Approved Research

Development and validation of deep-learning approaches for identification of carotid atherosclerotic plaque instability and prediction of stroke risk

Lay summary

Scientific Rationale: Strokes are one of the leading causes of death and disability in the world. Strokes are caused by the build-up of fatty deposits (atherosclerotic plaques) in the neck arteries, which can become dangerous (unstable), break-off, and block blood flow to the brain. The only current method to identify whether a person is at risk of having a stroke is to measure the narrowing of the artery caused by the plaque. However, this method is insufficient and leads to misdiagnosis or inappropriate treatment allocation.

Aims: Herein, we aim to develop a novel method, to be used by researchers and clinicians world-wide, that uses artificial intelligence to improve the characterization and the identification of dangerous plaques on ultrasound imaging. Furthermore, personalized stroke risk scores will be developed that combine ultrasound plaque feature measurements, clinical data, and blood marker measurements.  

Project duration: The duration of the project will be for 3 years.

Public health impact: The development of these novel methods can potentially lead to early detection, and improved management of dangerous plaques. It will improve the clinical diagnosis of patients with stable dangerous plaques (by not only basing decisions solely on artery narrowing but rather on a comprehensive characterization of plaque features and patient clinical data. Ultimately, we could implement better clinical guidelines, prevent strokes, and save many lives!