Tracking Eyelid Movement in Cogan's Lid Twitch Syndrome.

Area of Science:

• Ophthalmology
• Neurology
• Medical Imaging Analysis

Background:

• Ocular myasthenia gravis (OMG) diagnosis is challenging, often relying on subjective clinical signs like Cogan's lid twitch (CLT).
• Current diagnostic methods for CLT lack objectivity, leading to interobserver variability and delayed diagnosis.
• Objective diagnostic tools are needed to improve the accuracy and timeliness of OMG diagnosis.

Purpose of the Study:

• To investigate the potential of video-based eyelid tracking for the simplified diagnosis of Cogan's lid twitch (CLT).
• To explore a non-invasive method for enhancing the diagnostic accuracy of ocular myasthenia gravis (OMG).

Main Methods:

• Pilot study analyzing video recordings of CLT using pixel value changes and eyelid position.
• Video preprocessing techniques were applied for footage stabilization and artifact reduction.
• Eyelid tracking was performed using contour detection and polynomial fitting algorithms.

Main Results:

• Detectable variations in eyelid position during CLT events were observed.
• The accuracy of eyelid tracking for CLT detection was inconsistent.
• Challenges included differentiating subtle CLT movements from blinks and handling anatomical variations like double eyelids.

Conclusions:

• Video-based eyelid tracking shows potential as a non-invasive tool for OMG diagnosis.
• Further refinement of the tracking methodology is necessary for improved accuracy.
• This approach could significantly enhance the early diagnosis and management of OMG patients.