Research we have funded

Brain tumours are the most common cause of cancer death in children. They are often first diagnosed on an MRI scan. These scans provide information on the tumour location and size, but for precise diagnosis doctors and patients usually rely on pieces of tumour removed by surgery.

It can take up to four weeks to get a final diagnosis, making it hard for doctors to make treatment decisions and causing uncertainty and anxiety for patients and families. We need to improve and accelerate diagnosis for these tumours. This will give clinicians and patients more time and information to make the best decisions for each patient, potentially improving surgical treatment and reducing brain injuries

Modern MRI scans tell us about a tumour’s biology. Through advanced computing (radiomics), it is possible to extract much more information from MRI images than is visible by eye. Combined with artificial intelligence (AI) approaches we can help diagnose tumours when first identified on a scan. For 20 years through the Imaging of Tumours Study, we have collected a world-leading database of MRI images of childhood tumours and have developed AI approaches to diagnose different types of tumour. To be useful for patients, this needs to be delivered in hospitals in real time. Our software tool (MIROR) enables clinicians to analyse new cases and compare with previous cases of known tumour types and offers an AI prediction of tumour type and a confidence score. In this project, we will test how well the tool diagnoses new cases of brain tumours over one year.

In collaboration with the Grace Kelly Childhood Cancer Trust, this project will also further develop and improve the tool, increasing the number and range of tumours the programme uses, improving the AI and MRI algorithms, and linking them with information from biological studies on tumour tissue. This project harnesses AI to improve diagnosis and clinical decision-making leading to improved surgery, reduced side-effects, better and quicker treatment decisions and reduced uncertainty for patients and families.