Research Associate in Generative AI for Total Body Multi-Tracer PET Imaging

About the role

This role is intended to innovate in the area of multi-tracer imaging with positron emission tomography (PET), using kinetic modelling and AI to separate the information for at least 2 tracers so that simultaneous multi-tracer total body PET imaging can be conducted. The emphasis will be on the use of total body PET data with the new Quadra PET scanner.   

This will entail novel developments in a number of areas related to PET imaging and analysis:

• Generation of highly realistic training data examples for dual-tracer PET imaging
• Multiplexed PET data acquisition methodology and image reconstruction for simultaneous imaging of more than one PET radiotracer
• Image analysis and separation of single-tracer images from the multiplexed data acquisition

The particulars of this role will be adaptable within these areas of research, according to the interests and expertise of the candidate. The role can accommodate more focused research as well as broader contributions to the overall remit of advancing imaging physics for total body PET.

The role will also be part of the work of the EPSRC-funded programme for the ‘Next Generation Molecular Imaging and Therapy with Radionuclides’ and also part of a project funded by the Australian Research Council (ARC) through our collaboration with the University of Sydney. As such, in addition to innovating in robust image reconstruction, separation and analysis, the role will entail working with collaborators to ensure reconstructed images can be interpreted in terms of meaningful imaging biomarkers.

The role will be a basis for first- and senior author publications on the development of innovative methodologies in this field as well as co-authoring user-led publications. It is expected that the innovations will necessitate advances in deep learning, generative AI and PET image synthesis and analysis through exploiting the latest advances in deep learning and its integration with kinetic modelling and solving of inverse problems.

The post holder will be supervised by Professor Reader, providing expertise in image reconstruction, deep learning, imaging physics and analysis. 

This is a full time post (35 Hours per week), and you will be offered a fixed term contract until 15 May 2026.

About you

To be successful in this role, we are looking for candidates to have the following skills and experience:

Essential criteria 

• PhD awarded or near completion related to medical imaging/reconstruction/deep learning/image analysis/PET (or closely related subject)* 
• BSc (2:2 or above) in physics, engineering or related subject 
• Presenting scientific research in the form of papers, posters and oral presentations and patents 
• Technical programming experience in Python or similar
• Use of computers/software including database and literature searching
• Proven experience of preparation of academic manuscripts for high impact factor journals 
• Willingness to engage with and learn about clinical aspects of studies and projects 
• Willingness and ability to forge collaborative links with other academic and clinical disciplines 

Desirable criteria

• Postdoctoral experience in medical imaging and preferably radionuclide imaging 
• Knowledge of pharmacokinetics and of standard and state-of-the-art biomedical data/image analysis methods 
• Understanding of AI / deep learning and implementation, and technical programming experience (e.g. PyTorch, TensorFlow) 

Advert information