LATEST UPDATES
The latest research, publications, talks and activities from TESFA Lab.
OUR RESEARCH
Explore our latest work in trustworthy AI, medical image analysis, fairness, robustness and uncertainty.
August 2026
Victoria reviews the state-of-the-art and future directions in methods for predicting toxicity in radiation therapy.
PredictionJuly 2026
Iman Islam investigates loss functions for training echocardiography segmentation models on datasets from different sources with incomplete annotations.
Robust AIApril 2026
This work investigates how changes in correlations between image features and labels can lead to incorrect semantic predictions, even when a model identifies the relevant image regions.
Shortcut LearningApril 2026
This study explores methods to identify annotation errors and improve training data for deep learning-based echocardiography segmentation.
SegmentationMarch 2026
This work examines how uncertainty estimation and scan–rescan data can reveal limitations in the precision of AI-derived cardiac MRI biomarkers.
UncertaintyJanuary 2026
This study investigates whether visual explanations of AI predictions help clinicians diagnose myocardial infarction from echocardiogram videos.
Explainable AIDecember 2025
This work investigates strategies to mitigate ethnicity-related performance differences in cardiac MRI segmentation, including approaches informed by the underlying causes of bias.
Fairness & BiasBrowse more work on the Publications page.
PEOPLE, PROJECTS & EVENTS
News, media coverage, talks and activities from the group.
September 2026
Andrew King delivered a keynote at the ECCV workshop on Fairness and Ethics towards Transparent AI: Facing the Challenge through Model Debiasing (FAILED).
Talks & Events
June 2026
Andrew King writes a King's Health Partners blog on research into bias in healthcare AI and how its benefits can be shared more equitably.
Research Impact
June 2026
Andrew King joins Leo Celi and Mena Ramos to discuss AI in healthcare and how it can be made more human.
Podcast
February 2026
King's College London highlights research by Tiarna Lee investigating how to reduce racial bias in AI-based cardiac MRI segmentation.
Press Coverage
August 2025
The group is a partner in the EU-funded SkincAIr project, working with African partners to develop fair and robust AI for detecting skin-related neglected tropical diseases.
Research Projects
March 2025
Read about the group's research investigating the causes of racial bias in AI-based cardiac MRI analysis.
Press Coverage
March 2025
A video featuring Maram Alqarni's scholarship journey as a biomedical engineering PhD student.
PeopleExplore our research or get in touch with the group.
Contact the group →