Meeting Banner
Abstract #4249

Neural network based denoising of high temporal resolution cine images for tumor tracking in MR-guided radiotherapy

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

MR-linac systems allow for real-time tumor position updates. Higher temporal resolution imaging through k-space undersampling allows for an increased number of position updates, however iterative reconstructions may negate the decrease in acquisition time and undersampling artifacts may impact tracking stability.

In this study a fast method to denoise and suppress image artifact using a U-net is presented. Undersampled Cartesian and radial cine images were acquired from a patient with a liver tumor on an MR-linac. Tumor tracking stability was assessed. Denoising was found to improve tracking stability and has potential in high temporal resolution cine imaging on MR-linac systems.

This abstract and the presentation materials are available to members only; a login is required.

Join Here