Macular holes are a common eye condition which result in visual impairment. We look at the application of deep convolutional neural networks to the problem of macular hole segmentation. We use the 3D U-Net architecture as a basis and experiment with a number of design variants. Manually annotating and measuring macular holes is time consuming and error prone. Previous automated approaches to macular hole segmentation take minutes to segment a single 3D scan. Our proposed model generates significantly more accurate segmentations in less than a second. We found that an approach of architectural simplification, by greatly simplifying the network capacity and depth, exceeds both expert performance and state-of-the-art models such as residual 3D U-Nets.
@article{arxiv.2103.01299,
title = {Robust 3D U-Net Segmentation of Macular Holes},
author = {Jonathan Frawley and Chris G. Willcocks and Maged Habib and Caspar Geenen and David H. Steel and Boguslaw Obara},
journal= {arXiv preprint arXiv:2103.01299},
year = {2021}
}