Abstract #5275

Using Convolutional Neural Networks to detect and remove out-of-voxel MRS artefacts

Aaron T Gudmundson^1,2, Kathleen E Hupfeld^2,3, Yulu Song^2,4, Helge J Zöllner^1,2, Christopher W. Davies- Jenkins^1,2, İpek Özdemir^1,2, Georg Oeltzschner^2,3, and Richard A E Edden^1,2

¹The Russell H. Morgan Department of Radiology and Radiological Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, United States, ²F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD, United States, ³The Russell H. Morgan Department of Radiology and Radiological SciencesRadiology and Radiological Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, United States, ⁴The Russell H. Morgan Department of Radiology and Radiological Sciences Radiology and Radiological Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, United States

Synopsis

Keywords: Machine Learning/Artificial Intelligence, Spectroscopy, Out-of-voxel (OOV), MRS, Artefacts, Deep Learning, Convolutional Neural NetworkOut-of-voxel (OOV) artefacts, or echoes, are common in-vivo artefacts seen in MRS data. These artefacts are typically not identified until post-processing and are challenging to remove without modifying the underlying data. Here, we developed 2 Convolutional Neural Networks (CNNs) to overcome OOV artefacts at different stages. The first network (CNN1) was designed to identify OOV artefacts in single average data and offer a real-time assessment during data acquisition. The second (CNN2) predicts the OOV artefact to subtract during post-processing without impacting the metabolite 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.