Institute Homepage
Institute Homepage DE Sign In

Back

Conference Paper 2018

Learning-based solution to phase error correction in T2\textasteriskcentered-weighted GRE scans

{Long-TE gradient recalled-echo (GRE) scans are prone to phase artifacts due to B0 inhomogeneity. We propose a learning-based approach that does not rely on navigator readouts and allows to infer phase error offsets directly from corrupted data. Our method does not need to be pre-trained on a database of medical images that match a contrast/acquisition protocol of the input image. A sufficient input is a raw multi-coil spectrum of the image that needs to be corrected. We train a convolutional neural network to predict phase offsets for each k-space line of a 2D image. We synthesize training examples online by reconvolving the corrupted spectrum with point spread functions (PSFs) of the coil sensitivity profiles and superimposing artificial phase errors, which we attempt to predict. We evaluate our approach on \textquotedblleftin vivo\textquotedblright data acquired with GRE sequence, and demonstrate an improvement in image quality after phase error correction.}

Author(s): Loktyushin, A and Ehses, P and Schölkopf, B and Scheffler, K
Book Title: International Conference on Medical Imaging with Deep Learning (MIDL 2018)
Pages: 1--3
Year: 2018
Bibtex Type: Conference Paper (inproceedings)
Address: Amsterdam, The Netherlands
Electronic Archiving: grant_archive

BibTex 

@inproceedings{item_2643024,
  title = {{Learning-based solution to phase error correction in T2\textasteriskcentered-weighted GRE scans}},
  booktitle = {{International Conference on Medical Imaging with Deep Learning (MIDL 2018)}},
  abstract = {{Long-TE gradient recalled-echo (GRE) scans are prone to phase artifacts due to B0 inhomogeneity. We propose a learning-based approach that does not rely on navigator readouts and allows to infer phase error offsets directly from corrupted data. Our method does not need to be pre-trained on a database of medical images that match a contrast/acquisition protocol of the input image. A sufficient input is a raw multi-coil spectrum of the image that needs to be corrected. We train a convolutional neural network to predict phase offsets for each k-space line of a 2D image. We synthesize training examples online by reconvolving the corrupted spectrum with point spread functions (PSFs) of the coil sensitivity profiles and superimposing artificial phase errors, which we attempt to predict. We evaluate our approach on \textquotedblleftin vivo\textquotedblright data acquired with GRE sequence, and demonstrate an improvement in image quality after phase error correction.}},
  pages = {1--3},
  address = {Amsterdam, The Netherlands},
  year = {2018},
  slug = {item_2643024},
  author = {Loktyushin, A and Ehses, P and Sch\"olkopf, B and Scheffler, K}
}