Deep learning for extracting clinically useful information from medical images

Speaker:        Prof Daniel Rueckert
                Head of Department of Computing
                Imperial College London

Title:          "Deep learning for extracting clinically useful
                 information from medical images"

Date:           Friday, 31 August 2018

Time:           11:00 am to 11:45 am

Venue:          Room 3523
                (CSE Department Conference Room; via lift 25-26), HKUST

Abstract:

This talk will introduce framework for reconstructing MR images from
undersampled data using a deep cascade of convolutional neural networks to
accelerate the data acquisition process. We show that such a method can
outperforms state-of-the-art compressed sensing approaches, such as
dictionary learning-based MRI (DLMRI) reconstruction, both in terms of
image quality and reconstruction speed. We will also discuss image
super-resolution approaches that are based on residual CNNs and which can
reconstruct high resolution 3D volumes from 2D image stacks for
more accurate image analysis and visualisation. In addition, we will
present neural networks for medical image segmentation. More specifically,
we will discuss unsupervised domain adaptation using adversarial neural
networks to train a segmentation method which is more invariant to
differences in the input data (across different scanners and acquisition
protocols), and which does not require any annotations on the test domain.
Finally, the talk will ensemble methods for segmentation, (Ensembles of
Multiple Models and Architectures – EMMA) which provide robust performance
through aggregation of predictions from a wide range of methods. EMMA can
be seen as an unbiased, generic deep learning model which is shown to
yield excellent performance, winning the first position in the BRATS 2017
competition among 50+ participating teams.


*********************
Biography:

Daniel Rueckert joined the Department of Computing as a lecturer in 1999
and became senior lecturer in 2003. Since 2005 he is Professor of Visual
Information Processing and heads the Biomedical Image Analysis group. He
received a Diploma in Computer Science (equiv to M.Sc.) from the Technical
University Berlin and a Ph.D. in Computer Science from Imperial College
London. Before moving to Imperial College, he has worked as a
post-doctoral research fellow in the Division of Radiological Sciences and
Medical Engineering, King's College London where he has worked on the
development of non-rigid registration algorithms for the compensation of
tissue motion and deformation. The developed registration techniques have
been successfully used for the non-rigid registration of various
anatomical structures, including in the breast, liver, heart and brain and
are currently commercialized by IXICO, an Imperial College spin-out
company. During his doctoral and post-doctoral research he has published
more than 300 journal and conference articles. Professor Rueckert is an
associate editor of IEEE Transactions on Medical Imaging, a member of the
editorial board of Medical Image Analysis, Image & Vision Computing and a
referee for a number of international medical imaging journals and
conferences. He has served as a member of organising and programme
committees at numerous conferences, e.g. he has been General Co-chair of
MMBIA 2006 and FIMH 2013 as well as Programme Co-Chair of MICCAI 2009,
ISBI 2012 and WBIR 2012. In 2014, he has been elected as a Fellow of the
MICCAI society and in 2015 he was elected as a Fellow of the Royal Academy
of Engineering.