| Zugriffsnummer | 44694 |
| Dokumenttyp | Zeitschriftenartikel |
| Peer Review | mit Peer Review |
| Sprache | Englisch |
| Titel | Neural networks-based regularization for large-scale medical image reconstruction |
| Autor(in); Institution |
Kofler, Andreas; Department of Radiology, Charité - Universitätsmedizin Berlin, Berlin, GERMANY
Haltmeier, M.; Department of Mathematics, University of Innsbruck, Innsbruck, AUSTRIA
Schäffter, Tobias; 8, Medizinphysik und metrologische Informationstechnik, PTB-Berlin
Kachelrieß, M.; Division of X-ray Imaging and CT, German Cancer Research Center, Heidelberg, GERMANY
Dewey, M.; Department of Radiology, Charité - Universitätsmedizin Berlin, Berlin, GERMANY
Wald, C.; Department of Radiology, Charité - Universitätsmedizin Berlin, Berlin, GERMANY
Kolbitsch, Christoph; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin
|
| Quelle/Jahr | Physics in Medicine and Biology: 65 (2020), 13, 19 S. |
| Artikelnummer | 135003 |
| ISSN | 0031-9155 (PRINT) ; 1361-6560 (ONLINE) |
| DOI | |
| Verlag | Bristol: IOP |
| Freie Schlagworte | deep learning ; neural networks ; inverse problems ; low-dose CT ; radial cine MRI |
| Zusammenfassung | In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks (NNs) and cascaded NNs have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the application of the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by strictly separating the application of the NN, the regularization of the solution and the consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained NN which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative NNs. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude. |
| Kostenfreier Zugang | Open Access Hybrid |
| Rechteinformation | CC BY 3.0 ; Creative Commons Attribution 3.0 License |
| Themenbereich der Metrologie | Metrologie in der Medizin |
| Förderinformationen (1) |
Förderername: Deutsche Forschungsgemeinschaft (DFG)
Förderer ID: 0000 0001 2096 9829 Förderer ID Typ: ISNI Förderungsnummer: GRK2260, BIOQIC |
Zitierung
Kofler, A., Haltmeier, M., Schäffter, T., Kachelrieß, M., Dewey, M., Wald, C., & Kolbitsch, C. (2020). Neural networks-based regularization for large-scale medical image reconstruction. Physics in Medicine and Biology, 65(13), 19 S. https://doi.org/10.1088/1361-6560/ab990e