A generative adversarial network with multi-scale convolution and dilated convolution res-network for OCT retinal image despeckling

Yu，Xiaojun1,2; Li，Mingshuai1; Ge，Chenkun1; Shum，Perry Ping3; Chen，Jinna3; Liu，Linbo4

2023-02-01

10.1016/j.bspc.2022.104231

Biomedical Signal Processing and Control   Impact Factor & Quartile

1746-8094

1746-8108

Optical coherence tomography (OCT) has been widely adopted for imaging in various areas, yet it is largely affected by speckle noise generated from the coherent multiple-scattered photons. To alleviate the influences of speckle noise, a generative adversarial network with multi-scale convolution and dilated convolution res-network (MDR-GAN) is proposed in this study. Specifically, a cascade multi-scale module (CMSM) consisting of three convolution and dilated convolution res-network (CD-Rn) blocks is proposed to raise network learning capacity, while a new residual learning method is devised to link the input and output feature maps for feature reconstructions. Among them, CMSM has the characteristics of capturing multi-scale local features of images. Residual learning effectively avoids the degradation problem of the network. Extensive experiments with four retinal OCT datasets are conducted and results are compared with those of the state-of-the-art deep learning networks to verify the effectiveness of the proposed MDR-GAN. Results demonstrate that the denoising effect of MDR-GAN is better than those of the other denoising methods. The peak single-to-noise ratio (PSNR) of MDR-GAN is improved by 2 dB as compared that of Pix2pix, while its equivalent number of looks (ENL) is improved by at least 233.9% as compared with the-state-of-the-art existing methods. Our MDR-GAN code can be download at https://github.com/Austin-Lms/MDR-GAN.

Generative adversarial network Optical coherence tomography Residual learning Speckle noise

SCI

English

Corresponding

Basic and Applied Basic Research Foundation of Guangdong Province[2021B1515120013];National Natural Science Foundation of China[61705184];

Engineering

Engineering, Biomedical

WOS:000875634300015

ELSEVIER SCI LTD

2-s2.0-85139818771

Scopus

1.School of Automation,Northwestern Polytechnical University,Xi'an,Shaanxi,710072,China
2.Shenzhen Research Institute of NorthwesternPolytechnical University,Shenzhen,Guangdong,518057,China
3.Department of Electrical and Electronic Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,518055,China
4.School of Electrical and Electronic Engineering,Nanyang Technological University,639798,Singapore

Yu，Xiaojun,Li，Mingshuai,Ge，Chenkun,et al. A generative adversarial network with multi-scale convolution and dilated convolution res-network for OCT retinal image despeckling[J]. Biomedical Signal Processing and Control,2023,80.

Yu，Xiaojun,Li，Mingshuai,Ge，Chenkun,Shum，Perry Ping,Chen，Jinna,&Liu，Linbo.(2023).A generative adversarial network with multi-scale convolution and dilated convolution res-network for OCT retinal image despeckling.Biomedical Signal Processing and Control,80.

Yu，Xiaojun,et al."A generative adversarial network with multi-scale convolution and dilated convolution res-network for OCT retinal image despeckling".Biomedical Signal Processing and Control 80(2023).