Hybrid AI for image interpretation and isotopic identification

Applications are invited for a self-funded, 3 year full-time or 6 year part-time PhD project.

The PhD will be based in the School of Computing and will be supervised by Prof. Adrian Hopgood, Dr Mohamed Bader-El-Den and Dr Vincenzo Tamma.

This project will investigate the complementary use knowledge-based artificial intelligence (AI) and machine learning (ML) for image interpretation and isotopic identification. It will include the use of transfer learning to accelerate the ML training algorithms when moving from one application to another (in the case of imaging), or from one detector type to another (in the case of isotopic identification).

Our project partner, Innovative Physics Ltd (IPL), is specialised in radiation imaging systems. Application areas range from contraband detection for Customs and Excise, through to the nuclear power industry and healthcare. IPL’s technologies can detect the signature γ-ray emissions to identify chemical isotopes present within objects or in inaccessible positions. Recognition is not straightforward, as the spectra contain background noise alongside characteristics of the specific detectors deployed. Although IPL is experienced in the application of machine-learning techniques to recognise these signatures, it wishes to accelerate the learning when switching to adjunct applications and to apply knowledge-based models to apply context, understanding, and interpretation.

IPL also has broader interests in medical imaging (e.g., CT scans and MRI) and biochemical analysis (e.g., recognition of protein structures from x-ray diffraction patterns). It has the capability to generate datasets and has undertaken to make them available to this project. 

Prof Hopgood has led the design and implementation of a software framework that would be suited to the complementary AI techniques for this work, subject to further development within the scope of the project. Known as DARBS (Distributed Algorithmic and Rule-based Blackboard System), it allows a variety of different software tools to work collaboratively as independent intelligent agents.

Fees and funding

Visit the research subject area page for fees and funding information for this project.

Funding availability: Self-funded PhD students only. 

PhD full-time and part-time courses are eligible for the UK Government Doctoral Loan (UK and EU students only).

Bench fees

Some PhD projects may include additional fees – known as bench fees – for equipment and other consumables, and these will be added to your standard tuition fee. Speak to the supervisory team during your interview about any additional fees you may have to pay. Please note, bench fees are not eligible for discounts and are non-refundable.

When applying please quote project code: COMP5411021