English

Fast Dynamic Perfusion and Angiography Reconstruction using an end-to-end 3D Convolutional Neural Network

Image and Video Processing 2019-09-05 v2 Computer Vision and Pattern Recognition

Abstract

Hadamard time-encoded pseudo-continuous arterial spin labeling (te-pCASL) is a signal-to-noise ratio (SNR)-efficient MRI technique for acquiring dynamic pCASL signals that encodes the temporal information into the labeling according to a Hadamard matrix. In the decoding step, the contribution of each sub-bolus can be isolated resulting in dynamic perfusion scans. When acquiring te-ASL both with and without flow-crushing, the ASL-signal in the arteries can be isolated resulting in 4D-angiographic information. However, obtaining multi-timepoint perfusion and angiographic data requires two acquisitions. In this study, we propose a 3D Dense-Unet convolutional neural network with a multi-level loss function for reconstructing multi-timepoint perfusion and angiographic information from an interleaved 50%50\%-sampled crushed and 50%50\%-sampled non-crushed data, thereby negating the additional scan time. We present a framework to generate dynamic pCASL training and validation data, based on models of the intravascular and extravascular te-pCASL signals. The proposed network achieved SSIM values of 97.3±1.197.3 \pm 1.1 and 96.2±11.196.2 \pm 11.1 respectively for 4D perfusion and angiographic data reconstruction for 313 test data-sets.

Keywords

Cite

@article{arxiv.1908.08947,
  title  = {Fast Dynamic Perfusion and Angiography Reconstruction using an end-to-end 3D Convolutional Neural Network},
  author = {Sahar Yousefi and Lydiane Hirschler and Merlijn van der Plas and Mohamed S. Elmahdy and Hessam Sokooti and Matthias Van Osch and Marius Staring},
  journal= {arXiv preprint arXiv:1908.08947},
  year   = {2019}
}

Comments

11 pages, 4 figures, 1 table, conference paper, accepted in MLMIR2019

R2 v1 2026-06-23T10:55:27.050Z