TY - JOUR
T1 - Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images
AU - Li, Jiaxuan
AU - Jin, Peiyao
AU - Zhu, Jianfeng
AU - Zou, Haidong
AU - Xu, Xun
AU - Tang, Min
AU - Zhou, Minwen
AU - Gan, Yu
AU - He, Jiangnan
AU - Ling, Yuye
AU - Su, Yikai
N1 - Publisher Copyright:
© 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement.
PY - 2021/4
Y1 - 2021/4
N2 - An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma. However, due to the presence of the optic disc, the anatomical structure of the peripapillary region of the retina is complicated and is challenging for segmentation. To address this issue, we develop a novel graph convolutional network (GCN)-assisted two-stage framework to simultaneously label the nine retinal layers and the optic disc. Specifically, a multi-scale global reasoning module is inserted between the encoder and decoder of a U-shape neural network to exploit anatomical prior knowledge and perform spatial reasoning. We conduct experiments on human peripapillary retinal OCT images. We also provide public access to the collected dataset, which might contribute to the research in the field of biomedical image processing. The Dice score of the proposed segmentation network is 0.820 ± 0.001 and the pixel accuracy is 0.830 ± 0.002, both of which outperform those from other state-of-the-art techniques.
AB - An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma. However, due to the presence of the optic disc, the anatomical structure of the peripapillary region of the retina is complicated and is challenging for segmentation. To address this issue, we develop a novel graph convolutional network (GCN)-assisted two-stage framework to simultaneously label the nine retinal layers and the optic disc. Specifically, a multi-scale global reasoning module is inserted between the encoder and decoder of a U-shape neural network to exploit anatomical prior knowledge and perform spatial reasoning. We conduct experiments on human peripapillary retinal OCT images. We also provide public access to the collected dataset, which might contribute to the research in the field of biomedical image processing. The Dice score of the proposed segmentation network is 0.820 ± 0.001 and the pixel accuracy is 0.830 ± 0.002, both of which outperform those from other state-of-the-art techniques.
UR - http://www.scopus.com/inward/record.url?scp=85104394893&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85104394893&partnerID=8YFLogxK
U2 - 10.1364/BOE.417212
DO - 10.1364/BOE.417212
M3 - Article
AN - SCOPUS:85104394893
VL - 12
SP - 2204
EP - 2220
JO - Biomedical Optics Express
JF - Biomedical Optics Express
IS - 4
ER -