Accurate C/D ratio estimation with elliptical fitting for OCT image based on joint segmentation and detection network

Xu, Chenan; Chen, Zhongyue; Zhang, Xiao; Peng, Yuanyuan; Tan, Zhimin; Fan, Yu; Liao, Xulong; Chen, Haoyu; Shen, Jiayan; Chen, Xinjian

doi:10.1016/j.compbiomed.2023.106903

Cited by 1 publication

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the aforementioned image classification methods, image semantic segmentation methods detect and classify images at each pixel ( 21 , 22 ). Therefore, after semantic image segmentation, the retinal blood vessels or other important structures of the DR or other medical images are augmented, and the lesion area is directly detected and located.…”

Section: Introductionmentioning

confidence: 99%

Neighbored-attention U-net (NAU-net) for diabetic retinopathy image segmentation

Zhao,

Guan,

et al. 2023

Front. Med.

View full text Add to dashboard Cite

BackgroundDiabetic retinopathy-related (DR-related) diseases are posing an increasing threat to eye health as the number of patients with diabetes mellitus that are young increases significantly. The automatic diagnosis of DR-related diseases has benefited from the rapid development of image semantic segmentation and other deep learning technology.MethodsInspired by the architecture of U-Net family, a neighbored attention U-Net (NAU-Net) is designed to balance the identification performance and computational cost for DR fundus image segmentation. In the new network, only the neighboring high- and low-dimensional feature maps of the encoder and decoder are fused by using four attention gates. With the help of this improvement, the common target features in the high-dimensional feature maps of encoder are enhanced, and they are also fused with the low-dimensional feature map of decoder. Moreover, this network fuses only neighboring layers and does not include the inner layers commonly used in U-Net++. Consequently, the proposed network incurs a better identification performance with a lower computational cost.ResultsThe experimental results of three open datasets of DR fundus images, including DRIVE, HRF, and CHASEDB, indicate that the NAU-Net outperforms FCN, SegNet, attention U-Net, and U-Net++ in terms of Dice score, IoU, accuracy, and precision, while its computation cost is between attention U-Net and U-Net++.ConclusionThe proposed NAU-Net exhibits better performance at a relatively low computational cost and provides an efficient novel approach for DR fundus image segmentation and a new automatic tool for DR-related eye disease diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%