Abstract #4993

Assessing the Role of Deep Learning in Joint Motion and Image Estimation

Brian Nghiem^1,2, Zhe Wu¹, Melissa Haskell³, Lars Kasper¹, and Kamil Uludag^1,2

¹BRAIN-To Lab, University Health Network, Toronto, ON, Canada, ²Medical Biophysics, University of Toronto, Toronto, ON, Canada, ³Electrical Engineering and Computer Science, University of Michigan, Ann Arbour, MI, United States

Synopsis

We investigated the performance of CNN-assisted joint estimation in two cases of severe motion corruption in a 2D slice of T2w FSE MRI. We showed that the inclusion of the CNN can help speed up convergence of the joint estimation algorithm, corroborating previous findings. We also showed one case in which joint estimation failed to converge to the correct image and motion parameters, with and without the CNN. A more exhaustive study is required to confirm whether deep learning can help joint estimation salvage otherwise unsalvageable corrupted data.

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.