A deep learning framework for segmentation of retinal layers from OCT images

TL;DR

This paper presents a deep learning framework combining CNN and LSTM to automate retinal layer segmentation from OCT images, reducing manual parameter tuning and handling pathologies effectively.

Contribution

The proposed CNN-LSTM model automates OCT image preprocessing and segmentation, demonstrating high accuracy with minimal training data and outperforming traditional methods.

Findings

Pixel-wise mean absolute error of 1.30±0.48

Performance comparable to existing methods

Effective on both normal and AMD cases

Abstract

Segmentation of retinal layers from Optical Coherence Tomography (OCT) volumes is a fundamental problem for any computer aided diagnostic algorithm development. This requires preprocessing steps such as denoising, region of interest extraction, flattening and edge detection all of which involve separate parameter tuning. In this paper, we explore deep learning techniques to automate all these steps and handle the presence/absence of pathologies. A model is proposed consisting of a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The CNN is used to extract layers of interest image and extract the edges, while the LSTM is used to trace the layer boundary. This model is trained on a mixture of normal and AMD cases using minimal data. Validation results on three public datasets show that the pixel-wise mean absolute error obtained with our system is 1.30 plus or minus 0.48 which is lower than the inter-marker error of 1.79 plus or minus 0.76. Our model's performance is also on par with the existing methods.