Fiche publication
Date publication
décembre 2025
Journal
Medical physics
Auteurs
Membres identifiés du Cancéropôle Est :
Dr VUISSOZ Pierre-André
Tous les auteurs :
Quillien L, Oster J, Vuissoz PA
Lien Pubmed
Résumé
Accelerated MRI reconstruction techniques are necessary to avoid long cardiac exams. K-space-based parallel imaging (PI) reconstruction has recently been adapted to deep learning with a scan-specific training technique entitled scan-specific robust artificial neural-networks for k-space interpolation (RAKI), which incorporates nonlinearity by applying convolutional neural networks. While the scan-specific aspect alleviates the need for a large training database, as it consists of a single-shot training, it consequently increases the overall reconstruction time.
Mots clés
cardiac 2D cine, deep‐learning MRI reconstruction, parallel imaging
Référence
Med Phys. 2025 12;52(12):e70145
