| Zugriffsnummer | 48564 |
| Dokumenttyp | Konferenzartikel |
| Peer Review | unbekannt |
| Sprache | Englisch |
| Titel | Deep learning-based relative B1+ mapping in the human body at 7T |
| Autor(in); Institution |
Krüger, Felix; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin
Hammerik, K.; Technische Universität München, GERMANY
|
| Quelle/Jahr | Proceedings of the International Society for Magnetic Resonance in Medicine: 30 (2022), 3 S. |
| Artikelnummer | 0683 |
| Availability | [online only] |
| ISSN | 1545-4428 (online) |
| DOI | |
| Konferenzangaben | 31st Joint Annual Meeting ISMRM-ESMRMB & ISMRT, London, 07-12, May, 2022, UK |
| Zusammenfassung | In this work, we estimate relative 2D B1+-maps from initial localizer scans using deep learning at 7T. We investigate 7 UNets and MultiResUNets architectures to estimate complex, channel-wise, relative 2D B1+-maps of 8 transmit channels from a single gradient echo localizer obtained with 32 receive channels. The networks are evaluated in 5 unseen volunteers not included in the training library by comparing the prediction with the acquired relative B1+-maps using different evaluation metrics for homogeneous B1+ phase shimming. Our approach saves additional B1+-mapping scans, and, hence, overcomes long calibration times in the human body at 7T. |
| Themenbereich der Metrologie | Metrologie in der Medizin |