Faye Bourie

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Henry Dieckhaus

University of North Carolina at Chapel Hill

Thomas Yu

Sage Bionetworks

Jean‐Philippe Thiran

École Polytechnique Fédérale de Lausanne

Govind Nair

National Institute of Neurological Disorders and Stroke

Gian Franco Piredda

Siemens (Switzerland)

Tom Hilbert

Siemens (Switzerland)

Erin Beck

National Institute of Neurological Disorders and Stroke

Francesco La Rosa

Icahn School of Medicine at Mount Sinai

Jonadab dos Santos Silva

Icahn School of Medicine at Mount Sinai

Patrick Liebig

Chinese Academy of Medical Sciences & Peking Union Medical College

Cooperative Institutions

École Polytechnique Fédérale de Lausanne

University of Lausanne

National Institutes of Health

National Institute of Neurological Disorders and Stroke

Siemens (Switzerland)

Centre d'Imagerie BioMedicale

University Hospital of Lausanne

Siemens Healthcare (Germany)

Signal Processing (United States)

International Federation of Sports Medicine

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Self-Supervised Image Reconstruction of 7T MP2RAGE for Multiple Sclerosis: 0.5mm Isotropic Resolution in 10 Minutes

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 (2024)

Thomas Yu Francesco La Rosa Gian Franco Piredda Jonadab dos Santos Silva Faye Bourie

High-resolution 3D MR imaging is necessary for the detailed assessment of focal pathologies, such as cortical lesions. However, high-resolution demands tradeoffs with acceleration and SNR, which is difficult to address with standard machine learning reconstructions due to the infeasibility of collecting large datasets of fully sampled data. Using a dataset of high-resolution (0.5mm isotropic), 3D, 7T MP2RAGE scans of multiple sclerosis patients, we show that a self-supervised reconstruction from one scan, requiring no fully sampled data, has higher apparent SNR than a median of three scans, currently used for assessment, with comparable tissue contrast and lesion conspicuity.

High contrast

10.58530/2023/3115

Cite

Citations (0)