Active Thyroid-Associated Orbitopathy Detection on Frontal Eye Photographs

Developing a deep learning–based AI system for early monitoring and diagnosis of thyroid eye disease to enable timely treatment before irreversible damage.

2021.08 – 2021.12
Korea Innovation FoundationSystem Monitoring & Anomaly Detection
TEDCASEarly DiagnosisOphthalmology Imaging

Motivation

  • Thyroid eye disease is one of the representative complications of thyroid function.
  • The ophthalmology department determines the presence or absence of certain symptoms that appear in the early active inflammatory period and imposes a Clinical Activity Score (CAS) so that treatment can begin before irreversible changes occur due to thyroid ophthalmopathy.
  • Long-lasting thyroid eye disease can be a cause of great pain associated with Thyroid dysfunction.

Goal

To develop an AI system for early monitoring and diagnosis of thyroid eye disease during the active inflammatory phase, enabling timely treatment before irreversible changes occur.

Methodology

Utilizing the power of Deep Learning, we aims to detect all present diseases from eye images.