Tiarna Lee speaks to us about her research, working with Science Gallery London, and her journey from being an undergraduate to a PhD Student at the School.
Can you give us some background about your current research?
My research looks at fairness and biases in AI that is used for cardiac imaging. Datasets that are used for training models are often imbalanced in terms of subject demographics and so the resulting AI model has a better performance for the overrepresented group(s) and a worse performance for the underrepresented group(s). I’ve found that a model trained on an imbalanced dataset, for example, with 100% White subjects, will perform poorly for subjects it hasn’t seen, for example, Black subjects. In a medical context, this poorer performance might result in measures like your cardiac function being less accurate, leading to later or worse treatment and worse outcomes overall.
What drew you to doing your research in this area, and what are you looking forward to achieving with your work?
My research investigates these disparities in datasets used to train AI. I’ve always been interested in fairness and bias because it directly affects me, but I became passionate about it following my Master’s when I worked on a deep learning project. I'm looking forward to exploring the causes of bias I’ve identified in my work and ultimately taking steps to mitigate them.
Speaking of your Master’s, we have to ask- you now have nearly three degrees at King’s under your belt. What is it about the university and the School of Biomedical Engineering & Imaging Sciences that encourages you to pursue your academic career here?
I did my Undergraduate and Master’s degree at King’s so I’m becoming a veteran in the department. I’m particularly proud of the public engagement projects I’ve taken part in during my time as a PhD student. I’ve found King’s is a great place to pursue your interests and find a community that’s passionate about the same things. For me, this is fairness, and there are lots of groups that are working on promoting equality inside and outside of academia. I also have a very supportive research group and have formed great friendships and connections!
Recently, you've worked on exhibits and public engagement events on the subject of medical AI. Can you tell us more about this experience and your takeaways from it?
This year, I have presented work at Science Gallery London's AI: Who's Looking After Me? exhibition. One of these projects is Heartificial Intelligence, which examines the role that technology and community play in the healthcare journey of patients. Working with Science Gallery London was a great experience. I found speaking to young people about their heart conditions invaluable, as researchers don’t often have the opportunity to connect with people whom their work directly affects. I have also co-hosted events at the Gallery, which has taught me a lot about the public perception of AI and my work. It was great to be able to create a safe space for people to ask questions they hadn’t been brave enough to ask before!
What does a typical day in your life look like?
I wouldn't say many of my days are very typical! I usually wake up at 7.30am, have some peppermint tea and get ready for the day. When I'm focusing on my project, I spend the day working on my code. At the moment, I’m investigating the source of biases I’ve found in my work on cardiac segmentation models. I’m also a teaching assistant, so I work on a number of other projects.
And finally, we are speaking to you at an exciting time as you’ve joined us from Vancouver. We’d love to know about your work there and what advice you would give to young researchers breaking into academia.
My work has been recognised at the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2023), where I will be presenting my research at the Fairness of AI in Medical Imaging (FAIMI) workshop. I would tell early-career researchers that other researchers are your best friends. Whether it’s help with your project, moral support or inspiration, having a strong support network will help you through your research.
QUICK-FIRE ROUND
Favourite season?
My favourite season is winter. I actually don’t mind the rain!
Favourite TV Show?
I'm a big fan of silly humour and action so I'd say 'The Boys'.
Favourite Scientist?
It's difficult to choose a favourite scientist but one of my favourites is Edward Jenner for creating the first vaccine (smallpox).
Your go-to coffee order?
I'm not a big coffee drinker so my usual order is normally hot chocolate with oat milk!
Find out more about Science Gallery London's AI Season Exhibition and read Tiarna’s paper on biases and fairness in AI training models.