Tips on how to manage your PhD stipend FIND OUT MORE
University of Hong Kong Featured PhD Programmes
European Molecular Biology Laboratory (Heidelberg) Featured PhD Programmes

PhD Studentship – AI-based Cardiac Image Computing


School of Electronic Engineering and Computer Science

London United Kingdom Artificial Intelligence Biomedical Engineering Cardiology Computational Mathematics Computer Vision Data Analysis Data Science Machine Learning Software Engineering

About the Project

Applications are invited for a fully-funded PhD Studentship starting in September/October 2021 to undertake research in the area of AI-based cardiac image computing.

The PhD will research interpretable multi-modality AI fusion of cardiac data (images and metadata). Available datasets are often acquired with different modalities in isolation from each other (e.g., intravascular imaging modalities – OCT, IVUS – as well as echocardiographic, MRI, clinical metadata), and resulting AI methods suffer from this siloing. Instead of training two or more deep neural networks in isolation, we will explore new mechanisms to train them simultaneously by coupling their hidden layers. This will enable the learning of a shared representation with higher predictive power. We plan to extend recently proposed tensor and cross-modal attention methods to elucidate best practices in deep, multi-modality fusion. Further, in clinical applications, it is important that AI-based predictions are interpretable and not represent black-box mechanisms. To address this challenge, the PhD may research into invertible deep neural networks and normalizing flows.

The PhD will be part of a “mini-CDT” composed of three PhD students studying different aspects of AI-based cardiac image computing.

Applicants should have, or be expected to obtain by the start date, a 1st class or 2:1 degree (or equivalent) in Computer Science, Mathematics, Engineering, or a related subject. A research publication track record is desired, but not required for the role.

The student will be co-supervised by Prof Greg Slabaugh and Dr Martin Benning. Slabaugh is a Professor of Computer Vision and AI in Electronic Engineering and Computer Science (EECS) at Queen Mary and also Director of the Digital Environment Research Institute (DERI) which brings together researchers from across QMUL faculties to drive new multi-disciplinary research in data science. Benning is a Lecturer in Optimisation and Machine Learning at the School of

Mathematical Sciences; his area of expertise is the theoretical and computational handling of

inverse and ill-posed problems. Queen Mary is a leading research-intensive Russell Group university, ranked 5th among multi-faculty institutions in the UK for research outputs (Research Excellence Framework 2014), and 110th in the world overall (Times Higher Education World University Rankings 2020).

How to apply

Informal enquiries regarding the post may be made by email to Prof Slabaugh ().

Applications should be made by following the online process at https://www.qmul.ac.uk/postgraduate/research/subjects/computer-science.html. (“PhD – Full-time – (Semester 1 -  September Start)”).

The closing date for applications is March 31st 2021. Interviews are expected to take place in the week beginning Monday 15th April 2021. 


Funding Notes

Funding is for three years, covering student fees and, in addition, a tax-free stipend starting at £17,609 per annum. Applications are welcomed from candidates of all nationalities.

References


Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to Queen Mary University of London will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2021
All rights reserved.