A Deep Learning Approach Utilizing Covariance Matrix Analysis for the ISBI Edited MRS Reconstruction Challenge

Julian P. Merkofer; Dennis M. J. van de Sande; Sina Amirrajab; Gerhard S. Drenthen; Mitko Veta; Jacobus F. A. Jansen; Marcel Breeuwer; Ruud J. G. van Sloun

A Deep Learning Approach Utilizing Covariance Matrix Analysis for the ISBI Edited MRS Reconstruction Challenge

Medical Physics 2023-06-06 v1 Machine Learning Image and Video Processing

Authors: Julian P. Merkofer , Dennis M. J. van de Sande , Sina Amirrajab , Gerhard S. Drenthen , Mitko Veta , Jacobus F. A. Jansen , Marcel Breeuwer , Ruud J. G. van Sloun

View on arXiv ↗ PDF ↗

Abstract

This work proposes a method to accelerate the acquisition of high-quality edited magnetic resonance spectroscopy (MRS) scans using machine learning models taking the sample covariance matrix as input. The method is invariant to the number of transients and robust to noisy input data for both synthetic as well as in-vivo scenarios.

Keywords

magnetic resonance spectroscopy covariance matrix deep learning image reconstruction accelerated acquisition noise robustness

Cite

@article{arxiv.2306.02984,
  title  = {A Deep Learning Approach Utilizing Covariance Matrix Analysis for the ISBI Edited MRS Reconstruction Challenge},
  author = {Julian P. Merkofer and Dennis M. J. van de Sande and Sina Amirrajab and Gerhard S. Drenthen and Mitko Veta and Jacobus F. A. Jansen and Marcel Breeuwer and Ruud J. G. van Sloun},
  journal= {arXiv preprint arXiv:2306.02984},
  year   = {2023}
}

A Deep Learning Approach Utilizing Covariance Matrix Analysis for the ISBI Edited MRS Reconstruction Challenge

Abstract

Keywords

Cite

Related papers