Simultaneous arteriole and venule segmentation with domain-specific loss function on a new public database

Xiayu Xu, Rendong Wang, Peilin Lv, Bin Gao, Chan Li, Zhiqiang Tian, Tao Tan, Feng Xu

Research output: Contribution to journalArticlepeer-review

41 Citations (Scopus)


The segmentation and classification of retinal arterioles and venules play an important role in the diagnosis of various eye diseases and systemic diseases. The major challenges include complicated vessel structure, inhomogeneous illumination, and large background variation across subjects. In this study, we employ a fully convolutional network to simultaneously segment arterioles and venules directly from the retinal image, rather than using a vessel segmentation-arteriovenous classification strategy as reported in most literature. To simultaneously segment retinal arterioles and venules, we configured the fully convolutional network to allow true color image as input and multiple labels as output. A domain-specific loss function was designed to improve the overall performance. The proposed method was assessed extensively on public data sets and compared with the state-of-the-art methods in literature. The sensitivity and specificity of overall vessel segmentation on DRIVE is 0.944 and 0.955 with a misclassification rate of 10.3% and 9.6% for arteriole and venule, respectively. The proposed method outperformed the state-of-the-art methods and avoided possible error-propagation as in the segmentation-classification strategy. The proposed method was further validated on a new database consisting of retinal images of different qualities and diseases. The proposed method holds great potential for the diagnostics and screening of various eye diseases and systemic diseases.

Original languageEnglish
Article number#327542
Pages (from-to)3153-3166
Number of pages14
JournalBiomedical Optics Express
Issue number7
Publication statusPublished - 1 Jul 2018
Externally publishedYes


Dive into the research topics of 'Simultaneous arteriole and venule segmentation with domain-specific loss function on a new public database'. Together they form a unique fingerprint.

Cite this