A Multi-task Network to Detect Junctions in Retinal Vasculature

Junctions in the retinal vasculature are key points to be able to extract its topology, but they vary in appearance, depending on vessel density, width and branching/crossing angles. The complexity of junction patterns is usually accompanied by a scarcity of labels, which discourages the usage of very deep networks for their detection. We propose a multi-task network, generating labels for vessel interior, centerline, edges and junction patterns, to provide additional information to facilitate junction detection. After the initial detection of potential junctions in junction-selective probability maps, candidate locations are re-examined in centerline probability maps to verify if they connect at least 3 branches. The experiments on the DRIVE and IOSTAR showed that our method outperformed a recent study in which a popular deep network was trained as a classifier to find junctions. Moreover, the proposed approach is applicable to unseen datasets with the same degree of success, after training it only once.

[1]  Frans Coenen,et al.  Automatic Detection and Distinction of Retinal Vessel Bifurcations and Crossings in Colour Fundus Photography , 2018, J. Imaging.

[2]  Jeny Rajan,et al.  Recent Advancements in Retinal Vessel Segmentation , 2017, Journal of Medical Systems.

[3]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[4]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[5]  Erik J. Bekkers,et al.  Automatic detection of vascular bifurcations and crossings in retinal images using orientation scores , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[6]  Samaneh Abbasi-Sureshjani,et al.  Biologically-Inspired Supervised Vasculature Segmentation in SLO Retinal Fundus Images , 2015, ICIAR.

[7]  Roberto Marcondes Cesar Junior,et al.  Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification , 2005, ArXiv.

[8]  Domenico Tegolo,et al.  AUTOMATIC DETECTION AND CLASSIFICATION OF RETINAL VASCULAR LANDMARKS , 2014 .

[9]  George Azzopardi,et al.  Automatic detection of vascular bifurcations in segmented retinal images using trainable COSFIRE filters , 2013, Pattern Recognit. Lett..

[10]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[11]  Manuel G. Penedo,et al.  Automatic detection and characterisation of retinal vessel tree bifurcations and crossovers in eye fundus images , 2011, Comput. Methods Programs Biomed..

[12]  Hongbin Shen,et al.  Line Junction Detection Without Prior-Delineation of Curvilinear Structure in Biomedical Images , 2018, IEEE Access.

[13]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Tianfu Wang,et al.  A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images , 2016, IEEE Transactions on Medical Imaging.