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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.