International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 4, No. 4, 8 May 2012
Cover page and Table of Contents: PDF (size: 722KB)
Improvement of the Hard Exudates Detection Method Used For Computer- Aided Diagnosis of Diabetic Retinopathy
Full Text (PDF, 722KB), PP.19-27
Views: 0 Downloads: 0
Author(s)
Index Terms
Ophthalmology, Color Fundus Images, Diabetic Retinopathy (DR), Hard exudates, Segmentation, Mathematical morphology, k-means clustering algorithm
Abstract
Diabetic retinopathy is a severe and widely spread eye disease. Early diagnosis and timely treatment of these clinical signs such as hard exudates could efficiently prevent blindness. The presence of exudates within the macular region is a main hallmark of diabetic macular edema and allows its detection with high sensitivity. In this paper, we combine the k-means clustering algorithm and mathematical morphology to detect hard exudates (HEs) in retinal images of several diabetic patients. This method is tested on a set of 50 ophthalmologic images with variable brightness, color, and forms of HEs. The algorithm obtained a sensitivity of 95.92%, predictive value of 92.28% and accuracy of 99.70% using a lesion-based criterion.
Cite This Paper
Feroui Amel,Messadi Mohammed,Bessaid Abdelhafid,"Improvement of the Hard Exudates Detection Method Used For Computer- Aided Diagnosis of Diabetic Retinopathy", IJIGSP, vol.4, no.4, pp.19-27, 2012. DOI: 10.5815/ijigsp.2012.04.03
Reference
[1]M. Niemi, K. Winell. Diabetes In Finland Prevalence And Variation In Quality Of Care. Kirjapaino Hermes Oy Tampre, Finland, 2006.
[2]Akara Sopharak , Bunyarit Uyyanonvara , Sarah Barman, Thomas H. Williamson. Automatic Detection Of Diabetic Retinopathy Exudates From Non-Dilated Retinal Images Using Mathematical Morphology Methods. Computerized Medical Imaging And Graphics , 2008(32):720-727.
[3]Kauppi T, Kalesnykiene J, Kamarainen K, Lensu L, Sorri I. The Diaretdb1 Diabetic Retinopathy Database And Evaluation Protocol.
[4]Davis MD, Bressler SB, Aiello LP, Bressler NM, Browning DJ, Flaxel CJ. Comparison of time-domain and fundus photographic assessments of retinal thickening in eyes with diabetic macular edema. Invest Ophthalmol Vis Sci,2008(49):1745–52.
[5]Jayakumari C, Santhanam T. Detection of hard exudates for Diabetic Retinopathy Using Contextual Clustering and Fyzzy Art Neural Network. Asian Journal of Information Techonology, 2007(8): 842-846.
[6]Sánchez CI, García M, Mayo A, López MI, Hornero R. retinal image analysis based on mixture models to detect hard exudates. Medical Image Analysis, 2009(13): 650-658.
[7]Garcia M, Sanchez CI, Lopez MI, Abasolo D, R Hornero, “Neural network basad detection of hard exudates in retinal images”, Computer Methods and Programs in Biomedicine, 2009(93):9-19.
[8]Dupas B, Walter T, Erginay A, Ordonez R, Deb-Joardar N, Gain P, Klein JC, And Massin P, Evaluation Of Automated Fundus Photograph Analysis Algorithms For Detecting Microaneurysms, Haemorrhages And Exudates, And Of A Computer-Assisted Diagnostic System For Grading Diabetic Retinopathy. Diabets & Metabolism, 2010(36): 213- 220.
[9]Sanchez C. I., Niemeijer M., Schulten M. S. A. S., Abramo M., And Van Ginneken B., Improving Hard Exudate Detection In Retinal Images Through A Combination Of Local And Contextual Information,In Ieee Intl. Symposium On Biomedical Imaging, Pp 5-8,2010.
[10]Hussain F, Jaafar, Asoke K. Nandi and Waleed Al-Nuaimy, Automated Detection Of Exudates In Retinal Images Using A Splitand-Merge Algorithm,European Signal Processing Conference, EUSIPCO, 2010
[11]Hussain F. Jaafar, Asoke K. Nandi And Waleed Al-Nuaimy, Automated Detection And Grading Of Hard Exudates From Retinal Fundus Images, European Signal Processing Conference (EUSIPCO), 2011
[12]Kavitha S, Automatic Detection Of Hard And Soft Exudates In Fundus Images Using Color Histogram Thresholding. European Journal Of Scientific Research, 2011(48): 493-504.
[13]Ali Salem Bin Samma, Rosalina Abdul Salam. Adaptation Of K-Means Algorithm For Image Segmentation. Word Academy Of Science. Engineering Technology 50, 2009.
[14]Stephen S. Feman, Thomas C. Leonard-Martin, J. Stevens Andrews, Cecile C. Armbruster,Theresa L. Burdge, Judith D. Debelak, Angela Lanier, and Amy G. Fischer. A Quantitative System To Evaluate DiabeticRetinopathy From Fundus Photographs. Investigative Ophthalmology 8c Visual Scien, 1995(36) :174-181.
[15]Sinthanayothin C, Boyce JF, Cook HL, Williamson TH. Automated Localization Of The Optic Disc, Fovea, Retinal Blood Vessels From Digital Colour Fundus Images, Br J Ophthalmology, 1999(83):902–10.
[16]Suman Tatiraju, Avi Mehta. Image Segmentation Using K-Means Clustering, Em And Normalized Cuts. Department Of Eecs, University Of California – Irvine, Ca 92612.
[17]Francisco A. Pujol, Mar Pujol and Ramón Rizo. Optimizing Mathematical Morphology for Image Segmentation and Vision-based Path Planning in Robotic Environments. Vision Systems: Segmentation and Pattern Recognition,2007 :546
[18]Markku Kuivalainen. Retinal Image Analyzing Machine Vision; Master’s Thesis; Department Of Information Technology, Lappeenranta University Of Technology, 2005
[19]Rafael C, Richard E, Woods And Steven L, Digital Image Using Matlab Processing, University Of Tennessee, 2004.Liu He. Digital Image Processing and Application. Beijing: China Electric Power Press, 2006.
[20]Giancardo L, Meriaudeau F, Karnowski TP Li Y, Tobin Jr KW, Chaum E. Automatic Retina Exudates Segmentation Without A Manually Labelled Training Set,Internationa Symposium On Biomedica L Imaging, Russian Federation, 2011.
[21]Http://Messidor.Crihan.Fr/Download.Php.
[22]John A. Moving Beyond Sensitivity And Specificity: Using Likelihood Ratios To Help Interpret Diagnostic Tests. Austral. Prescrib, 2003(26):111-113.
[23]Maria K. Evaluation Strategies For Medical-Image Analysis And Processing Methodologies, In Medical Image Analysis Methods: The Electrical Engineering And Applied Signal Processing Series. Costaridou, L., Editor; Crc Press: Boca Raton, Fl, Usa,2005: 433-471.
[24]Ivo Soares, Miguel Castelo-Branco, António M. G. Pinheiro. Exudates Dynamic Detection In Retinal Fundus Images Based On The Noise Map Distribution. 19th European Signal Processing Conference (EUSIPCO), 2011.