Relation Networks for Optic Disc and Fovea Localization in Retinal Images

Diabetic Retinopathy is the leading cause of blindness in the world. At least 90\% of new cases can be reduced with proper treatment and monitoring of the eyes. However, scanning the entire population of patients is a difficult endeavor. Computer-aided diagnosis tools in retinal image analysis can make the process scalable and efficient. In this work, we focus on the problem of localizing the centers of the Optic disc and Fovea, a task crucial to the analysis of retinal scans. Current systems recognize the Optic disc and Fovea individually, without exploiting their relations during learning. We propose a novel approach to localizing the centers of the Optic disc and Fovea by simultaneously processing them and modeling their relative geometry and appearance. We show that our approach improves localization and recognition by incorporating object-object relations efficiently, and achieves highly competitive results.

[1]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[2]  Yichen Wei,et al.  Relation Networks for Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Jaspreet Kaur,et al.  Automated Localisation of Optic Disc and Macula from Fundus Images , 2012 .

[4]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

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

[6]  Joni-Kristian Kämäräinen,et al.  The DIARETDB1 Diabetic Retinopathy Database and Evaluation Protocol , 2007, BMVC.

[7]  A. Sevastopolsky,et al.  Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network , 2017, Pattern Recognition and Image Analysis.

[8]  C. G. Ravichandran,et al.  Automatic localization of fovea in retinal images based on mathematical morphology and anatomic structures , 2014 .

[9]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[10]  Fabrice Mériaudeau,et al.  Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research , 2018, Data.

[11]  Abdulkadir Sengür,et al.  Optic disc determination in retinal images with deep features , 2018, 2018 26th Signal Processing and Communications Applications Conference (SIU).

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[14]  Wasi Haider Butt,et al.  Retinal Images: Optic Disk Localization and Detection , 2010, ICIAR.

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

[16]  Hongying Lilian Tang,et al.  Automatic Optic Disc Abnormality Detection in Fundus Images: A Deep Learning Approach , 2016 .

[17]  Beverley Balkau,et al.  The prevalence of and factors associated with diabetic retinopathy in the Australian population. , 2003, Diabetes care.