DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images

TL;DR

This paper introduces DRUNET, a deep learning model that accurately segments six optic nerve head tissue layers in OCT images, aiding glaucoma diagnosis through automated tissue analysis.

Contribution

The paper presents a novel dilated-residual U-Net architecture specifically designed for multi-tissue segmentation in OCT images, achieving high accuracy.

Findings

Achieved a mean dice coefficient of 0.91 for tissue segmentation.

Demonstrated robustness of the segmentation framework against manual expert annotations.

Provides a foundation for automated analysis of ONH tissues in glaucoma studies.

Abstract

Given that the neural and connective tissues of the optic nerve head (ONH) exhibit complex morphological changes with the development and progression of glaucoma, their simultaneous isolation from optical coherence tomography (OCT) images may be of great interest for the clinical diagnosis and management of this pathology. A deep learning algorithm was designed and trained to digitally stain (i.e. highlight) 6 ONH tissue layers by capturing both the local (tissue texture) and contextual information (spatial arrangement of tissues). The overall dice coefficient (mean of all tissues) was $0.91 \pm 0.05$ when assessed against manual segmentations performed by an expert observer. We offer here a robust segmentation framework that could be extended for the automated parametric study of the ONH tissues.