Methods to enhance digital fundus image for diabetic retinopathy detection

Digital fundus images (DFIs) are crucial in detecting pathological phenomenon that would lead to various diseases. However, DFI has multiple contrast and illumination problems which makes enhancement a necessity. Consequently, DFI must be enhanced to allow for better visualization in order to facilitate ophthalmologists to carry out their diagnosis. In this work, an investigation of three enhancement methods namely, Histogram Equalization(HE), Contrast Limited Adaptive Histogram Equalization(CLAHE) and Mahalanobis Distance (MD), were conducted on the digital fundus images and the results are qualitatively presented using histogram representation and image product quality. The result shows that the MD is the best algorithm for the application of blood vessels image enhancement.

[1]  Toufique Ahmed Soomro,et al.  Enhancement of colour fundus image and FFA image using RETICA , 2012, 2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences.

[2]  P. Prentasic,et al.  Detection of Diabetic Retinopathy in Fundus Photographs , 2013 .

[3]  S. Hori.  Guidelines for the Management of Diabetic Retinopathy for the Internist , 2002 .

[4]  S. Pizer,et al.  An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement. , 1988, IEEE transactions on medical imaging.

[5]  S. Poornachandra,et al.  Retinal blood vessel segmentation using morphological structuring element and entropy thresholding , 2012, 2012 Third International Conference on Computing, Communication and Networking Technologies (ICCCNT'12).

[6]  Ian Constable,et al.  Fluorescein angiography and adverse drug reactions revisited: the Lions Eye experience , 2006, Clinical & experimental ophthalmology.

[7]  Lili Xu,et al.  A novel method for blood vessel detection from retinal images , 2010, Biomedical engineering online.

[8]  Enrico Grisan,et al.  Model-based illumination correction in retinal images , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[9]  Mahendra Kumar Patil,et al.  REVIEW OF IMAGE ENHANCEMENT TECHNIQUES USING HISTOGRAM EQUALIZATION , 2013 .

[10]  Ahmad Fadzil M. Hani,et al.  Retinal vasculature enhancement using independent component analysis , 2009 .

[11]  D. P. Sharma,et al.  Intensity Transformation using Contrast Limited Adaptive Histogram Equalization , 2013 .

[12]  S. Pizer,et al.  Adaptive grey level assignment in CT scan display. , 1984, Journal of computer assisted tomography.

[13]  Aliaa A. A. Youssif,et al.  Comparative Study of Contrast Enhancement and Illumination Equalization Methods for Retinal Vasculat , 2006 .

[14]  Himanshu Aggarwal,et al.  A Comprehensive Review of Image Enhancement Techniques , 2010, ArXiv.

[15]  V. Saravanan,et al.  Automated red lesion detection in diabetic retinopathy , 2013, 2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES.

[16]  Helen K. Li,et al.  Digital versus film Fundus photography for research grading of diabetic retinopathy severity. , 2010, Investigative ophthalmology & visual science.

[17]  Dongbo Zhang,et al.  Observation model based retinal fundus image normalization and enhancement , 2011, 2011 4th International Congress on Image and Signal Processing.

[18]  U. Rajendra Acharya,et al.  An Integrated Index for the Identification of Diabetic Retinopathy Stages Using Texture Parameters , 2012, Journal of Medical Systems.

[19]  M D Fox,et al.  Enhancement of chest radiographs with gradient operators. , 1988, IEEE transactions on medical imaging.

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