Research Fellow in AI-enabled Neurology
KCL is co-Leading (jointly with UCL) a long-term Wellcome-funded, 5+ years programme of translational research seeking to transform acute neurology through the application of novel, domain-tailored machine learning.
The Programme for High-Dimensional Neurology, running for 3 years, is creating a comprehensive, large-scale, multi-site, hospital-embedded framework for complex modelling of rich clinical and brain imaging data, and delivering a suite of real-world applications across stroke, neuroradiology, and acute cognitive dysfunction.
Unifying multidisciplinary expertise across KCL (School of Biomedical Engineering & Imaging Sciences; Institute of Psychiatry, Psychology and Neuroscience), and UCL (Queen Square Institute of Neurology), the programme is being deeply integrated with partner hospitals, and aligned with their priority research strategies, including UCLH's flagship Research Hospital Initiative to weave artificial intelligence into the operational and clinical fabric of the hospital.
The programme is supported by globally unique clinical data sources including a curated catalogue >106 annotated MR imaging sessions across neurology, and prospective streams of ~104 richly phenotyped patient admissions annually.
Computation is assisted by the largest hospital-embedded HPC installation in Europe with a joint capacity of >15 petaFLOPS at half precision, allied to the London Medical Imaging & Artificial Intelligence Centre for Value-Based Healthcare centre, and dedicated facilities at UCL.
The programme seeks to pioneer novel, state-of-the-art machine learning methods rendered uniquely feasible by the conjunction of high performance compute with large-scale, comprehensive, fully-inclusive data. Special attention is being be given to enabling large-scale distributed learning while assuring data security through the use of privacy-preserving generative models, and federated learning.
We are building a large team of outstanding researchers with a passion for innovation with rapid, real-world impact, achievable within the life-time of the project. Successful applicants will join what is probably the largest and most ambitious project of its kind, apply their skills to globally unique datasets, and help deliver a flagship programme of translational research with major impact in the field.
The programme represents a superb training opportunity both for those seeking an academic career in translational research and for those intending to move to industry through new spin-outs or established enterprises through the newly formed St Thomas MedTech Hub.
Two new roles are available across the following domains: 1) automated data labelling and curation, 2) natural language processing, and 3) modelling of normal and diversely abnormal multi-modal brain imaging.
The roles will be based at King’s College London (St Thomas Campus). Staff are expected to spend a significant proportion of time at King’s College Hospital (Denmark Hill) working with our clinical collaborators, and will regularly meet with the UCL part of the team. This programme will also collaborate with large industry partners (i.e. NVIDIA, NetApp, SCAN computers and IBM), and with SMEs both local and international.
This post will be offered on a fixed-term contract for 2 years
This is a full-time post
The successful applicant will be responsible for developing and integrating new models and tools for clinical and imaging data analysis and reporting, including modelling of clinical and operational outcomes for acute neurological applications.
The programme will be using infrastructure co-developed as part of the new London Medical Imaging and AI centre for Value Based Healthcare, which is creating a general-purpose open-source AI infrastructure based on technologies such as XNAT, CogStack and ElasticSearch, and MONAI. The applicant is expected to use, work with, and contribute towards these software packages as part of their activities.
The applicant should ideally have some knowledge and experience of:
1. Medical image analysis
2. Machine learning
3. Data science
4. Statistical modelling
The position would appeal to a candidate with strong software development skills, including:
1. Classic machine learning and deep learning packages (SciKitLearn, Tensorflow, pytorch,…)
2. Data science and statistical modelling packages (Pandas, SciPy/Statsmodels)
3. Database querying tools and APIs (REST, MySQL, ElasticSearch/Lucene)
An interest in neurological and neuroradiological applications is important, but previous experience is not essential. Previous experience with large-scale computing services would be useful but not essential.
Strong communication skills are required to work with researchers from other disciplines, such as clinical end-users, and industry collaborators.
The candidate is also expected to:
• work in close collaboration with UCL and IoPPN staff associated with this project
• work towards a common software stack
Experience working with interdisciplinary teams of engineers and clinicians will be valued. A strongly independent applicant is required who will need to work well with inter-disciplinary teams.
The above list of responsibilities may not be exhaustive, and the post holder will be required to undertake such tasks and responsibilities as may reasonably be expected within the scope and grading of the post.
Skills, knowledge, and experience
1. PhD awarded in Mathematics, Engineering or Computer Science
2. Substantial post-doctoral research experience in Medical Image analysis and Deep Learning
3. Higher language computer programming (e.g. Python)
4. General machine learning experience
5. Scientific / Medical Writing
6. Machine learning libraries (SciKit Learn, pytorch,…)
7. Interest in medical imaging
8. Ability to work and develop clinical and industrial relationships
9. Ability to work calmly under pressure and act on initiative
10. Demonstrable experience with research and student supervision collaboration
1. Image segmentation and object detection
2. HPC computing services (SGE-like batch-queuing system, Kubernetes, Docker, Containers)
3. Independent and interdisciplinary researcher