Meeting Banner
Abstract #5124

A Data Augmentation Framework to Improve R-peak Detection in ECG Recorded in MRI Scanners

Maroua Mehri1,2, Pierre Aublin3, Guillaume Calmon1, Freddy Odille1,3,4, and Julien Oster3,4
1Epsidy, Nancy, France, 2University of Sousse, National School of Engineers, LATIS-Laboratory of Advanced Technology and Intelligent Systems, Sousse, Tunisia, 3IADI, INSERM U1254 and Université de Lorraine, Nancy, France, 4CIC-IT 1433, INSERM, Université de Lorraine and CHRU Nancy, Nancy, France

Synopsis

Keywords: Heart, Data Analysis, Machine learning/Artificial intelligenceDetecting R-peaks in ECG using deep learning (DL) requires large, annotated datasets. Such datasets with the MRI-specific magneto-hydrodynamic (MHD) effect, do not exist currently. We propose a robust data augmentation framework using records available online, adding realistic MHD artifacts to augment the training dataset. MHD artifacts were modelled from eight 3T MRI-ECG records, and added to 75 non-MRI-ECG records. The R-peak detection was evaluated on six 3T MRI-ECG records. Compared to a DL model trained without data augmentation, the number of false positives and missed detections were reduced by 57.6% and 16.4%, the overall error was decreased by 25%.

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.

Keywords