Analysis of Retinal Vessel Segmentation with Deep Learning and its Effect on Diabetic Retinopathy Classification

The success of deep learning methodologies draws a huge attention to their applications in medical image analysis. One of the applications of deep learning is in segmentation of retinal vessel and severity classification of diabetic retinopathy (DR) from retinal funduscopic image. This paper studies U-Net model performance in segmenting retinal vessel with different settings of dropout and batch normalization and use it to investigate the effect of retina vessel in DR classification. Pre-trained Inception V1 network was used to classify the DR severity. Two sets of retinal images, with and without the presence of vessel, were created from MESSIDOR dataset. The vessel extraction process was done using the best trained U-Net on DRIVE dataset. Final analysis showed that retinal vessel is a good feature in classifying both severe and early cases of DR stage.

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

[2]  Dinesh Kant Kumar,et al.  Automatic Analysis of Retinal Vascular Parameters for Detection of Diabetes in Indian Patients with No Retinopathy Sign , 2016, International scholarly research notices.

[3]  Rajiv Raman,et al.  Prevalence of diabetic retinopathy in India: Sankara Nethralaya Diabetic Retinopathy Epidemiology and Molecular Genetics Study report 2. , 2009, Ophthalmology.

[4]  A. Rakhlin.  Diabetic Retinopathy detection through integration of Deep Learning classification framework , 2017 .

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

[6]  Z. Ockrim,et al.  Managing diabetic retinopathy , 2010, BMJ : British Medical Journal.

[7]  Ronnie D. Caytiles,et al.  Classification of Diabetic Retinopathy Images by Using Deep Learning Models , 2018 .

[8]  M. Engelgau,et al.  The Evolving Diabetes Burden in the United States , 2004, Annals of Internal Medicine.

[9]  Guy Cazuguel,et al.  FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE , 2014 .

[10]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[11]  Sven Loncaric,et al.  Retinal Vessel Segmentation using Deep Neural Networks , 2015, VISAPP.

[12]  Stephen Lin,et al.  DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field , 2016, MICCAI.

[13]  Ann L. Albright,et al.  Prevalence of diabetic retinopathy in the United States, 2005-2008. , 2010, JAMA.

[14]  R. Klein,et al.  Visual impairment in diabetes. , 1984, Ophthalmology.

[15]  Wynne Hsu,et al.  Alterations in Retinal Microvascular Geometry in Young Type 1 Diabetes , 2010, Diabetes Care.

[16]  Fitriani Fitriani,et al.  THE PREVALENCE OF DIABETIC RETINOPATHY , 2018 .

[17]  Tien Yin Wong,et al.  Retinal Vascular Geometry Predicts Incident Retinopathy in Young People With Type 1 Diabetes , 2011, Diabetes Care.

[18]  P. Mitchell,et al.  Retinal Vascular Geometry in Asian Persons with Diabetes and Retinopathy , 2012, Journal of diabetes science and technology.

[19]  Luc Van Gool,et al.  Deep Retinal Image Understanding , 2016, MICCAI.

[20]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Bunyarit Uyyanonvara,et al.  An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation , 2012, IEEE Transactions on Biomedical Engineering.

[22]  T. NagiReddy,et al.  Diabetic eye screening in multi ethnic population of Malaysia: epidemiological risk factors for development of diabetic retinopathy. , 2014 .

[23]  Dinesh Kumar,et al.  Validating retinal fundus image analysis algorithms: issues and a proposal. , 2013, Investigative ophthalmology & visual science.

[24]  Sang Jun Park,et al.  Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks , 2017, ArXiv.

[25]  Nishanthan Ramachandran,et al.  Diabetic retinopathy screening using deep neural network , 2018, Clinical & experimental ophthalmology.

[26]  Matthew D. Davis,et al.  Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. , 2003, Ophthalmology.

[27]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Kenneth W. Tobin,et al.  Exudate-based diabetic macular edema detection in fundus images using publicly available datasets , 2012, Medical Image Anal..

[29]  Tien Yin Wong,et al.  Retinal Vessel Tortuosity and Its Relation to Traditional and Novel Vascular Risk Markers in Persons with Diabetes , 2015, Current eye research.

[30]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.