In this paper, we reformulate the conventional 2-D Frangi vesselness measure into a pre-weighted neural network (“Frangi-Net”), and illustrate that the Frangi-Net is equivalent to the original Frangi filter. Furthermore, we show that, as a neural network, Frangi-Net is trainable. We evaluate the proposed method on a set of 45 high resolution fundus images. After fine-tuning, we observe both qualitative and quantitative improvements in the segmentation quality compared to the original Frangi measure, with an increase up to 17% in F1 score.
Unable to display preview. Download preview PDF.
- 1.Maji D, Santara A, Mitra P, et al. Ensemble of deep convolutional neural networks for learning to detect retinal vessels in fundus images. arXiv. 2016.Google Scholar
- 2.Kirbas C, Quek F. A review of vessel extraction techniques and algorithms. ACM Comput Surv. 2004;36(2):81–121.Google Scholar
- 3.Frangi AF, Niessen WJ, Vincken KL, et al.; Springer. Multiscale vessel enhancement filtering. Proc MICCAI. 1998; p. 130–137.Google Scholar
- 4.Budai A, Bock R, Maier A, et al. Robust vessel segmentation in fundus images. Int J Biomed Imaging. 2013.Google Scholar
- 5.Maji D, Santara A, Ghosh S, et al.; IEEE. Deep neural network and random forest hybrid architecture for learning to detect retinal vessels in fundus images. Proc EMBC. 2015; p. 3029–3032.Google Scholar
- 6.Tetteh G, Rempfler M, Zimmer C, et al.; Springer. Deep-FExt: deep feature extraction for vessel segmentation and centerline prediction. Int Worksh Mach Learn Med Imaging. 2017; p. 344–352.Google Scholar
- 7.Würfl T, Ghesu FC, Christlein V, et al.; Springer. Deep learning computed tomography. Proc MICCAI. 2016; p. 432–440.Google Scholar
- 8.Budai A, Odstrcilik J. High resolution fundus image database; 2013.Google Scholar
- 9.Yin B, Li H, Sheng B, et al. Vessel extraction from non-fluorescein fundus images using orientation-aware detector. Med Image Anal. 2015;26(1):232–242.Google Scholar
- 10.Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015;15(1):29.Google Scholar