HomeProjectsInformation and Communication TechnologiesAI System for Detecting COVID-19 Infections in CT Images

AI System for Detecting COVID-19 Infections in CT Images

Print IconPrint the page
Using new federated learning techniques, the AI system is trained on multicentre data in Hong Kong without the need to centralise data in one place, thus protecting patient privacy. The established AI system is validated on multiple, unseen, independent external cohorts from mainland China and Europe, showing the potential and feasibility to build large-scale medical datasets with privacy protection, so as to rapidly develop reliable AI models amidst a global disease outbreak such as the COVID-19 pandemic.
Overview of our AI scheme to develop a privacy-preserving CNN-based model for detecting CT abnormalities in COVID-19 patients with a multinational validation study. The privacy-preserving AI system was developed with CT data from three hospitals in Hong Kong using federated learning, and then the generalizability was validated on external cohorts from Mainland China and Germany.

Uniqueness and Competitive Advantages:

  • Can accurately evaluate the CT data in around 40 ms
  • Wide validation and applicability on cohorts with various imaging scanners and different demographics show outstanding robustness and generalisability of the established AI model in complex real-world situations
  • Rapid and accurate detection of COVID-19 infections in CT images
Case studies with longitudinal CT scans relying on dense scoremaps of lesion regions for lesion burden estimation. The raw images are shown accompanied with dense prediction scoremaps, more hot color denotes higher estimation score. The CT images are chronologically ordered from left to right, top to down, in accordance to the scanning date.

Do you like our project?

Contact us

MORE TO EXPLORE

All projects >