University of Cambridge > Talks.cam > CMIH seminar series > Deformable image registration of abdominal CT images using deep learning: challenges and opportunities

Deformable image registration of abdominal CT images using deep learning: challenges and opportunities

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact J.W.Stevens.

In the past few years, a variety of different methods have been proposed to use deep learning for deformable medical image registration. However, certain challenges need to be overcome before such methods can be readily used in clinical settings. For example, how do these methods deal with small amounts of training data or challenging registrations? Which characteristics of displacement fields are prohibitive when using deep learning? And which image similarity metrics and evaluation methods are most informative when quantifying the performance of such methods? This lecture will demonstrate how such questions may be answered using a longitudinal dataset of abdominal CT images. In addition, a novel training strategy is proposed based on transfer learning and displacement field simulations.

This talk is part of the CMIH seminar series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity