| EPSRC Reference: |
EP/Y015665/1 |
| Title: |
Privacy-preserving Artificial Intelligence for Fibrosis Progression Prediction for Patients with Neovascular AMD |
| Principal Investigator: |
Rueckert, Professor D |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computing |
| Organisation: |
Imperial College London |
| Scheme: |
Standard Research - NR1 |
| Starts: |
02 October 2023 |
Ends: |
01 April 2025 |
Value (£): |
381,435
|
| EPSRC Research Topic Classifications: |
| Artificial Intelligence |
Medical Imaging |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
Age related macular degeneration (AMD) is the commonest cause of blindness in the elderly. By 2020, 200 million people are expected to be affected by AMD, increasing to nearly 300 million by 2040. Treatment via injections of Anti-VEGF monoclonal antibodies has had a significant impact on reducing the levels of blindness and restoring part of the visual loss experienced by individuals. However, retinal fibrosis is a pathological process which limits the visual improvement that may be achieved for such a patient. Currently, ophthalmologists assess retinal fibrosis and disease activity manually by clinical examination and review of retinal photographs and optical coherence tomography (OCT) scans. However, there is wide variation between clinicians in their interpretation of the degree of fibrosis present. Treatment decisions are based on assessing fibrosis and the likelihood of response to Anti-VEGF treatment. Thus, making an accurate assessment is crucial. Artificial intelligence (AI) has the potential to automate the accurate characterization and quantification of fibrosis in OCT scans. Moreover, AI has the potential to stratify patients into those who would most benefit from additional therapy with anti-fibrotic agents.
At same time, the development of novel AI techniques is often held back by privacy concerns regarding the sharing of sensitive patient data. This often creates barriers for the effective use of data-driven AI approaches. In this proposal, we aim to address key challenges of privacy-preserving AI approaches, which can help physicians and scientists to leverage patient data across multiple institutions in a trustworthy and secure fashion. We will apply and evaluate our approach in the context of an end-to-end trainable, federated deep-learning approach for the prediction and quantification of fibrosis in patients with AMD.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.imperial.ac.uk |