The National Cancer Imaging Translational Accelerator (NCITA) Infrastructure is collaborating with University of Cambridge team to support the development of an open-source artificial intelligence (AI) tool called AIX-COV-NET for diagnosis, triaging and treatment planning for COVID-19 patients.
The study, led by Professor Carola-Bibiane Schönlieb and Professor Evis Sala at The Cambridge Centre for Mathematical Imaging in Healthcare (CMIH), aims to develop a flexible, open-source AI tool that could be used by hospitals worldwide to support the rapid diagnosis and triaging of patients with COVID-19.
The study team brings together collaborators with expertise in AI for imaging, radiology and clinical applications from the UK, China, Austria and Italy to develop an AI prediction model that can rapidly and reliably diagnose COVID-19 and predict how patients may progress and recover.
The new AIX-COV-NET tool combines chest imaging data with laboratory and clinical data, and will be accompanied by a comprehensive algorithmic strategy that will allow fine-tuning for datasets with different characteristics and implementation in different countries.
The NCITA Repository Unit will collaborate with the University of Cambridge team to provide repository support for the secure storage and sharing of patient datasets between international research institution sites. The NCITA Repository Unit will also support the assessment of algorithmic methods and deep learning models to optimise the AIX-COV-NET AI-tool.
The University of Cambridge team hope to launch the AIX-COV-NET tool within the next 12 to 18 months. The project is by the EU-funded Innovative Medicines Initiative and Intel.
About the NCITA Repository Unit
The NCITA Repository Unit provides an image repository and data management service for secure storage of imaging biomarker trial data and sharing of anonymised datasets between trials sites in multicentre clinical trials. The repository is based on a comprehensive platform for secure archiving, processing and sharing of research imaging data previously developed by the CRUK Cancer Imaging Centres (CIC) initiative.
If you are interested to find out more about the NCITA Repository Unit support services for clinical research studies, please contact us at email@example.com