Automatic artery/vein classification using a vessel-constraint network for multicenter fundus images

• Verfasst von: Hu, Jingfei [VerfasserIn]
• Verfasst von: Wang, Hua [VerfasserIn]
• Verfasst von: Cao, Zhaohui [VerfasserIn]
• Verfasst von: Wu, Guang [VerfasserIn]
• Verfasst von: Jonas, Jost B. [VerfasserIn]
• Verfasst von: Wang, Ya Xing [VerfasserIn]
• Verfasst von: Zhang, Jicong [VerfasserIn]
• Titel: Automatic artery/vein classification using a vessel-constraint network for multicenter fundus images
• Verf.angabe: Jingfei Hu, Hua Wang, Zhaohui Cao, Guang Wu, Jost B. Jonas, Ya Xing Wang and Jicong Zhang
• E-Jahr: 2021
• Jahr: 11 June 2021
• Umfang: 15 S.
• Fussnoten: Gesehen am 05.10.2021
• Titel Quelle: Enthalten in: Frontiers in cell and developmental biology
• Ort Quelle: Lausanne : Frontiers Media, 2013
• Jahr Quelle: 2021
• Band/Heft Quelle: 9(2021), Artikel-ID 659941, Seite 1-15
• ISSN Quelle: 2296-634X
• DOI: doi:10.3389/fcell.2021.659941
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1772414824

Abstract

Retinal blood vessel morphological abnormalities are generally associated with cardiovascular, cerebrovascular, and systemic diseases, automatic artery/vein (A/V) classification is particularly important for medical image analysis and clinical decision making. However, the current method still has some limitations in A/V classification, especially the blood vessel edge and end error problems caused by the single scale and the blurred boundary of the A/V. To alleviate these problems, in this work, we propose a vessel-constraint network (VC-Net) that utilizes the information of vessel distribution and edge to enhance A/V classification, which is a high-precision A/V classification model based on data fusion. Particularly, the VC-Net introduces a vessel-constraint (VC) module that combines local and global vessel information to generate a weight map to constrain the A/V features, which suppresses the background-prone features and enhances the edge and end features of blood vessels. In addition, the VC-Net employs a multiscale feature (MSF) module to extract blood vessel information with different scales to improve the feature extraction capability and robustness of the model. And the VC-Net can get vessel segmentation results simultaneously. The proposed method is tested on publicly available fundus image datasets with different scales, namely, DRIVE, LES, and HRF, and validated on two newly created multicenter datasets: Tongren and Kailuan. We achieve a balance accuracy of 0.9554 and F1 scores of 0.7616 and 0.7971 for the arteries and veins, respectively, on the DRIVE dataset. The experimental results prove that the proposed model achieves competitive performance in A/V classification and vessel segmentation tasks compared with state-of-the-art methods. Finally, we test the Kailuan dataset with other trained fusion datasets, the results also show good robustness. To promote research in this area, the Tongren dataset and source code will be made publicly available. The dataset and code will be made available at https://github.com/huawang123/VC-Net.