Learned Pre-processing for Automatic Diabetic Retinopathy Detection on Eye Fundus Images

Diabetic Retinopathy is the leading cause of blindness in the working-age population of the world. The main aim of this paper is to improve the accuracy of Diabetic Retinopathy detection by implementing a shadow removal and color correction step as a preprocessing stage from eye fundus images. For this, we rely on recent findings indicating that application of image dehazing on the inverted intensity domain amounts to illumination compensation. Inspired by this work, we propose a Shadow Removal Layer that allows us to learn the pre-processing function for a particular task. We show that learning the pre-processing function improves the performance of the network on the Diabetic Retinopathy detection task.

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

[2]  Raanan Fattal.  Single image dehazing , 2008, SIGGRAPH 2008.

[3]  Enrico Grisan,et al.  Luminosity and contrast normalization in retinal images , 2005, Medical Image Anal..

[4]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Jian Sun,et al.  Single image haze removal using dark channel prior , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Chris Dainty,et al.  Illumination correction of retinal images using Laplace interpolation. , 2012, Applied optics.

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

[8]  Sudipta Roy,et al.  Enhancement and restoration of non-uniform illuminated Fundus Image of Retina obtained through thin layer of cataract , 2018, Comput. Methods Programs Biomed..

[9]  Aurélio J. C. Campilho,et al.  Illumination Correction by Dehazing for Retinal Vessel Segmentation , 2017, 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS).

[10]  Shree K. Nayar,et al.  Vision and the Atmosphere , 2002, International Journal of Computer Vision.

[11]  Shree K. Nayar,et al.  Chromatic framework for vision in bad weather , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  Huiqi Li,et al.  An enhancement method for color retinal images based on image formation model , 2017, Comput. Methods Programs Biomed..

[13]  Sajib Saha,et al.  A novel method for automated correction of non-uniform/poor illumination of retinal images without creating false artifacts , 2018, J. Vis. Commun. Image Represent..

[14]  H R Taylor,et al.  Prevalence of diabetic retinopathy in Type 2 diabetes in developing and developed countries , 2013, Diabetic medicine : a journal of the British Diabetic Association.

[15]  Alessandro Bria,et al.  On the Duality Between Retinex and Image Dehazing , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.