A real-world AI-based infrastructure for screening and prediction of progression in age-related macular degeneration (AMD) providing accessible shared care
Objectives
- Invent a methodology of AI for retinal image interpretation from longitudinal volumetric OCT scans addressing the challenges of high dimensional data, temporality and data efficient training, as well as model interpretability required to develop trustworthy AI-based predictive models of AMD progression.
- Run large prospective observational studies of natural observation of patients with intermediate AMD (SUDETES) and functional atrophic AMD (APENNINES) addressing the challenge of limited longitudinal data availability and currently limited evaluation of the performance of the developed AI-based predictive models.
- Automated diagnosis of AMD on OCT devices available in community-based eye care professionals’ offices addressing the challenge of transferring the models from the clinical setting to a community-based scenario applicable to AMD patients in their natural environment (PYRENEES).
- Predictive model of AMD disease progression using OCT imaging applicable to different ranges of OCT devices, addressing the challenges of image domain shift, and patient as well as disease heterogeneity, by providing a personalised risk estimator of future AMD progression and therapeutic response.