| Zugriffsnummer | 46098 |
| Dokumenttyp | Konferenzartikel |
| Peer Review | unbekannt |
| Sprache | Englisch |
| Titel | DL2 - deep learning + dictionary leraning-based regularization for accelerated 2D dynamic cardic MR image reconstruction |
| Autor(in); Institution |
Kofler, Andreas; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin
Schäffter, Tobias; 8, Medizinphysik und metrologische Informationstechnik, PTB-Berlin
Kolbitsch, Christoph; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin
|
| Quelle/Jahr | ISMRM 29th annual meeting & exhibition: 15-20 May 2021; virtual conference:(2021), 3 S. |
| Artikelnummer | 1970 |
| Availability | [online only] |
| URL | |
| Verlag | Wiley / ISMRM |
| Konferenzangaben | 29th Annual Meeting of the International Society of Magnetic Resonance in Medicine (ISMRM), Virtual Conference, 15-20 May 2021 |
| Zusammenfassung | In this work, we combine Convolutional Neural Networks (CNN)- with Dictionary Learning (DL)- and Sparse Coding (SC)-based regularization for dynamic cardiac MR image reconstruction. The regularization on the image is imposed by patch-wise sparsity with respect to a learned overcomplete dictionary and closeness to a CNN-based image-prior which is obtained from a pre-trained CNN. We compare the proposed method to two iterative methods which incorporate the di"erent components separately. We demonstrate the combination of CNNs with DL and SC leads to improved image quality and faster convergence compared to DL+SC only. |
| Themenbereich der Metrologie | Metrologie in der Medizin |
Zitierung
Kofler, A., Schäffter, T., & Kolbitsch, C. (2021). DL2 - deep learning + dictionary leraning-based regularization for accelerated 2D dynamic cardic MR image reconstruction. 29th Annual Meeting of the International Society of Magnetic Resonance in Medicine (ISMRM), Virtual Conference, 15-20 May 2021.