From Local to Global: A Graph Framework for Retinal Artery/Vein Classification

• Published in: IEEE transactions on nanobioscience Vol. 19; no. 4; pp. 589 - 597
• Main Authors: Huang, Fan, Tan, Tao, Dashtbozorg, Behdad, Zhou, Yi, Romeny, Bart M. Ter Haar
• Format: Magazine Article
• Language: English
• Published: United States IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Arteries; artery/vein classification; Artificial neural networks; Biomarkers; Biomedical imaging; Blood vessels; Classification; Convolution; Deep learning; Diabetes; Diabetes mellitus; Error correction; Eye disorders; Feature extraction; Fundus images; GCNet; graph convolutional networks; Image edge detection; Model accuracy; Neural networks; Photography; prediabetes; Retina; Retinopathy; Veins
• ISSN: 1536-1241; 1558-2639
• DOI: 10.1109/TNB.2020.3004481

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.