Microsoft Research PhD Scholarship in Machine Learning for Medical Imaging

Employer: Imperial College London
Job location
South Kensington Campus, London
Job salary
Studentship: Untaxed bursary of £17,285 per annum (2020/21 figure including London weighting plus home/EU fees)
Job closing date

This is an ongoing opportunity, however early applications are strongly encouraged.

Applications are invited for a PhD student in Machine Learning for Medical Imaging under the supervision of Dr Ben Glocker (Imperial) and Dr Ozan Oktay (Microsoft).

The PhD research will explore the ambitious and important topic of predicting failure of machine learning models in image-guided clinical decision support which remains an open research challenge. In clinical practice, however, it is of utmost importance to understand when the machine gets it wrong. A better understanding of the limitations of current techniques is essential for building more robust and more reliable tools that can guarantee a safe use of computer-assisted decision making. The project will investigate techniques for quantifying robustness and automated detection of failure cases with the goal to develop new machine learning algorithms for image-based predictive modelling.

The research is at the intersection of artificial intelligence and healthcare and has the potential to make significant positive impact on society by improving patient care through better diagnosis and treatment.

To apply for this position, you will need to have a strong background in at least one of the following areas: machine learning, computer vision, image computing, applied mathematics.

Applicants are expected to have a First Class or Distinction Masters level degree, or equivalent, in a relevant scientific or technical discipline, such as computer science or mathematics. Applicants must be fluent in spoken and written English. The position is fully funded, covering tuition fees, travel funds and a stipend/bursary. The position is available to home and EU students.

More details on how to apply: