Abstract #2387

The repeatability of deep learning-based segmentation of the prostate on T2-weighted MR images

Mohammed R. S. Sunoqrot¹, Sandra Kucharczak², Magdalena Grajek², Kirsten M. Selnæs^1,3, Tone F. Bathen^1,3, and Mattijs Elschot^1,3

¹Department of Circulation and Medical Imaging, NTNU, Norwegian University of Science and Technolog, Trondheim, Norway, ²Department of quantum electronics, Adam Mickiewicz University, Poznań, Poland, ³Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway

Inter- and intra-observer variability are current limitations of radiological reading of multiparametric MR images of the prostate. Deep learning (DL)-based segmentation has proven to provide good performance, but little is known about the repeatability of these methods. In this work, we investigated the intra-patient repeatability of shape features for DL segmentation methods of the prostate on T2-weighted MR images and compared it to manual segmentations. We found that the repeatability of the investigated methods is excellent for most of the investigated shape features.

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.