Automated brain morphometry for sub-millimeter 7T MRI using transfer learning

Gian Franco Piredda, Punith Venkategowda, Piotr Radojewski, Tom Hilbert, Arun Joseph, Gabriele Bonanno, Roland Wiest, Karl Egger, Shan Yang, Jean‐Philippe Thiran, Ricardo Corredor‐Jerez, Bénédicte Maréchal, Tobias KoberProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

Large spatial signal variations due to field inhomogeneities complicate the application of automated brain morphometry at 7T. In this work, we propose to use transfer learning to adapt a template-based segmentation algorithm to sub-millimeter ultra-high field applications. More specifically, a convolutional neural network pre-trained on T 1 -weighted scans to extract the total intracranial volume (TIV) from MP-RAGE acquisitions was re-trained to retrieve the TIV mask directly from MP2RAGE volumes. The developed method proved to reliably deliver brain tissue masks and volumetry at 7T.
BibTeX
@inproceedings{piredda2023automated,
  author = {Gian Franco Piredda and Punith Venkategowda and Piotr Radojewski and Tom Hilbert and Arun Joseph and Gabriele Bonanno and Roland Wiest and Karl Egger and Shan Yang and Jean‐Philippe Thiran and Ricardo Corredor‐Jerez and Bénédicte Maréchal and Tobias Kober},
  title = {{Automated brain morphometry for sub-millimeter 7T MRI using transfer learning}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/2155},
}

Loading related content...

Figure