Simultaneous arteriole and venule segmentation of dual-modal fundus images using a multi-task cascade network

Differentiating arterioles and venules in the fundus image is important for not only various eye diseases but also systemic diseases such as hypertension and ischemic stroke. In this paper, we use dual-modal fundus images and develop a cascade refined U-net (CRU-net) to improve the arteriovenous segmentation. In this paper, dual-modal fundus images include not only a regular color fundus image (RGB image) but also another two monochromic images acquired using two different wavelengths, 570 and 610 nm. The choice of these two wavelengths is based on the absorption spectra of hemoglobin. The two monochromic images provide much richer information on the arteriole and venule. Our proposed CRU-net can fully utilize the information and achieves the state-of-the-art performance on our dual-modal dataset (DualModal2019). The arteriovenous classification accuracy evaluated on the automatically detected vessels is 97.27%, significantly surpassed previous methods. The F1-scores are 77.69% and 79.53% for the arteriole and venule segmentation, respectively. We also test our CRU-net on the public DRIVE dataset with only the color fundus images. We achieve the accuracy of 93.97%, F1-scores of 73.50%, and 75.54% for the arteriole and venule, all of which significantly surpassed previously published methods. Our DualModal2019 dataset with manually annotated arterioles and venules is publicly available.