Micro-Vessel Image Segmentation Based on the AD-UNet Model
Zhongming Luo,
Yu Zhang,
Lei Zhou,
Binge Zhang,
Jianan Luo,
Haibin Wu
Affiliations
Zhongming Luo
The Higher Education Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang Province, National Experimental Teaching Demonstration Center of Measuring and Control Technology, Harbin University of Science and Technology, Harbin, China
The Higher Education Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang Province, National Experimental Teaching Demonstration Center of Measuring and Control Technology, Harbin University of Science and Technology, Harbin, China
Lei Zhou
The Higher Education Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang Province, National Experimental Teaching Demonstration Center of Measuring and Control Technology, Harbin University of Science and Technology, Harbin, China
Binge Zhang
Heilongjiang Institute of Construction Technology, Harbin, China
Jianan Luo
The Higher Education Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang Province, National Experimental Teaching Demonstration Center of Measuring and Control Technology, Harbin University of Science and Technology, Harbin, China
Haibin Wu
The Higher Education Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang Province, National Experimental Teaching Demonstration Center of Measuring and Control Technology, Harbin University of Science and Technology, Harbin, China
Retinal vessel segmentation plays a vital role in computer-aided diagnosis and treatment of retinal diseases. Considering the low contrast between retinal vessels and the background image, complex structural information as well as blurred boundaries between tissue and blood vessels, the retinal vessel image segmentation algorithm based on the improved U-Net network is proposed in the paper. The algorithm introduces an attention mechanism and densely connected network into the original U-Net network and realizes the automatic segmentation of retinal vessels. According to the test results of the algorithm on commonly-used datasets of the DRIVE and STARE fundus images, respectively, the accuracy is 0.9663 and 0.9684; the sensitivity is 0.8075 and 0.8437; the specificity is 0.9814 and 0.9762; the AUC values are 0.9846 and 0.9765; and the F-measures are 0.8203 and 0.8419, respectively. In the paper, the Attention-Dense-UNet (AD-UNet) algorithm is applied to segment human bulbar conjunctival micro-vessels. The experimental results show that the algorithm can achieve ideal segmentation results.
