文献类型：期刊文献

英文题名：Retinal vessel segmentation with constrained-based nonnegative matrix factorization and 3D modified attention U-Net

作者：Yu, Yang[1];Zhu, Hongqing[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China

年份：2021

卷号：2021

期号：1

外文期刊名：EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING

收录：;EI(收录号：20210509872598);WOS:【SCI-EXPANDED(收录号:WOS:000613243800001)】；

基金：This work was supported by the National Nature Science Foundation of China under Grant 61872143.

语种：英文

外文关键词：Nonnegative matrix factorization; Retinal vessel segmentation; Within-class and between-class constrained; 3 Dimension; Attention U-Net

摘要：Due to the complex morphology and characteristic of retinal vessels, it remains challenging for most of the existing algorithms to accurately detect them. This paper proposes a supervised retinal vessels extraction scheme using constrained-based nonnegative matrix factorization (NMF) and three dimensional (3D) modified attention U-Net architecture. The proposed method detects the retinal vessels by three major steps. First, we perform Gaussian filter and gamma correction on the green channel of retinal images to suppress background noise and adjust the contrast of images. Then, the study develops a new within-class and between-class constrained NMF algorithm to extract neighborhood feature information of every pixel and reduce feature data dimension. By using these constraints, the method can effectively gather similar features within-class and discriminate features between-class to improve feature description ability for each pixel. Next, this study formulates segmentation task as a classification problem and solves it with a more contributing 3D modified attention U-Net as a two-label classifier for reducing computational cost. This proposed network contains an upsampling to raise image resolution before encoding and revert image to its original size with a downsampling after three max-pooling layers. Besides, the attention gate (AG) set in these layers contributes to more accurate segmentation by maintaining details while suppressing noises. Finally, the experimental results on three publicly available datasets DRIVE, STARE, and HRF demonstrate better performance than most existing methods.