AI heart shortlisted in nationwide image competition  

24 Oct 2023

Professor Michelle Williams – Associate Director for Imaging at the BHF Data Science Centre – has been shortlisted for the British Heart Foundation’s prestigious ‘Reflections of Research’ image competition. 

Michelle’s image – an Artificial Intelligence (AI)-generated heart – illustrates the complexity of the heart in vibrant colour, but also underlines the shortcomings with today’s AI in generating imagery. 

The competition challenges BHF-funded scientists to put forward the most awe-inspiring image taken as part of their research into cardiovascular health and disease. Each offers a stunning insight into their work. 

‘A Window into the Heart of Artificial Intelligence’ was submitted by Michelle, who is also Personal Chair in Cardiovascular Imaging at the University of Edinburgh, and was created using the AI image generator Dall.e, from the sentence “An image of the heart from a computed tomography scan, digital art”.  

Whilst able to create a stunning image, the AI image includes a few mistakes in the anatomy and structure of this heart, most noticeably in the branching pattern of the blood vessels.  

Part of Michelle’s work is focused on whether healthcare professionals can spot the differences between AI-generated images and real images taken from heart scans. She is also investigating how AI could improve the accuracy and detail of information from heart scans, like the computed tomography (CT) scan imitated in this image.  

She said:

“AI has huge potential to improve the treatment and care of heart and circulatory disease patients, including by enhancing the diagnosis and management of these diseases with heart scanning. However, it is important to remember that, at this stage of development, it can also introduce mistakes and biases. 

“I’m very pleased to make the shortlist for the BHF’s image competition, and for the opportunity to draw attention to these issues.” 

Michelle Williams, BHF Data Science Centre, Associate Director, Imaging

Find out more about Michelle’s exciting work in Imaging.

For more information about Reflections of Research visit Reflections of Research 2022 |BHF .

  • AI
  • Imaging
  • News