|
Abstract Hemorrhages are early symptoms of diabetic retinopathy (DR), the accurate detection of hemorrhages in fundus images is an important contribution for building automatic screening system of DR, a novel algorithm based on kmeans clustering and adaptive template matching was proposed in this work. Firstly, HSV brightness correction and contrast limited adaptive histogram equalization were applied to fundus images. Then, the candidate hemorrhages were extracted by using kmeans clustering. At last, adaptive template matching with normalized crosscorrelation and SVM classifier were used to screen the candidates, and the hemorrhages were detected. The approach was evaluated on 219 fundus images from the databases of DIARETDB. Using an image criterion, we achieved 100% sensitivity, 80% specificity and 924% accuracy. With a lesion criterion, we reached a sensitivity of 89% and a positive predictive value of 873%. The results show that hemorrhages in fundus images can be detected automatically using this method.
|
|
|
|
|
[1]Ravishankar S, Jain A, Mittal A. Automated feature extraction for early detection of diabetic retinopathy in fundus images [C] //International Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 210-217.
[2]Jaafar HF, Nandi AK, AlNuaimy W. Automated detection of red lesions from digital color fundus photographs [C] //33rd Annual International Conference of the Engineering in Medicine and Biology Society. Boston: IEEE, 2011: 6232-6235.
[3]Nutnaree K, Smith G, Bunyarit U. Automated retinal hemorrhage detection using morphological top hat and rulebased classification [C] //3rd International Conference on Intelligent Computational Systems. Singapore: IEEE, 2013: 39-43.
[4]Li Tang, Niemeijer M, Abramoff MD. Splat feature classification: detection of the presence of large retinal hemorrhages [C] //8th International Symposium on Biomedical Imaging: From Nano to Macro. Chicago: IEEE, 2011: 681-684.
[5]Niemeijer M, Ginneken B, Staal J, et al. Automatic detection of red lesions in digital color fundus photographs [J]. IEEE Transactions on Medical Imaging, 2005, 24(5): 584-592.
[6]Hatanaka Y, Nakagawa T, Hayashi Y, et al. CAD scheme to detect hemorrhages and exudates in ocular fundus images [J]. SPIE Medical Imaging: ComputerAided Diagnosis, 2007, 6514(2): 1-8.
[7]Hatanaka Y, Nakagawa T, Hayashi Y, et al. Improvement of automated detection method of hemorrhages in fundus images [C] //30th Annual International Conference of the Engineering in Medicine and Biology Society. Vancouver: IEEE, 2008: 5429-5432.
[8]Saleh MD, Eswaran C. An automated decisionsupport system for nonproliferative diabetic retinopathy disease based on MA and HA detection [J]. Computer Methods and Programs in Biomedicine, 2012, 108(1): 186-196.
[9]García M, Sánchez CI, López MI, et al. Automatic detection of red lesions in retinal images using a multilayer perceptron neural network [C] //30th Annual International Conference of the Engineering in Medicine and Biology Society. Vancouver: IEEE, 2008: 5425-5428.
[10]García M, López MI, lvarez D, et al. Assessment of four neural network based classifiers to automatically detect red lesions in retinal images [J]. Medical Engineering & Physics, 2010, 3210): 1085-1093.
[11]Kande GB, Savithri TS, Subbaiah PV. Automatic detection of microaneurysms and hemorrhages in digital fundus images [J]. Journal of Digital Imaging, 2010, 23(4): 430-437.[12]Bae JP, Kim KG, Kang HC, et al. A study on hemorrhage detection using hybrid method in fundus images [J]. Journal of Digital Imaging, 2011, 24(3): 394-404.
[13]Devaraj D, Nagaveena. Detection of red lesion in diabetic retinopathy using adaptive thresholding method [J]. International Journal of Engineering Research & Technology, 2013, 2(4): 1889-1892.
[14]Krishna K, Murty MN. Genetic Kmeans algorithm [J]. IEEE Transactions on System, Man and Cybernetics, 1999, 29(3): 433-439.
[15]Vlachos M, Dermatas E. Multiscale retinal vessel segmentation using line tracking [J]. Computerized Medical Imaging and Graphics, 2010, 34(3): 213-227.
[16]Lewis JP. Fast template matching [C] //Canadian Image Processing and Pattern Recognition Society. Quebec: IEEE, 1995: 120-123. |
|
|