By developing computational tools, the OMNI Lab aims to address key needs in modern medicine: (i) automated analysis relieves the requirement for highly-skilled radiologists; (ii) discovery of novel markers for diagnostic screening; (iii) software for portable devices, thus broadening access to high-quality care in the developing world; and (iv) investing in sophisticated software while leveraging existing imaging hardware provides a large cost benefit to an already constrained healthcare system.

Over the past few years, there has been rapid progress in our understanding of the developing brain. By leveraging the strengths of deep learning, we aim to continue this progress using ultrasound imaging: the first step in the continuum of pregnancy care, and the modality that is ubiquitous in medical centres around the world.

There are four main areas of research:

1. Developing machine learning models to characterise human fetal brain maturation
2. Reducing computational burden of neural networks through model compression
3. Federated learning techniques for training data-private, multi-site models for large-scale population
4. Understanding fetal neurodevelopment and exploring developmental outcomes in infancy

Technologies and methods

The OMNI Lab is primarily a computational group that uses a wide range of machine learning and image analysis methods to process large-scale population datasets of brain images. A list of tools and resources can be found via our GitHub page.

Joining the OMNI Lab

If you are interested in joining please go to the recruitment page.

Funding

We are grateful for funding from the University of Oxford EPSRC Impact Acceleration scheme, and EPSRC Doctoral Prizes, Bill and Medlinda Gates Foundation, the Academy of Medical Sciences Springboard Awards scheme, and the Royal Academy of Engineering.