期刊
IEEE TRANSACTIONS ON NANOBIOSCIENCE
卷 19, 期 4, 页码 589-597出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNB.2020.3004481
关键词
Retina; Arteries; Veins; Image edge detection; Biomedical imaging; Feature extraction; Fundus images; artery; vein classification; deep learning; graph convolutional networks; GCNet; prediabetes; diabetes; retinopathy
资金
- Netherlands Organization for Scientific Research (NWO) [629.001.003]
- Science and Technology Development Project of GuangZhou City [201604020016]
- Natural Science Foundation of China [61876194]
- Shanghai Key Lab of Digital Media Processing and Transmission [STCSM 18DZ2270700]
Fundus photography has been widely used for inspecting eye disorders by ophthalmologists or computer algorithms. Biomarkers related to retinal vessels plays an essential role to detect early diabetes. To quantify vascular biomarkers or the corresponding changes, an accurate artery and vein classification is necessary. In this work, we propose a new framework to boost local vessel classification with a global vascular network model using graph convolution. We compare our proposed method with two traditional state-of-the-art methods on a testing dataset of 750 images from the Maastricht Study. After incorporating global information, our model achieves the best accuracy of 86.45% compared to 85.5% from convolutional neural networks (CNN) and 82.9% from handcrafted pixel feature classification (HPFC). Our model also obtains the best area under receiver operating characteristic curve (AUC) of 0.95, compared to 0.93 from CNN and 0.90 from HPFC. The new classification framework has the advantage of easy deployment on top of local classification features. It corrects the local classification error by minimizing global classification error and it brings free additional classification performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据