Abstract #0987

Refining synthetic training data improves image quality transfer for ultra-low-field structural brain MRI

Lisa Ronan¹, Sean Deoni², Muriel Bruchhage³, Godwin Ogbole⁴, Matteo Figini⁵, Ikeoluwa Lagunju⁴, Felice D'Arco⁶, Helen Cross⁶, Delmiro Fernandez-Reyes⁵, James Cole⁵, and Daniel Alexander⁵

¹Computer Science, University College London, London, United Kingdom, ²Gates Foundation, Seattle, WA, United States, ³University of Stavanger, Stavanger, Norway, ⁴University of Ibadan, Ibadan, Nigeria, ⁵University College London, London, United Kingdom, ⁶Great Ormand Street Hospital for Children, London, United Kingdom

Synopsis

Keywords: Machine Learning/Artificial Intelligence, Low-Field MRI, super-resolution, Hyperfine

Computer vision methods can be used for image quality transfer (IQT) to address the poor contrast, decreased resolution and increased noise observed in MR images acquired at ultra-low magnetic fields. Current methods have been shown to produce high-quality synthetic outputs for low-field (~0.5T) but not ultra-low-field (~0.05T) field images. Moreover, these methods do not adapt well to the presence of abnormal morphology (e.g. lesions). Here we introduce a new approach to ultra-low field IQT that improves on previous methods and is adaptive to the presence of synthetic lesions.

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.