Approved research

Retinal Vasculature Representation Learning for Computational Biomarker Discovery

Lay summary

Our research aims to develop and validate methodologies to identify and quantify in the vessels structure of the human retina. Such methodology would enable the use of portable fundus cameras, and smartphone adaptors for community-based screening and monitoring by operators with minimal medical training. This will tackle two unmet medical needs: ====== AIM 1 Cardiovascular disease remains the leading cause of mortality among adults aged 65 years or older in the US. Evaluating microvasculature is important, amongst other reasons, for prevention and screening. Invasive tests to assess microvasculature health exist, however, these tests are not readily available for population level screening purposes, especially in point-of-care applications. ====== AIM 2: In neurodegenerative diseases such as Alzheimer or Parkinson's disease, it is estimated that neuronal loss precedes the clinical diagnosis for more than 10 years (prodromal phase) which leads to a subtle decline that cannot be detected with clinical measurements in the current standard of care. This is an urgent unmet medical need. In fact, multiple research groups have independently argued that experimental neuroprotective drugs could significantly slow down or stop the disease progression if administered at the early stages of neuronal damage. Tools to quantify and recognize neurodegeneration in the prodromal phase are an urgent need in clinical trials evaluating disease modifying therapies. ====== Duration: We will split our project in multiple iterations for a total of 30-months. Each iteration will last 6 months. ====== Public health impact: - Facilitating the prompt recognition of cardiovascular disease with a technology scalable to population health. - Creating tools to quantify and recognize neurodegeneration early enough for enabling clinical trials evaluating new disease modifying therapies.