SUN J D, ZHANG H Y.DMDR-UNet：An algorithm for retinal blood vessel segmentation[J].Journal of Henan Polytechnic University(Natural Science) ,2023,42(6):142-148.

doi:10.16186/j.cnki.1673-9787.2022030060

Received:2022/03/23

Revised:2022/05/20

Published:2023/11/25

DMDR-UNet：An algorithm for retinal blood vessel segmentation

SUN Junding, ZHANG Hongying

School of Computer Science and Technology，Henan Polytechnic University，Jiaozuo 454000，Henan，China

Abstract:Aiming at the difficulty of collecting microvascular features of retinal vessels in fundus，an improved DMDR-UNet （deformable multiscale dense residual-UNet） segmentation model was proposed based on U-Net model.Firstly，a deformable convolutional network module was proposed to enhance the extraction of microvascular features，considering the free trend and rich morphology of retinal vessels.Secondly，multi-scale cavity convolution module was used to aggregate multi-scale information of retinal vessels under different receptive fields.Finally，a dense residual connection module was designed to reduce the semantic gap between codecs and enhance the interaction and supplement of feature information.Experiments based on DRIVE dataset showed that the proposed method could accurately identify and segment retinal microvessels，and achieve better segmentation results.

Key words:retinal vascular segmentation;U-Net;deformable convolution;multiscale;dense residual

018_2022030060_孙君顶_L.pdf