Layer boundary evolution method for macular OCT layer segmentation.

Area of Science:

• Ophthalmology
• Medical Imaging
• Neurology

Background:

• Optical Coherence Tomography (OCT) provides high-resolution retinal images, essential for ophthalmological assessment.
• OCT is increasingly utilized for evaluating neurological conditions like Multiple Sclerosis (MS).
• Automatic segmentation of retinal layers in OCT scans offers speed and consistency over manual methods.

Purpose of the Study:

• To develop a fast, multi-layer macular OCT segmentation method.
• To improve the accuracy and efficiency of retinal layer segmentation in OCT imaging.

Main Methods:

• A fast level set method is employed for multi-layer macular OCT segmentation.
• The framework utilizes contours optimized for OCT layer segmentation across the macular cube.
• Boundary probability maps from a trained random forest are iteratively refined to subvoxel precision.

Main Results:

• The proposed method demonstrates statistically superior performance compared to a state-of-the-art graph-based method.
• Evaluations were conducted on OCT scans from both healthy subjects and those with Multiple Sclerosis.
• The algorithm achieves accurate segmentation of retinal layers within the macular cube.

Conclusions:

• The developed fast multi-layer macular OCT segmentation method is effective and accurate.
• This technique shows promise for enhancing the diagnosis and monitoring of neurological disorders like MS through OCT analysis.
• The method offers a significant advancement over existing segmentation techniques for OCT imaging.