Method for segmentation of the layers in the outer retina

Area of Science:

• Ophthalmology
• Medical Imaging
• Biomedical Engineering

Background:

• The outer retina comprises distinct layers crucial for visual function.
• Accurate segmentation of these layers is essential for diagnosing and monitoring retinal diseases.
• Optical coherence tomography (OCT) is a key imaging modality for in-vivo retinal visualization.

Purpose of the Study:

• To develop and validate a computational method for determining the number of visible outer retinal layers.
• To perform accurate layer segmentation in human retinal images.
• To assess the method's performance in both healthy and diseased retinas.

Main Methods:

• Representing each retinal layer as a Gaussian function.
• Employing multiple models with varying layer numbers to represent the outer retina.
• Utilizing maximum likelihood estimation (MLE) for parameter calculation.
• Selecting the best-fit model based on goodness of fit and complexity.

Main Results:

• Successful determination of the number of visible outer retinal layers.
• Accurate segmentation of retinal layers demonstrated.
• Application to in-vivo macular images from optical coherence tomography (OCT).
• Validation on both normal and retinitis pigmentosa (RP) affected retinas.

Conclusions:

• The proposed method effectively determines and segments outer retinal layers.
• The Gaussian function and MLE approach provide a robust model selection process.
• This technique holds potential for clinical applications in retinal disease assessment.