A 3D Segmentation Method for Retinal Optical Coherence Tomography Volume Data

TL;DR

This paper introduces a novel 3D segmentation method for retinal OCT volume data that enhances accuracy and robustness by integrating pixel intensity, boundary information, and boundary point smoothing.

Contribution

The paper presents a new 3D segmentation technique for retinal OCT data that improves upon existing methods in efficiency, accuracy, and robustness.

Findings

The method effectively segments retinal OCT volumes with high accuracy.

It demonstrates robustness against noise and data variability.

The approach is computationally efficient for large datasets.

Abstract

With the introduction of spectral-domain optical coherence tomography (OCT), much larger image datasets are routinely acquired compared to what was possible using the previous generation of time-domain OCT. Thus, the need for 3-D segmentation methods for processing such data is becoming increasingly important. We present a new 3D segmentation method for retinal OCT volume data, which generates an enhanced volume data by using pixel intensity, boundary position information, intensity changes on both sides of the border simultaneously, and preliminary discrete boundary points are found from all A-Scans and then the smoothed boundary surface can be obtained after removing a small quantity of error points. Our experiments show that this method is efficient, accurate and robust.