EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Recovering high‐quality fiber orientation distributions from a reduced number of diffusion‐weighted images using a model‐driven deep learning architecture

Joseph J Bartlett iD, Catherine E Davey iD, Leigh A Johnston iD, Jinming Duan iD

Magnetic Resonance in Medicine · 2024-11 · 92 (5) · 2193-2206

DOI: 10.1002/mrm.30187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 09.06.2024. Verfasst von Joseph J Bartlett und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Melbourne Brain Centre Imaging Unit, Graeme Clark Institute, The University of Melbourne, Parkville, Victoria, …. Hauptthemen laut MEDLINE: Deep Learning, Diffusion Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Brain. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The aim of this study was to develop a model‐based deep learning architecture to accurately reconstruct fiber orientation distributions (FODs) from a reduced number of diffusion‐weighted images (DWIs), facilitating accurate analysis with reduced acquisition times.

Methods

Our proposed architecture, Spherical Deconvolution Network (SDNet), performed FOD reconstruction by mapping 30 DWIs to fully sampled FODs, which have been fit to 288 DWIs. SDNet included DWI‐consistency blocks within the network architecture, and a fixel‐classification penalty within the loss function. SDNet was trained on a subset of the Human Connectome Project, and its performance compared with FOD‐Net, and multishell multitissue constrained spherical deconvolution.

Results

SDNet achieved the strongest results with respect to angular correlation coefficient and sum of squared errors. When the impact of the fixel‐classification penalty was increased, we observed an improvement in performance metrics reliant on segmenting the FODs into the correct number of fixels.

Conclusion

Inclusion of DWI‐consistency blocks improved reconstruction performance, and the fixel‐classification penalty term offered increased control over the angular separation of fixels in the reconstructed FODs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDiffusion Magnetic Resonance ImagingImage Processing, Computer-AssistedBrainConnectomeAlgorithmsHumansDiffusion Tensor Imaging

Stichwörter der Autor:innen

FOD reconstructiondiffusion MRIfixel‐based analysismodel‐based deep learning

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Melbourne Brain Centre Imaging Unit, Graeme Clark Institute, The University of Melbourne, Parkville, Victoria, Australia.
  • School of Computer Science, University of Birmingham, Birmingham, UK.
  • The Alan Turing Institute, London, UK.

ORCID-Profile: Joseph J Bartlett, Catherine E Davey, Leigh A Johnston, Jinming Duan

Zitieren

APA

Bartlett, J. J., Davey, C. E., Johnston, L. A., & Duan, J. (2024). Recovering high‐quality fiber orientation distributions from a reduced number of diffusion‐weighted images using a model‐driven deep learning architecture. Magnetic Resonance in Medicine, 92(5), 2193-2206. https://doi.org/10.1002/mrm.30187

Vancouver

Bartlett JJ, Davey CE, Johnston LA, Duan J. Recovering high‐quality fiber orientation distributions from a reduced number of diffusion‐weighted images using a model‐driven deep learning architecture. Magnetic Resonance in Medicine. 2024;92(5):2193-2206. doi:10.1002/mrm.30187

BibTeX
@article{Bartlett2024,
  author = {Bartlett, Joseph J and Davey, Catherine E and Johnston, Leigh A and Duan, Jinming},
  title = {Recovering high‐quality fiber orientation distributions from a reduced number of diffusion‐weighted images using a model‐driven deep learning architecture},
  journal = {Magnetic Resonance in Medicine},
  year = {2024},
  volume = {92},
  number = {5},
  pages = {2193--2206},
  doi = {10.1002/mrm.30187}
}
Kostenlos starten →