A GCN-assisted deep learning method for peripapillary retinal layer segmentation in OCT images

Jiaxuan Li, Yuye Ling, Jiangnan He, Peiyao Jin, Jianfeng Zhu, Haidong Zou, Xun Xu, Shuo Shao, Yu Gan, Yikai Su

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Accurate retinal layer segmentation, especially the peripapillary retinal nerve fiber layer (RNFL) is critical for the diagnosis of ophthalmic diseases. However, due to the complex morphologies of the peripapillary region, most of the existing methods focus on segmenting the macular region and could not be directly applied to the peripapillary retinal optical coherence tomography (OCT) images. In this paper, we propose a novel graph convolutional network (GCN)-assisted segmentation framework based on a U-shape neural network for peripapillary retinal layer segmentation in OCT images. We argue that the strictly stratified structure of retina layers in addition to the centered optic disc is an ideal objective for GCN. Specifically, a graph reasoning block is inserted between the encoder and decoder of the U-shape neural network to conduct spatial reasoning. In this way, the peripapillary retina in OCT images is segmented into nine layers including RNFL. The proposed method was trained and tested on our collected dataset of peripapillary retinal OCT images. Experimental results showed that our segmentation method outperformed other state-of-the-art methods. In particular, compared with ReLayNet, the average and RNFL Dice coefficients are improved by 1.2% and 2.6%, respectively.

Original languageEnglish
Title of host publicationOptical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXV
EditorsJoseph A. Izatt, James G. Fujimoto
ISBN (Electronic)9781510640955
DOIs
StatePublished - 2021
EventOptical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXV 2021 - Virtual, Online, United States
Duration: 6 Mar 202111 Mar 2021

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11630
ISSN (Print)1605-7422

Conference

ConferenceOptical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXV 2021
Country/TerritoryUnited States
CityVirtual, Online
Period6/03/2111/03/21

Keywords

  • Deep learning
  • Glaucoma diagnosis
  • Global reasoning
  • Graph convolution
  • Image segmentation
  • Optical coherence tomography
  • Peripapillary retinal layer

Fingerprint

Dive into the research topics of 'A GCN-assisted deep learning method for peripapillary retinal layer segmentation in OCT images'. Together they form a unique fingerprint.

Cite this