Automatic retinal vessel segmentation based on active contours method in Doppler spectral-domain optical coherence...

Area of Science:

• Ophthalmology
• Medical Imaging
• Biomedical Engineering

Background:

• Retinal vessel segmentation is crucial for diagnosing and monitoring various eye diseases.
• Current segmentation methods can be time-consuming and require manual intervention.
• Spectral-domain optical coherence tomography (SD-OCT) provides high-resolution cross-sectional images of the retina.

Purpose of the Study:

• To develop and validate a fast and automatic method for retinal vessel segmentation.
• To assess the feasibility of real-time retinal vessel segmentation using active contours.
• To evaluate the performance of the proposed method in phantom and in vivo rodent eye images.

Main Methods:

• Employing the active contours method for segmentation in Doppler SD-OCT images.
• Extracting phase variations between adjacent A-lines and removing bulk motion.
• Initializing the contour at the image boundary and iterating until stabilization.

Main Results:

• Achieved fast and automatic retinal vessel segmentation.
• Segmentation completed in under 50 seconds on a standard office computer.
• Demonstrated successful segmentation in both controlled phantom and in vivo rodent eye images.

Conclusions:

• The active contours method offers a rapid and automated solution for retinal vessel segmentation.
• The method's speed enables potential for real-time clinical applications.
• Validated efficacy in diverse imaging scenarios, paving the way for improved ophthalmic diagnostics.