Research news

An iceberg in the middle of the ocean

Keeping an AI on the icebergs

A team led by Leeds scientists has trained an Artificial Intelligence system to accurately map in onehundredth of a second the surface area and outline of giant icebergs captured on satellite images.

Monitoring icebergs is critical for both maritime safety and scientific study of the polar environment. They can be extremely large – in some cases the size of small countries – and can pose a risk to passing ships. As they melt, icebergs release nutrients and freshwater, impacting marine ecosystems.

Human interpretation of satellite imagery can take several minutes to delineate the outline of a single iceberg – and if that has to be repeated numerous times, the process quickly becomes time-consuming and laborious. The new AI technique, led by scientists at Leeds’s Centre for Polar Observation and Monitoring is a major advance on existing automated systems which struggle to distinguish icebergs from other features in the image.

Improving cancer outcomes

A personalised treatment for the most common form of adult leukaemia helps patients survive longer, Leeds research shows. The trial was identified as “groundbreaking” by the American Society of Hematology after its results were presented at the Society’s annual conference.

Patients with chronic lymphocytic leukaemia were given a combination of cancer growth blocking drugs over varied durations depending on how rapidly their disease responded, with their progress being checked with regular blood tests. This approach significantly improved outcomes compared to standard treatments, with more than 95 per cent of patients in remission three years after joining the trial.

Lead author and Professor of Experimental Haematology Peter Hillmen described the findings as “exceptional”, adding “patients on our trial had better outcomes while also enjoying a better quality of life. Most patients treated with the new combination have no detectable leukaemia in their blood or bone marrow by the end of treatment.”

Tackling child tooth decay

A quarter of five-year-olds in England have tooth decay, a figure which rises to half in deprived areas. The burden of tooth decay is significant, causing pain and affecting what children eat, their speech, sleep, quality of life and attendance at nursery or school.

A new toolkit co-created by University of Leeds researchers aims to address these health inequalities and encourage supervised toothbrushing for younger children. Its free resources are available to parents, nurseries, schools, NHS organisations and local government.

Five children stand in a line brushing their teeth

Predicting heart failure

Artificial intelligence could improve the early diagnosis of heart failure. Heart failure happens when the heart cannot pump blood effectively around the body and affects more than one million people in the UK. Around half die within five years of diagnosis.

Researchers led by Professor of Cardiovascular Medicine Chris Gale used machine learning to find telltale patterns in an individual’s health records and predict those at greatest risk. “Data collected in people’s interactions with healthcare is a powerful resource and it’s time to use this to benefit patients,” he says. “This algorithm could bring diagnoses forward, opening a window of opportunity for treatment.”

Drinking in history

Three cans of beer on a table

Leeds historian Dr Samuel Gartland has collaborated with local brewery Northern Monk to create a beer inspired by a 5,000-year-old recipe, featuring the traditional ingredients of meadowsweet, spelt and honey. Though given modern-day styling as a double dry hopped India Pale Ale, Mhór celebrates the fact that beers have been drunk in Britain since ancient times.

Creeping robots to fight cancer

A robot with magnetic skin, whose movement mimics creeping vine plants, could transform cancer diagnosis and treatment.

A team led by Leeds developed the soft, slender robots which can squeeze through narrow complex pathways deep inside the human body, such as in the lungs. It could pave the way for a revolution in the field, leading to advanced less invasive surgical tools that can be precisely steered through intricate and sensitive areas of the body to aid diagnosis, perform biopsies and deliver treatments.