary to current slice-to-volume registration (SVR) methods, requiring an inflexible anatomical enclosure of a single investigated organ, the proposed patch-to-volume reconstruction (PVR) approach is able to reconstruct a large field of view of non-rigidly deforming structures. It relaxes rigid motion assumptions by introducing a specific amount of redundant information that is exploited with parallelized patch-wise optimization, super-resolution, and automatic outlier rejection. We further describe and provide an efficient parallel implementation of PVR allowing its execution within reasonable time on commercially available graphics processing units (GPU), enabling its use in the clinical practice. We evaluate PVR’s computational overhead compared to standard methods and observe improved reconstruction accuracy in presence of affine motion artifacts of approximately 30% compared to conventional SVR in synthetic experiments. Furthermore, we have evaluated our method qualitatively and quantitatively on real fetal MRI data subject to maternal breathing and sudden fetal movements. We evaluate peak-signal-to-noise ratio (PSNR), structural similarity index (SSIM), and cross correlation (CC) with respect to the originally acquired data and provide a method for visual inspection of reconstruction uncertainty. With these experiments we demonstrate successful application of PVR motion compensation to the whole uterus, the human fetus, and the human placenta.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: