Research Themes

Developing novel machine learning and AI techniques for medical imaging pipelines, from acquisition through reconstruction to analysis and interpretation

Modern healthcare professionals must analyse and interpret large amounts of data from a variety of sources such as imaging, clinical records, and other medical or lab examinations. In this context artificial intelligence (AI) has the potential to fundamentally transform the future of medicine and healthcare by enabling earlier, faster and more accurate diagnosis, as well as enhanced screening and stratification to optimal treatment. This will lead to better outcomes for patients as well as improved efficiency in healthcare.

Areas of research include:

• AI for image acquisition, reconstruction and analysis
• AI-enabled decision support for diagnosis and prognosis
• Novel methodologies that address the challenges in translating AI solutions into the clinic

Academic theme leads

Bernhard Kainz

Imperial College London

Emma Robinson

King’s College London

x

Developing and validating more accurate targeted imaging probes for a variety of modalities

Modern imaging probes enable effective use of multiple modalities. However, their production and use present many challenges. Improving existing probes and producing new ones will expand the potential applications of these tools within the clinical environment.

Research foci include:

• Disease-related redox changes
• Molecular imaging supporting emerging therapies
• Drug resistance in cancer
• Biophysical effects of radionuclide therapy
• Radiochemistry platforms for streamlined synthesis of short half-life tracers

Smart imaging probes can be designed for use in both well-established and emerging modalities including:

• SPECT
• PET
• MRI
• Hybrid PET-MR
• Low-dose CT
• Optical and photo-acoustic molecular imaging

Academic theme leads

Michelle Ma

King’s College London

Phil Miller

Imperial College London

x

Disrupting medical imaging with new technologies to improve diagnosis, treatment and prognosis

New ways to revolutionise clinicians’ means to acquire, reconstruct, analyse and interpret medical images are being devised. These include novel imaging technologies; development, validation and consolidation of processes for use of multiple existing modalities; and wider applications of current imaging techniques.

Research focuses on modalities including:

• Multinuclear MRI
• Interventional XMR
• Multi-transmission technology
• Ultra-high field 7T MR
• PET-MR hybrid imaging
• Novel MR, PET and PET-MR acquisition and reconstruction methods

Using existing modalities, research also addresses imaging
approaches to:

• Simultaneous tissue characterisation
• Anato-metabolic assessment

Academic theme leads

Po-Wah So

King’s College London

Radhouene Neji

King’s College London

Pioneering low-cost portable imaging technologies and wearable sensors suited to front-line carers in both the developed and developing worlds

Healthcare providers and purchasers around the world are facing enormous financial pressure. Our solutions help to address aspects such as long-term sustainability of healthcare systems and more equitable access to care.

Affordable imaging challenges and solutions we are looking into include:

• Automated gestational age estimation with low-cost 2D ultrasound screening systems to assess the role that pre-term birth plays in neonatal mortality in the developing world
• Obstetric and other applications of scan guidance systems and automatic report generation
• Empowering non-expert ultrasound users to carry out crucial biometric evaluation
• Detection and characterisation of lesions using super-resolution ultrasound imaging
• Addressing the challenges of obesity in relation to medical imaging
• Simpler, more accessible and cost-effective radiotracer synthesis for molecular imaging by PET, SPECT and molecular radiotherapy

Academic theme leads

Kirsten Christensen-Jeffries

King’s College London

Mengxing Tang

Imperial College London