User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Fast multi-compartment microstructure fingerprinting using deep neural networks

Primary tabs

download
  • Open access
  • PDF
  • 3.76 M
Dessain, Quentin [UCL] Delinte, Nicolas [UCL] Macq, Benoît [UCL] Rensonnet, Gaëtan [UCL]

We estimate microstructural features of crossing fascicles in the white matter by using a fast multi-compartment fingerprinting, an extension of MR fingerprinting to diffusion MRI. The acceleration uses efficient sparse optimization and a dedicated feed-forward neural network to circumvent the inherent combinatorial complexity of the fingerprinting estimation. The accuracy of the results and the speedup factors obtained on in vivo brain data suggest the potential of our method for a fast quantitative estimation of microstructural features in complex white matter configurations.

Document type Communication à un colloque (Conference Paper) – Poster
Access type Accès libre
Publication date 2022
Language Anglais
Conference "30th Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM)", London, United Kingdom (du 07/05/2022 au 12/05/2022)
Affiliation UCL - SST/ICTM/ELEN - Pôle en ingénierie électrique
Keywords diffusion MRI ; dMRI ; Microstructure Fingerprinting ; brain
Links
Bibliographic reference Dessain, Quentin ; Delinte, Nicolas ; Macq, Benoît ; Rensonnet, Gaëtan. Fast multi-compartment microstructure fingerprinting using deep neural networks.30th Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM) (London, United Kingdom, du 07/05/2022 au 12/05/2022).
Permanent URL http://hdl.handle.net/2078.1/260761