Automated segmentation of the macula by optical coherence tomography

Area of Science:

• Ophthalmology
• Biomedical Imaging
• Medical Image Analysis

Background:

• Accurate segmentation of retinal layers is crucial for diagnosing and monitoring eye diseases.
• Current segmentation algorithms can be computationally intensive, limiting their clinical application.
• Optical coherence tomography (OCT) provides high-resolution cross-sectional images of the retina.

Purpose of the Study:

• To develop and evaluate novel segmentation algorithms for retinal layer identification using OCT signal intensity variations.
• To reduce the computational time required for segmenting the internal limiting membrane (ILM) and retinal pigment epithelium (RPE).
• To provide an efficient method for analyzing the structural features of healthy and diseased retinas.

Main Methods:

• Implementation of two signal intensity variation-based segmentation algorithms: one for ILM and one for RPE identification.
• Utilizing an 830 nm spectral domain OCT device for data acquisition.
• Validation of the segmentation method on OCT images from healthy and diseased eyes.

Main Results:

• Demonstration of a novel segmentation approach for retinal layer identification.
• Successful identification of the ILM and RPE using OCT signal intensity variations.
• The proposed algorithms aim to decrease calculation time for retinal layer segmentation.

Conclusions:

• The presented signal intensity variation-based segmentation algorithms offer an efficient method for retinal layer identification.
• This approach facilitates the structural analysis of retinas in both healthy and diseased conditions.
• The developed OCT segmentation technique has potential applications in clinical ophthalmology and research.