INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK BLOOD VESSEL EXTRACTION FOR AUTOMATED DIABETIC RETINOPATHY JAYKUMAR S. LACHURE 1, PROF. A.V. DEORANKAR 2, PROF. SAGAR LACHURE 3 1. M. Tech. Scholar (CSE), GCOE Amravati, GCOE Amravati, YCCE Nagpur. 2. HOD of Information & Technology, GCOE Amravati, GCOE Amravati, YCCE Nagpur. 3. Assistant Professor (CSE), GCOE Amravati, GCOE Amravati, YCCE Nagpur. Accepted Date: 05/03/2015; Published Date: 01/05/2015 Abstract: The extraction of retinal blood vessels in the retina is a critical and important step in identification of diabetic retinopathy (DR).DR can lead to chronical disease which can lead to permanent blindness. This paper represents the hybrid method for blood vessel extraction to extract blood vessels. Extraction of the blood vessels is the necessary steps in the detection of DR because the blood vessels are the important features of the retinal image. The exudates are the brightest portion of the image which occurs due to lesion deposit. Extraction of the blood vessels can help the ophthalmologists to detect the diseases earlier for avoidance of further disease. The blood vessels are extracted and eliminated by using morphology operation such as opening, closing, filling, dilation, erosion and morphological reconstruction. The objective of this paper is to detect the GLCM texture features of the image. By using this result, the ophthalmologists can easily detect the diseases. Keywords: Diabetic Retinopathy, Blood Vessels, Morphological Operation, Texture Corresponding Author: MR. JAYKUMAR S. LACHURE Access Online On: www.ijpret.com How to Cite This Article: PAPER-QR CODE 1703
INTRODUCTION Many people in the world are threatened by the DR. DR is the eye disease that can lead to permanent blindness. It arises due to the high sugar level and glucose level in the blood. According to the research, the screening of DR can lead to reduce the risk of blindness by 50% [1]. Therefore, early detection could limit the severity of the disease and the disease get treat more efficiently. The optic disc (OD) detection is an important step for detection of features like GLCM and texture parameter. The OD can be seen as the elliptical shape in the eye fundus image. Size of OD varies from one person to another. In color fundus image, it appears as the bright yellowish region as the exudates. The OD is the normal feature of the image and the exudates are occurring in abnormal case. Detection the OD can lead to avoid the false positive in the detection of the exudates [4]. And also the extraction of the blood vessels is as important as the detection of the OD because the optic disc and the blood vessels are the normal features of the image. Manual detection of blood vessels is difficult since the appearance of blood vessel in a retinal image is complex and having low contrast [5]. A number of methods for optic disc detection and blood vessels detection have been published. Located the optic disc center by means of template matching and extracted its boundary using a snake initialized on a morphologically enhanced region of the optic disc.. Initially, they determined a set of OD candidate regions by means of multi-resolution processing through pyramidal decomposition. For each OD region candidate, they calculated a simple confidence value representing the ratio between the mean intensity inside the candidate region and inside its neighborhood. The Canny edge detector and a Rayleigh-based threshold were then applied to the green-band image regions corresponding to the candidate regions, constructing a binary edge map. As final step, using the Hausdorff distance between the edge map regions and circular templates with different radii, they decided the OD among all the candidates. There are some methods for blood vessels detection in retinal fundus images such as region growing technique [10], morphological and thresholding techniques [11], neural network based approaches [12], statistical classification based methods and hierarchical methods [12]. This paper presents the optic disc detection and blood vessels detection techniques based on mathematical morphology on the fundus images because it is very fast and requires lower computing power. Therefore the system can be used even on a very poor computer system. 1704
PRE-PROCESSING STAGE Image Acquisition All digital retinal images are taken from patients using the non-mydriatic retinal fundus camera. The images are used From publically messidor data set. The original (RGB) image is transformed into appropriate colour space for further processes. And then, filtering technique is used to reduce the effect of noise. After using the filtering technique, the noise such as salt and pepper noise are removed from the image. Then contrast-limited adaptive histogram equalization (CLAHE) is used for image enhancement. Unlike histogram, it operates on small data regions rather than the entire image. This function uses a contrast-enhancement method that work significantly better than regular histogram equalization for most images. Converting Colors from RGB to HSI Fig1: Histogram Equalization HSI means hue saturation and intensity. In this colour model space, the intensity component is decoupled from colour carrying information (hue and saturation) in colour image, hence an ideal tool for the development of image processing algorithms. The HSI space consists of a vertical intensity axis and the locus of colour points that lie on a plane perpendicular to this axis, as the plan move up and down the intensity axis [14]. The important components of HSI colour space are the vertical intensity axis and the length of the vector to the colour point and the angle this vector makes to the red axis. The transformation equations used in the conversion of RGB to HSI are 1705
h = undefined if c = 0 G B mod6 if M = R C B R + 2 if M = R C R G + 4 if M = B C and the saturation component is given by, S = 1-3/(R+G+B)][min(R,G,B)]. Finally, the intensity component is given by, I = 1/3(R+G+B). Filtering Techniques h = 60 h Noise can cause the trouble in the detection of disease. The noise contains in the image is reduced by using the filtering technique such as median filter. Median Filtering The median filter is a nonlinear filter, which can reduce impulsive distortions in an image and without too much distortion to the edges of such an image. It is an effective method that of suppressing isolated noise without blurring sharp edges. Median filtering operation replaces a pixel by the median of all pixels in the neighbourhood of small sliding window. It gives better results then the neighbourhood averaging in the case where noise is of impulsive nature. The advantage of a median filter is that it is very robust and has the capability to filter only outliers and is thus an excellent choice for the removal of especially salt and pepper noise and horizontal scanning artefacts. Figure2 Original Image before Median Filtering, Image after Median Filtering 1706
According to the result images, the median filter is the best suit to reduce the effect the noise. And also, it can reduce the noise without blurring the edge. Therefore, the median filter is chosen for the filtering purpose. Image Enhancement The result image of the median filter is enhanced by using the histogram equalization technique. The histogram equalization technique is used to overcome the uneven-illumination case. There are two methods to enhance the image: Histogram equalisation and Adaptive histogram equalisation Histogram Equalisation It enhances the contrast of the images by transforming the values in an intensity image. The procedures of the histogram equalisation are- (i) Find the running sum of the pixel values (ii) Normalise the values by dividing the total number of pixels (iii) Multiply by the maximum gray-level value and round the value Adaptive Histogram Equalisation Unlike histogram, it operates on small data regions (tiles) rather than the entire image. And also contrast enhancement can be limited in order to avoid amplifying the noise which might be presented in the image. So, Adaptive histogram equalisation technique works significantly better than regular histogram equalization for most images. According to results, the adaptive histogram equalisation technique is used for image enhancement purpose. Morphology Operation Dilation adds pixels to the boundaries of objects in an image. Erosion removes pixels on object boundaries. The morphological open operation is an erosion followed by a dilation, using the same structuring element for both operations. Dilated A B = Z (B) Z A φ Disk Shaped SE(B) on A 1707
Erosion A B = Z (B) z A Closing Operator A B = (A B) B Thresholding The Otsu's thresholding technique is applied to the image to detect the desire area. The optic disc is the largest and brightest region of the image. The optic disc detection is useful because it can reduce the false positive detection of the exudates. BLOOD VESSELS DETECTION The blood vessels detection and elimination is also important as the optic disc detection for further process because the optic disc and the blood vessels are the normal features of the images. The general flow chart of the blood vessels detection is shown in Figure below. To detect the blood vessels, first the input image is converted into grayscale image due to strengthen the appearance of the blood vessels. Then the median filtering and the CLAHE techniques are used for reducing noise and image enhancement purposes. Then, the closing and the filling operators are used to close the same intensity values and fill the holes in the vessels. I (Difference) =ϕ (B1)(I)-fill(I) [1] Where, B1 is the morphological structuring element. Then the Otsu's thresholding technique is applied to the result image to obtain the vessels area. I(vessels) =Thresholding(I) [2] RESULTS The results of the blood vessels detection are shown in below. The closing and the filling operators are used to close the same intensity values and fill the holes in the vessels. The result of the closing and the filling of the images are used to detect the line tracking of the vessels. To get the blood vessels detected image finally boundary clipping image is subtracted to get blood vessel image from Fig. 3f) 1708
Fig. 3a) colour fundus image Fig. 3b) green channel image Fig. 3c) Histogram Equalization Fig. 3d) Boundary Clipping image Fig. 3e)Line track image Fig. 3f) Blood vessel detected image CONCLUSIONS Morphology operations are performed for optic disc and the blood vessels detections. The input image is in RGB colour space and for the further processes the image is converted into HSI colour space model. The adaptive median filter is used to the reduced noise and also reduces 1709
the effect of noise without blurring the edge. And then, applied the adaptive histogram equalisation technique is used for image enhancement and also used to overcome the uneven brightness. Therefore, adaptive median filter and the adaptive histogram equalisation techniques are used for noise reduction and image enhancement purposes. Optic disc detection and the blood vessels detection are the major role in the screening of DR. The results of this work can be used in the future processes such as the screening of diabetic retinopathy, glaucoma and so on. This detection method doesn't need the highly efficient computer so it is suitable for rural area in developing countries. REFERENCES 1. Li Tang, Meindert Niemeijer, Joseph M. Reinhardt, Mona K. Garvin,and Michael D. Abràmoff, Splat Feature Classification with Application to Retinal Hemorrhage Detection in Fundus Images, Medical Imaging, IEEE Transactions Vol. 32, No. 2, pp. 364-375, Feb.2013. 2. Istvan Lazar and Andras Hajdu, Retinal Microaneurysm Detection Through Local Rotating Cross-Section Profile Analysis, IEEE Transactions On Medical Imaging, Vol. 32, No. 2, Feb. 2013. 3. Balint Antal and Andras Hajdu, An Ensembl -Based System for Microaneurysm Detection and Diabetic Retinopathy Grading, IEEE Transactions On Biomedical Engineering, Vol. 59, No. 6, June 2012. 4. K. Sai Deepak, J. Sivaswamy, Automatic Assessment of Macular Edema from Colour Retinal Images, Medical Imaging, IEEE Transactions, Vol. 31, No. 3, pp. 766-776, March 2012.. 5. L. Giancardo, F. Meriaudeau, T. Karnowski, K. Tobin, E. Grisan, P. Favaro, A. Ruggeri, and E. Chaum, Textureless macula swelling detection with multiple retinal fundusimages, IEEE Trans. Biomed. Eng., Vol. 58, No. 3, pp. 795 799, Mar. 2011. 6. Keerthi Ram, G. D. Joshi, J. Sivaswamy, A Successive clutter-rejection Based Approach for Early Detection of Diabetic Retinopathy, IEEE Transactions on Biomedical Engineering,Vol. 58, No. 3, March 2011. 7. C. Agurto, V. Murray, E. Barriga, S.Murillo, M.Pattichis, H. Davis, S.Russell, M.Abramoff, and P. Soliz, Multiscale am-fm methods for diabetic retinopathy lesion detection, Medical Imaging, IEEE Transactions, vol. 29, No. 2, pp. 502 512, Feb. 2010. 1710
8. Keerthi Ram and Jayanthi Sivaswamy, Multi-space clustering for segmentation of Exudates in Retinal Colour Photographs, 31st Annual International Conference of the IEEE EMBS, USA, pp 1437-1440, September 2009. 9. Alireza Osare et al., A Computational Intelligence-Based Approach for Detection of Exudates in Diabetic Retinopathy Images, IEEE Transactions on Information Technology in Biomedicine, Vol. 13, No. 4, pp 535-545, July 2009. 10. Akara Sopharek et. Al., Automatic exudates detection for diabetic retinopathy Screening, 10.2306/Science asia1513-1874.2009. 35.080, pp 80-88. Feb 2009 11. Wang Huan, Hsu Wynne, Lee Mong Li, Effective Detection of Retinal Exudates in Fundus Images, IEEE Conference on Biomedical Engineering and Informatics, DOI: 978-1-4244-4134- 1/09, Jan 2009. 12. Sai Prasad Ravishankar, Arpit Jain, Anurag Mittal, Automated Feature Extraction for Early Detection of Diabetic Retinopathy in Fundus Images, IEEE Conference on Computer vision and Pattern Recognition, 210-217, DOI 10.1109/ CVPR.2009.5206763, Jan 2009. 13. Yang, S.Huang, N.Rao M, An automatic hybrid Method For Retinal Blood Vessel Extraction, International Journal of Applied Math. Comput. Sci,2008, Vol18,No.3, pp 399-407,2008 1711