Abstract #0931

Deep learning based segmentation of aortic cross sections (2D+t) in multi-vendor 4D PCMRI

Chiara Manini¹, Markus Hüllebrand^1,2, Marius Pullig³, Titus Kühne^1,4, Sarah Nordmeyer⁵, Lina Jarmatz⁵, Andreas Harloff⁶, Jeanette Schulz-Menger^4,5, and Anja Hennemuth^1,2,4,7

¹Institute of Computer-assisted Cardiovascular Medicine, Charité – Universitätsmedizin Berlin, Berlin, Germany, ²Fraunhofer MEVIS, Bremen, Germany, ³IBM Germany, Berlin, Germany, ⁴DZHK (German Center for Cardiovascular Research), Partner site Berlin, Germany, ⁵Charité – Universitätsmedizin Berlin, Berlin, Germany, ⁶University Hospital Freiburg, Freiburg, Germany, ⁷University Medical Center Hamburg-Eppendorf, Hamburg, Germany

Synopsis

Keywords: Flow, Velocity & Flow, Aorta segmentationStandardized 4D PCMRI postprocessing protocols could enable comparable bloodflow quantification. We propose an automatic segmentation of aortic cross section over time with a residual trained data from different imaging sequences, scanner types, pathologies and position of cross section planes. Dice score, Hausdorff metric as well as flow and velocity curves for the segmented areas show good performance both in the validation and test sets.

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.