Multiscale Network Followed Network Model for Retinal Vessel Segmentation
The shape of retinal blood vessels plays a critical role in the early diagnosis of diabetic retinopathy. However, it remains challenging to segment accurately the blood vessels, particularly the capillaries, in color retinal images. In this paper, we propose the multiscale network followed network (MS-NFN) model to address this issue. This model consists of an ‘up-pool’ NFN submodel and a ‘pool-up’ NFN submodel, in which max-pooling layers and up-sampling layers can generate multiscale feature maps. In each NFN, the first multiscale network converts an image patch into a probabilistic retinal vessel map, and the following multiscale network further refines the map. The refined probabilistic retinal vessel maps produced by both NFNs are averaged to construct the segmentation result. We evaluated this model on the digital retinal images for vessel extraction (DRIVE) dataset and the child heart and health study Open image in new window dataset. Our results indicate that the NFN structure we designed is able to produce performance gain and the proposed MS-NFN model achieved the state-of-the-art retinal vessel segmentation accuracy on both datasets.
KeywordsRetinal vessel segmentation Network followed network Fully convolutional network
This work was supported in part by the National Natural Science Foundation of China under Grants 61771397 and 61471297, in part by the China Postdoctoral Science Foundation under Grant 2017M623245, in part by the Fundamental Research Funds for the Central Universities under Grant 3102018zy031, and in part by the Australian Research Council (ARC) Grants. We also appreciate the efforts devoted to collect and share the DRIVE and Open image in new window datasets for retinal vessel segmentation.
- 1.Saker, S.: Diabetic retinopathy: in vitro and clinical studies of mechanisms and pharmacological treatments. University of Nottingham (2016)Google Scholar
- 7.Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
- 11.Setiawan, A.W., Mengko, T.R., Santoso, O.S., Suksmono, A.B.: Color retinal image enhancement using CLAHE. In: ICISS, pp. 1–3. IEEE, Jakarta (2013)Google Scholar
- 12.Mapayi, T., Viriri, S., Tapamo, J.R.: Adaptive thresholding technique for retinal vessel segmentation based on GLCM-energy information. Comput. Math. Methods Med. 2015, 597475 (2015)Google Scholar
- 14.Roychowdhury, S., Koozekanani, D., Parhi, K.: Blood vessel segmentation of fundus images by major vessel extraction and sub-image classification. IEEE J. Biomed. Health Inform. 19, 1118–1128 (2015)Google Scholar
- 16.Dasgupta, A., Singh, S.: A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation. In: IEEE 14th ISBI, pp. 248–251. IEEE, Melbourne (2017)Google Scholar