Noble Group

Welcome to the Noble Group website

The Noble Group is led by Professor Alison Noble CBE FRS FREng. Our research interest is in biomedical image analysis, spanning cardiac magnetic resonance image analysis, to fetal ultrasound image analysis, to cell image analysis.

A particular focus for the group has been understanding the interplay of ultrasound device design (physics), clinical acquisition, and downstream image analysis and computer vision. Much of our recent work has concerned machine learning in ultrasound. We are interested in answering questions such as why is ultrasound scanning and interpretation hard to learn? How can we get computers to mimic what a skilled sonographer can do? What is the role of multi-modal analysis (such as eye-tracking and ultrasound video) in ultrasound imaging? And, can ultrasound be simplified (assisted by AI-assistive technologies) so that minimally trained clinical professionals can use it in non-traditional healthcare settings. Our research is motivated by unmet important clinical needs in developed world and developing world settings, and involves inter-disciplinary translational research collaborations with clinical groups from the UK and overseas.

About Us

Our Team

Our Publications

Our Twitter

Projects that we lead

TF HUMAN-MACHINE COLLABORATION - We study how AI can assess human skill in clinical settings, and how AI can enhance and complement human skill, working towards a new generation of AI which takes as input multi-modal video data for shared human-machine decision-making in healthcare imaging.

TF FEDERATED LEARNING – We develop next generation methods for healthcare research collaborations that aim to seamlessly model real-world clinical analysis tasks from decentralised and heterogenous image, video and multi-modal imaging.

COCHE – We develop machine learning-based methods to automate fetal echocardiography sweep video analysis for early detection of congenital heart disease in current and new healthcare settings.

MEDICAL IMAGING AI in LMICs – We develop and validate medical imaging AI methods for current and new LMICs settings in partnership with collaborators in the UK and overseas in India and Africa.

Projects that we partner on

VISUAL AI - We develop novel methods inspired by computer vision advances that aim to be interpretability and are able to input audio-visual data (such as multi-modal ultrasound video) and transform it into usable semantic information to describe clinical tasks.

BRC IMAGING THEME - We develop new biomedical image analysis algorithms and perform sonography data science for first, second and third trimester fetal sonography in a hospital setting.

Past projects

PULSE - We apply the latest ideas from machine learning and computer vision to perform sonography data science and build computational models of ultrasound image analysis and guidance tasks from large scale multi-modal ultrasound, eye tracking, probe movement and audio data.

TraCer (PRECISE) - We develop an easy-to-use point-of-care low-cost ultrasound-based device for fetal gestational age estimation at any point in pregnancy for LMIC settings.

CALOPUS - We combine easy-to-learn ultrasound sweep protocols with novel machine-learning algorithms for pregnancy risk assessment in India healthcare settings.