Research Associate in Computerized Seizure Analysis from Video

Job description

We are seeking a post-doctoral research associate to develop novel artificial intelligence algorithms to analyse video data obtained as part of routine clinical video-telemetry of patients with epilepsy. Video-telemetry data comprises simultaneous recording of video and EEG data. Clinically, video-telemetry data is reviewed by trained neurologists to infer brain regions involved in epileptic seizure onset and spread. The post holder will develop artificial intelligence algorithms to characterise patient motion during seizure from the video data and use this information to classify seizures into different, clinically relevant, subtypes. Ultimately this research could aid clinicians in identifying brain regions involved in seizure onset for specific subtypes to assist in determining appropriate treatment.   

In this role, the post holder will be responsible for the development of novel artificial intelligence algorithms to assess video data, working closely with Dr. Rachel Sparks, a Lecturer in the Department of Surgical & Interventional Engineering. Candidates should have demonstrable experience in designing or using deep learning algorithms applied to either medical images, natural images, or video data. Candidates are expected to have demonstratable experience with PyTorch, TensorFlow, or an equivalent software package. Familiarity with version control software (git) and experience working within a multi-developer team is desirable. 

This project is part of a close collaboration with experts in epilepsy diagnosis and treatment and King’s College Hospital. As such the successful candidate will be able to work closely with experts in epilepsy to understand the clinical context of the problem and obtain feedback on the methods developed.  

The successful candidate is expected to disseminate their research through presenting at scientific conferences, such as MICCAI or MIDL, publications in peer-reviewed journals, and providing open-source code to the developed methods. Candidates are expected to have a good track record of scientific publications in computer vision or medical imaging journals or equivalent conference publications. Candidates should have strong written and oral presentation skills.  

Candidates will be based in the Department of Surgical and Interventional Engineering (SIE) reporting to Dr. Rachel Sparks, a Lecturer specialising in neurosurgical planning and treatment. SIE has an open, collaborative environment with the potential for close collaborations. The successful candidate will have the ability to collaborate with other researchers, attend regular seminars, and potentially apply their algorithm to other related clinical problems. 

This post will be offered on a fixed-term contract for 18 months 

This is a full-time post

Key responsibilities

•         Develop novel algorithms to quantify patient motion and used this information to classify retrospective video data of patients with epilepsy.  

•         Present key findings at scientific conferences. 

•         Prepare high quality scientific manuscripts for publication. 

•         Liaise with key collaborators at King’s College Hospital providing timely updates on their research progress and lay summaries of the key findings. 

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 

Essential criteria  

1.       PhD in image processing, medical image analysis, computer vision, machine learning or a closely related field* 

2.       Demonstratable skills in designing neural networks or machine learning algorithms for medical images, natural images, or video. 

3.       Good to expert knowledge of PyTorch or Tensorflow, or equivalent software package. 

4.       A track record of first author papers in high quality scientific journals and conferences. 

5.       The ability to work with people from diverse backgrounds.  

6.       The ability to communicate technical concepts to people without technical backgrounds, including medical personnel. 

7.       Experience working on at least one of the following computer vision or medical imaging topics: classification, registration, or motion tracking. 

8.       Excellent written and oral communication skills. 

Desirable criteria

1.       Good knowledge of version control (Git) 

2.       Experience working on a code base with a multi-developer team 

3.       A track record of open source code  

Please note that this is a PhD level role but candidates who have submitted their thesis and are awaiting award of their PhDs will be considered. In these circumstances the appointment will be made at Grade 5, spine point 30 with the title of Research Assistant. Upon confirmation of the award of the PhD, the job title will become Research Associate and the salary will increase to Grade 6.