Abstract #0194

Deep residual learning of radial under sampling artefacts for real-time MR image guidance during radiotherapy

Bjorn Stemkens^1,2, Cheryl Sital^1,2,3, Max Blokker^1,2,4, Tom Bruijnen¹, Jan JW Lagendijk¹, Rob HN Tijssen¹, and Cornelis AT van den Berg¹

¹Radiotherapy, University Medical Center Utrecht, Utrecht, Netherlands, ²MR Code B.V., Zaltbommel, Netherlands, ³Biomedical Engineering, University of Technology Eindhoven, Eindhoven, Netherlands, ⁴Medical Natural Sciences, VU Amsterdam, Amsterdam, Netherlands

MRI-guided radiotherapy using hybrid MR-Linac systems, requires high spatiotemporal resolution MR images to guide the radiation beam in real time. Here, we investigate the concept of deep residual learning of radial undersampling artifacts to decrease acquisition time and minimize extra reconstruction time by using the fast forward evaluation of the network. Within 8-10 milliseconds most streaking artifacts were removed for undersampling rates between R=4 and R=32 in the abdomen and brain, facilitating real-time tracking for MR-guided radiotherapy.

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

Join Here