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±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.
@article{arxiv.1803.00232,
title = {DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images},
author = {Sripad Krishna Devalla and Prajwal K. Renukanand and Bharathwaj K. Sreedhar and Shamira Perera and Jean-Martial Mari and Khai Sing Chin and Tin A. Tun and Nicholas G. Strouthidis and Tin Aung and Alexandre H. Thiery and Michael J. A. Girard},
journal= {arXiv preprint arXiv:1803.00232},
year = {2018}
}