Clinical imaging data is essential to the development of new research software which contributes to assisted diagnosis, treatment planning and image-guided surgery. However, it is limited by the difficulty in performing fast and secure data transfer between healthcare and academia due to complex IT infrastructures and strict patient confidentiality rules.
Dr Tom Doel (UCL Medical Physics & Biomedical Engineering), lead author on this work, said: “Patients frequently want to share their imaging data to help medical research, but transferring these images from the hospital to the researcher is surprisingly burdensome. With GIFT-Cloud we have simplified the data sharing process, which will allow our researchers to work with a greater and richer range of imaging data. This develops our understanding of disease and enables us to create new and better algorithms to inform doctors when planning treatments.”
GIFT-Cloud is a system which tackles many of the data access problems faced by imaging researchers. Key benefits of the system include the ability to easily integrate with the IT systems of hospitals and universities, to support varied collaboration agreements and for the data sharing process to fit easily within routine clinical workflow. This reduces the time burden on clinicians and makes it easier for researchers to access a wider range of imaging data, vital for developing innovative and robust code.
More advanced functions include a new way of anonymising information automatically which clears patient data from both the file metadata and pixel data whilst still allowing for longitudinal studies and the ability to store and share software test results for quick feedback.
GIFT-Cloud was developed to tackle the data transfer burden on researchers and clinicians collaborating on GIFT-Surg. The team needed a fast and secure method of sharing and collaborating on imaging data between UCL, KU Leuven, UCLH, Great Ormond Street Hospital and UZ Leuven. The software is publicly available on GitHub.
GIFT-Surg is a 7-year research project funded by Wellcome and EPSRC under the ‘Innovative Engineering for Health’ initiative and supported by the University College London Hospitals Biomedical Research Centre.