Florian Friedrich1,2, Juliane Hörner-Rieber3, Peter Bachert1,2, Mark E. Ladd1,2,4, and Benjamin R. Knowles1
1Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany, 2Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany, 3Department of Radiation Oncology, University Hospital of Heidelberg, Heidelberg, Germany, 4Faculty of Medicine, Heidelberg University, Heidelberg, Germany
1Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany, 2Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany, 3Department of Radiation Oncology, University Hospital of Heidelberg, Heidelberg, Germany, 4Faculty of Medicine, Heidelberg University, Heidelberg, Germany
Image denoising and artifact suppression using U-net
increases tumor tracking stability in undersampled Cartesian and radial cine
acquisitions on MR-linac systems.
Figure 2: Denoising of undersampled Cartesian images of a
liver tumor (arrow).
Figure 3: Denoising of undersampled radial images of a liver
tumor (arrow).
