Low-field MRI, operating at magnetic field strength two orders of magnitude lower than commercial clinical scanners, offers excellent potential for bringing cheap, sustainable and effective imaging to regions and countries where MRI is scarce or unavailable. This field of research is rapidly growing and initial clinical usage of these devices, in specific situations, is becoming a reality. However, these low-field systems suffer from a number of technical limitations that prevent widespread adoption, in particular: images have low contrast between different tissue types; poor signal-to-noise ratio; increased geometric distortions; and if unshielded, suffer strongly from interference artefacts. 

This project will address some of these challenges in low-field brain MRI through the development of novel image analysis and machine learning methods. The overall project aim is to produce images and derived measurements that contain robust clinically useful information from low-field MRI. As large low-field datasets are unavailable, this work will focus on working with small “paired” high- and low-field datasets and simulating low-field MRI, from existing large-scale high-field datasets. 

This is a computational project, which would suit a student with good mathematical and programming skills and a keen interest in medical imaging. Students will be expected to present their work at top-tier medical image analysis, computer vision or machine learning venues such as MICCAI, IPMI, CVPR, ICCV/ECCV, MICCAI, NeurIPS etc.  

This project is jointly supervised by Dr Ivor Simpson, a lecturer in the Predictive Analytics Lab within the AI research group at the University of Sussex and Professor Itamar Ronen the academic director of the Clinical Imaging Sciences Centre at Brighton and Sussex Medical School. Both institutions are situated within the fantastic south coast city of Brighton and Hove, adjacent to the beautiful South Downs national park.  

Apply online for a full time PhD in Informatics using our step-by-step guide (http://www.sussex.ac.uk/study/phd/apply). Here you will also find details of our entry requirements. 

Please clearly state on your application form that you are applying for the Towards diagnostic quality low-field brain MRI using machine learning Scholarship, under the supervision of Dr Ivor Simpson. 

Interested candidates may contact Dr Simpson directly prior to applications. All applicants should include a Statement of Academic Interests, explaining their specific interests in the research topic and their relevant skills.