A deep learning framework for segmentation of retinal layers from OCT images
This addresses the need for automated diagnostic tools in ophthalmology, but it is incremental as it builds on existing deep learning methods with performance on par with prior work.
The paper tackled the problem of automating retinal layer segmentation from OCT images by proposing a deep learning framework combining CNN and LSTM, achieving a pixel-wise mean absolute error of 1.30 ± 0.48, which is lower than the inter-marker error of 1.79 ± 0.76.
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.