Meeting Banner
Abstract #2203

In-vivo cardiac diffusion weighted image registration aided by AI semantic segmentation

Pedro F Ferreira1,2, Raquel Martin2, Andrew D Scott1,2, Zohya Khalique1,2, Guang Yang1,2, Sonia Nielles-Vallespin1,2, Dudley Pennell1,2, and David Firmin1,2
1Royal Brompton Hospital, London, United Kingdom, 2Imperial College, London, United Kingdom

In-vivo cardiac diffusion weighted images contain contrast differences that complicate image registration from multiple breath-holds. Additionally, neighbouring structures of the chest wall, liver and stomach do not move rigidly with the heart during the respiratory cycle which further hinders registration. In this work we remove other structures and pre-process the image with the help of a convolutional neural network trained to segment multiple heart structures. These additional steps increase the accuracy of registration of the left ventricular myocardial ring resulting in more accurate diffusion tensors.

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