Automated delineation of corneal layers on OCT images using a boundary-guided CNN. (December 2021)

• Record Type: Journal Article
• Authors: Wang, Lei; Shen, Meixiao; Chang, Qian; Shi, Ce; Chen, Yang; Zhou, Yuheng; Zhang, Yanchun; Pu, Jiantao; Chen, Hao
• Is Part Of: Pattern recognition. Volume 120(2021)
• Publication Date: 2021-12
• Subjects: Corneal layers -- OCT images -- Segmentation -- Convolutional neural networks; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108158
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A boundary-guided convolutional neural network (BG-CNN) was proposed to accurately and simultaneously segment different corneal layers and delineate their boundaries from OCT images. Two network modules were defined based on the classical U-Net network by introducing three different convolutional blocks. Experiment results on our collected OCT images demonstrated that the developed network achieved reasonable performance to identify corneal layers, as compared with several available networks. Abstract: Accurate segmentation of corneal layers depicted on optical coherence tomography (OCT) images is very helpful for quantitatively assessing and diagnosing corneal diseases ( e.g., keratoconus and dry eye). In this study, we presented a novel boundary-guided convolutional neural network (CNN) architecture (BG-CNN) to simultaneously extract different corneal layers and delineate their boundaries. The developed BG-CNN architecture used three convolutional blocks to construct two network modules on the basis of the classical U-Net network. We trained and validated the network on a dataset consisting of 1, 712 OCT images acquired on 121 subjects using a 10-fold cross-validation method. Our experiments showed an average dice similarity coefficient (DSC) of 0.9691, an intersection over union (IOU) of 0.9411, and a Hausdorff distance (HD) of 7.4423 pixels. Compared with several other classical networks, namely U-Net, Attention U-Net, Asymmetric U-Net, BiO-Net, CE-Net, CPFnte, M-Net, and Deeplabv3, on the same dataset, the developed network demonstrated a promising performance, suggesting its unique strength in segmenting corneal layers depicted on OCT images.