DTA3 MSCA Research Fellow - Fully automated quantification of myocardial infarct size using artificial intelligence methods
A fully-funded PhD opportunity has arisen for a highly motivated individual. The area of the project is Deep Learning on Cardiovascular MRI. This is an exciting project that also involves an attractive remuneration package.
Project title: Fully automated quantification of myocardial infarct size using artificial intelligence methods.
Project Description: Myocardial infarction (MI) (a.k.a. heart attack) occurs when the supply of blood to the heart muscle is suddenly blocked. In 2013/14 over 80,000 patients were admitted to hospital with an acute MI in England and Wales.
Cardiovascular Magnetic Resonance (CMR) can detect and quantify myocardial infarction with unique precision using the late gadolinium enhancement (LGE) technique. This can provide prognostic information independently of ejection fraction. However, CMR is currently dependent on the limited availability of qualified experts, subjective assessment and is too time-consuming for clinical practice. Semi-automated methods (such as Full-Width Half-Maximum, N-standard deviations, etc.) also rely on the subjective determination of endocardial/epicardial borders. On top of this, the above classifiers also fail to generalize to datasets acquired by different labs due to acquisition-related variation (imaging protocols, field strength, vendor etc.). The presence of artefacts is another challenge for this type of algorithms.
Deep learning (DL) is a rapidly growing trend in general data analysis that currently drives the artificial intelligence (AI) boom. Deep convolutional neural networks (CNNs) are DL architectures and related algorithms which are well-suited for image analysis tasks.
The project will use DL to develop tools to enable fast, accurate, automatic 3D model generation of myocardial scar data. An excellent annotated dataset from 1,958 research patients who have had CMR following MI will be used. The datasets for this project were obtained at 7 leading CMR centres in UK. The tools developed in this project will allow multi-centre comparisons, which in turn, will facilitate the establishment of novel CMR-based biomarkers (infarct size) as predictors of hard clinical points. The proposed algorithms will also allow high-risk sub-groups to be identified for future interventional studies.
The research will be driven by the following hypotheses:
• CNNs will replicate a cardiac MRI expert manual labelling of myocardial scar tissue in cardiac MRI datasets of MI patients, but be faster and more robust.
• AI-based techniques of scar quantification will be more strongly associated with clinical outcomes, compared with the standardised semi-automated techniques.
• Deep learning can be used to learn CMR acquisition-invariant representations, so that a (scar tissue) classifier, that has been trained on data from a specific scanner vendor/field strength/protocol, can be applied to data that was differently acquired.
• Deep learning architectures can be trained to recognise artefacts in the remote myocardium.
Host Institution The PhD project will be hosted by School of Science and Technology at Nottingham Trent University (NTU), UK. Data Science at School of Science and Technology, NTU is equipped with powerful hardware for achieving incredible performance in deep learning problems. The world-class research community at NTU tackles society’s biggest challenges with research that is transforming the world and saving lives. Research at NTU won the 2015 Queens Anniversary Prize –the highest honour for a UK university– and 90% of NTU’s research was classed as world-leading, internationally excellent or internationally recognised in the 2014 Research Excellence Framework. The British Heart Foundation Cardiovascular Research Centre at Leicester is a project partner. The newly-established Leicester centre houses state-of-the-art facilities that enable pioneering research on cardiovascular diseases to continue apace. The UK in uniquely placed to address many of the unanswered questions regarding MI.
Applications Entrants must have a Bachelors Honours degree with an Upper Second or First Class grade in Data Science, Applied Mathematics, Computer Science, Mathematics, Electrical Engineering, or Biomedical Engineering. Entrants with a Lower Second Class grade in their Bachelors Honours degree must also have a postgraduate Masters Degree at Merit or above. Experience with Deep Learning frameworks and Python programming language is desirable and would be considered as an advantage. You will need an overall IELTS (International English Language Testing System) score of 6.5 with minimum sub-scores of 6.0 in all component sections (writing, reading, listening and speaking).
Applicants must apply using the online form on the University Alliance website at https://unialliance.ac.uk/dta/cofund/how-to-apply/
Guidance to complete the application form, eligibility requirements (Please note the EU mobility rule: Candidates must not have been resident in the UK for more than 12 months in the three years immediately prior to the call deadline), and a Frequent Asked Questions guide can be found at the above link. The final deadline for applications is the 14th October 2019, 23:59 BST. The PhD student will start in early April 2020.
Contact details: For informal applicant queries regarding the project please send an email to [Email Address Removed]
The successful applicant will be employed for 36 months with a minimum salary of £22,300 per annum. On top of this, tuition fees will be waived for the DTA3/COFUND fellow who will also be able to access an annual DTA elective bursary to enable attendance at DTA training events and interact with colleagues across the Doctoral Training Alliance(s). Other research costs will also be supported. This project has received funding from the European Union research and innovation programme Horizon 2020 under the Marie Skłodowska-Curie grant agreement No 801604.
How good is research at Nottingham Trent University in General Engineering?
FTE Category A staff submitted: 14.40
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities