Covid-19: Oxford University spin-out develops new AI tech platform to analyse Covid-19 x-rays to speed up

ZEGAMI BUILDS NEW TECH PLATFORM TO ANALYSE COVID-19 X-RAYS TO HELP SPEED UP DIAGNOSIS AND POTENTIALLY LEAD TO MORE EFFECTIVE TREATMENTS

·         Platform will help medical professionals predict outcome for patients on different treatments by comparing their x-rays to previous patients with similar conditions

·         Platform could be ready to use by researchers developing Covid-19 diagnostic tools within a matter of weeks

·         Open letter to the NHS requesting images of Covid-19 x-rays to complete the platform

Zegami, the Oxford University data visualisation spin-out, has developed a new machine learning model using x-rays of Covid-19 infected lungs, artificial intelligence techniques and data visualisation tools that could help medical professionals identify Coronavirus cases more effectively, but also potentially help provide a better idea of potential outcomes for patients, and even lead to more effective treatments.

However, to reach its full potential, Zegami needs a huge supply of Covid-19 x-rays and details on treatments used for patients and the outcomes, so it has written an open letter to The Oxford Health NHS Foundation Trust, and the NHS as a whole, asking for these images and data, and offering its services in the fight against Coronavirus.

It believes it would only take a matter of weeks to have enough images of Covid-19 x-rays for its new platform to become usable as a diagnostic tool.

Zegami says its new model could not only help identify and differentiate Covid-19 cases more easily from other lung conditions such as  'bacterial pneumonia' and 'viral pneumonia', it could also help predict potential outcomes for patients by comparing their Covid-19 lung x-rays with other previous patients who had similar conditions, and what eventually happened to them based on different treatment options.

In developing its new platform, Zegami has initially used images of COVID-19 x-rays from the GitHub data initiative, which was launched by Joseph Paul Cohen, a Postdoctoral Fellow from Mila, University of Montreal.  He is looking to develop the world’s largest collection of X-ray and CT images of Covid-19 infected lungs, to enable automated diagnosis faster and more accurately. 

To date, because the images used by Zegami give no details on what happened to the patients, its model can only help distinguish Covid-19 cases more easily from other lung conditions.  

Roger Noble, CEO and founder of Zegami said: “Covid-19 is a huge challenge, and technology should play a key role in defeating it. We believe the model we have developed cannot only be used to help identify cases of Coronavirus more quickly, with the right visuals and information loaded on to our platform and using data visualisation and AI tools, we can help identify potential outcomes for patients by comparing their cases with former patients who had similar conditions and learning what happened to them.

“However, to complete our project we need more data and visuals of Covid-19 x-rays and the treatments used for these case and their eventual outcomes, so we have written to the NHS asking if they would like to work with us on this project, and to see if they can provide the visuals and data we need.

“The model we develop could not only help our amazing NHS staff to make more informed decisions and potentially save lives, it could be shared around the world and play a role in helping to defeat Covid-19 on a global scale.”

Zegami launched out of Oxford University in 2016.  It is currently exploring new ideas and making new discoveries for 35 clients and counting, across an ever-growing variety of sectors.  

About Zegami

Zegami is a data visualisation platform that allows you to easily explore large image datasets and unlock powerful insight by combining advanced analysis tools with a unique visualisation interface. The Zegami platform enables users to rapidly analyse, categorise, label and clean large image datasets, invaluable for many applications including training machine learning. It also creates insightful visualisations from the widest range of structured and unstructured data in business and scientific research.

Zegami and the medical sector

Zegami believes that over the next few years, the medical professional will be one of the biggest adopters of data visualisation tools, and it’s already working on several projects in this sector.  They include:

• A project collaborating with MRC Weatherall Institute for Molecular Medicines (MRC WIMM) Centre for Computational Biology to help clean its data and assist with the training of its machine learning models, specifically around developing a better understanding of which proteins in genes bind, and where they do this in the genome.
• After winning Cancer Research UK’s Early Cancer Detection Sandpit Challenge in 2019, Zegami is currently working with Professor Barbara Braden (Oxford University), Dr Xiohang Gao (Middlesex University) and Dr Wei Pan (Herriot Watt University) on a range of cancer projects.  One such project is linked to oesophageal cancers, most of which are detected by endoscopy when they have reached an advanced stage and treatment is less effective and patient prognosis is poor.

·         Working with Oxford University researchers to help improve its diagnosis of cardiovascular diseases such as coronary heart and aortic diseases. It will do this by applying data visualisation techniques to echo cardiogram images, making it easier to categorise them and identify trends and patterns poor.