Automatic Drusen Detection from Digital Retinal Images: AMD Prevention

Size: px
Start display at page:

Download "Automatic Drusen Detection from Digital Retinal Images: AMD Prevention"

Transcription

1 Automatic Drusen Detection from Digital Retinal Images: AMD Prevention B. Remeseiro, N. Barreira, D. Calvo, M. Ortega and M. G. Penedo VARPA Group, Dept. of Computer Science, Univ. A Coruña (Spain) {bremeseiro, nbarreira, dcalvo, mortega, mgpenedo}@udc.es Abstract. The age-related macular degeneration (AMD) is the main cause of blindness among people over 50 years in developed countries and there are 150 million people affected worlwide. This disease can lead to severe loss central vision and adversely affect the patient s quality of life. The appearance of drusen is associated with the early AMD, so we proposed a top-down methodology to detect drusen in initial stages to prevent AMD. The proposed methodology has several stages where the key issues are the detection and characterization of suspect areas. We test our method with a set of images, obtaining a system with a high sensitivity in the localization of drusen, not just fake injuries. Key words: drusen, AMD, retinal images, template matching, normalized cross correlation, region growing. 1 Introduction The age-related macular degeneration (AMD) [1] is a degenerative eye disease that affects the central vision. This kind of vision is needed to perform daily tasks such as reading, sewing or driving. The AMD causes significant visual impact to the center of the retina, the macula, and therefore the center of the visual field. In 1995, an international classification was proposed by Bird, using color eye fundus images. The AMD was defined as a degenerative disease that affects people over 50 years old and has two stages: early and late AMD. The former is characterized by the presence of drusen and pigment epithelium abnormalities. The later includes the late, atrophic and humid injuries. In this sense, early detection of drusen is useful in the diagnose and treatment of patients that suffer AMD. Therefore, the development of a screening system based on drusen could prevent the AMD. Drusen, in their early stages, are circular, small and white structures which can be observed in retinal images as Fig. 1 shows. There are some works in the literature that try to detect drusen, but none of them is focused on initial stages. For example, the work proposed by Sbeh et al. [2] tries to segment drusen using an adaptative algorithm based on morphological operations. Rapantzikos and Zervakis [3] developed a segmentation technique called HALT (Histogram-based Adaptive Local Thresholding) with the aim of

2 (a) (b) Fig. 1. Examples of drusen: (a) shows a retinal image with two drusen in the macular area and (b) shows the zoom in this area (contrast enhanced). detecting drusen in eye fundus images by extracting useful information. In 2003, Brandon and Hoover [4] proposed a multilevel algorithm to detect drusen in retinal images without human supervision. One year later, the work proposed by Mora et al. [5] uses classical image processing techniques to detect and model drusen. In 2006, Garg et al. [6] proposed two different methods to detect, count and segment drusen in retinal images, without human interaction or supervision. Both of them use morphological characteristics of drusen, such as texture and their 3D profiles. Another work, the proposed by Niemeijer et al. [7], presents a system that allows to detect exudates and cotton-wool spots in color fundus images and distinguish them from drusen. All mentioned works have one thing in common: they detect drusen at any stage, but they do not provide results on their performance in initial stages. However, only drusen detected at early stages can be used to prevent AMD. Thus this work is focused on the automatic detection and characterization of drusen in early stages. We propose a top-down methodology to detect circular diffuse spot with a maximun diameter of 125µm, using techniques such as template matching and region growing. This methodology can be integrated in a screening system for AMD diagnose. This paper is organised as follows: in section 2 a description of the five stages methodology is presented. Section 3 shows the experimental results and validation obtained using a set of retinal images provided by ophthalmologists. Finally, section 4 provides some discussion and conclusion. 2 Methodology The proposed methodology consists of five stages (see Fig. 2). The first stage involves the acquisition of the retinal image. The second stage entails the extraction of the green channel of the colour image. In the third stage, the search area

3 is restricted to the inside of the ETDRS (Early Treatment Diabetic Retinophaty Study) protocol grille. The fourth stage tries to localize the areas of the image which are suspected of being drusen using the template matching technique. Finally, the suspect areas are segmented using the region growing technique and filtered to rule out false lesions. In the following sections, all these stages will be explained in detail. Fig. 2. Methodology general chart 2.1 Acquisition of the Retinal Image The acquisition of the image is the first step towards the drusen detection. All of the images used in this work have been acquired with the F F 450 plus F undus Camera, a 2 Mpx camera. They are colour fundus images, in PPM format and their resolution is pixels. 2.2 Extraction of the Green Channel The green channel of the colour image contains the most of the image information since its contrast is greater than the contrast of the other RGB channels. This is due to the optical characteristics of the eye and the nature of the cameras. the blue channel of the image contains little information while the red channel is too saturated. For this reason, the green channel of the image is extracted and it will be used in next stages. Other works also use the green channel according to the same reasoning [4, 6, 7]. 2.3 Localization of the Search Area The ETDRS [8] is a standard protocol that studies the diabetic retinopathy. The ETDRS protocol grille was initially created to divide the central retina in different areas to the treatment of diabetic people. Nowadays, ophthalmologists use it in other pathologies such as AMD. The drusen outside the grille correspond to a very peripheral area of the vision. In this area, there is neither vision in detail nor colour vision, so the presence of drusen outside the grille has a negligible impact on the visual field. In addition, all of the images are focused on the macula so the peripheral drusen may appear blurred and deformed, distorting, consequently, their analysis. Therefore, the proposed system will detect the drusen inside the grille, so that this area has been called search area. The grille (see Fig. 3) consists of three concentric circumferences focused on the macula. The search area is limited to

4 the area occupied by the grille in order to focus the system on the area of interest. As a result, the drusen are searched in a circumference of 7.2 mm diameter and centered on the macula. The idea proposed by Mariño et al. [9] was used to center the circumference on the macula. Fig. 3. ETDRS protocol grille over a retinal image. 2.4 Detection of the Suspect Areas The detection of the suspect areas is one of the key stages in the proposed methodology. The goal is to identify the regions of the image that might be drusen. It is intended to achieve the fullest possible detection, which means high sensitivity. The technique used is the template matching [10]. Its adaptation to the suspect area problem entails the creation of a template that represents a drusen and the search for parts of the retinography that resemble the template. The similarity measurement used is the normalized cross correlation [10], so the output image will have pixels with values between -1 and 1. A threshold δ is selected to determine which are the suspect areas. Drusen have a circular shape with fuzzy edges and a whitish colour. Their intensity is variable, but always higher than the surrounding retinal tissue. Regarding the size, we only consider those drusen with a maximum diameter of 125µm. Due to the drusen characteristics, two different templates were tested: circular templates and gaussian templates. As drusen have different sizes, a multiscale approach was used. The experimental results obtained with four test images proved that the most suitable configuration includes two gaussian templates with radius 3 and 4 and square window sizes 9 and 15, respectively. The threshold was set to δ = Figure 4 shows the results which were obtained in a retinal image after applying this stage, using the above-mentioned parameters.

5 Fig. 4. Results after the detection of the suspect areas. Two drusen were detected (upper circle), which means 100% sensitivity, and one false positive was included in the set of suspect areas (lower circle). 2.5 Characterization of the Suspect Areas In the previous stage, all the suspect areas, this is, the candidate areas to contain drusen, were identified. The goal was to get a high sensitivity despite of the number of false positives. In this stage, the areas previously detected are analyzed to determine if they are drusen. This way, the number of false positives is reduced. This stage has two important steps: the segmentation of the suspect areas, to achieve a good fit of the candidate regions, and the region filtering, to reduce the number of false positives. The goal of the segmentation process is to distinguish the different regions the suspect areas contain. In order to achieve a good fit of the candidate areas, the technique used is region growing [11]. This technique involves three steps: the selection of the center of mass or seed associated with each region, the definition of a criterion to include a pixel in a region and, finally, the creation of a stopping criterion to finish the segmentation. In our case, the seed for each suspect area is the point of maximum correlation for each region: R i, S i = p j /corr(p j ) = max{corr(p k ), p k R i }, i = 1... N. (1) where R i is the i th region of the N suspect areas of this stage, S i is the seed of the R i region and p j is the j th pixel of the R i which correlation value is the maximum of this region. Moreover, a pixel is added to a region if it exceeds a threshold ϑ and is neighbor of another pixel that belongs to that region. Since lighting is not constant throughout the retina this threshold is computed for each suspect area using the next equation:

6 ϑ(x, y) = I bg (x, y) α(i bg (x, y) I(x, y)). (2) where I is the input image, I bg is the input image after applying a median filter and α is a weighting variable, with values between 0 and 1. In this work α = 0.6. The process finishes when no more pixels can be added to any existing region or if the region exceeds the maximum size ζ = 150 pixels. After the segmentation process, we have a vector which contains all the candidate areas. This vector is processed to analyze the candidate areas and do the region filtering process. In this case, four properties were studied to reduce the number of false positives: size, circularity, intensity and correlation mean. The first two do not work because the segmented structures are very tiny. Also, the third one does not work due to the high variability in the tonality of the images. This way, the correlation mean is analyzed in order to rule out false lesions from the suspect areas. The idea is to create a correlation mean filter to eliminate the candidates which pixels do not show continuity with respect to their correlation value. The average of the correlation values of the pixels in each region is computed as follows: R i, ν(r i ) = 1 m m corr(p j ), p j R i, i = 1... N. (3) j=1 where R i is the i th region of the N segmented areas, ν(r i ) is the correlation average value of R i and p j is the j th pixel of the m pixels belonging to this group. Then, the candidates which average value does not exceed a threshold ϱ are eliminated. We have set ϱ = 0.35 after several experiments with four test images. Figure 5 shows the results which were obtained in the same retinal image than in the previous stage, after applying the segmentation process and the region filtering process, using the above-mentioned parameters. 3 Results The proposed methodology was tested with a set of images in PPM format obtained with a F F 450 plus F undus Camera. Two different experiments have been used to prove the accuracy of the proposed methodology. The first experiment consists of two test benchs. The first bench has four images with 11 drusen in initial stages marked by ophtalmologists and the second one has five healthy retinal images. We had obtained a sensitivity of 82% whereas the number of false positives is close to 0 (see Table 1). The second experiment arises due to the problem to evaluate the method, because of the shortage of images showing drusen in incipient stages. This experiment consists of two test benchs too. The first bench has four images with 11 drusen in initial stages and 13 drusen added artificially. The second bench has five healthy retinal images with 16 drusen added artificially. The method to add

7 Fig. 5. Results after characterizing the suspect areas: two drusen detected (inside the circle), which means 100% sensitiviy, and no false positive. Bench 1 Bench 2 TP FN FP Average FP Sensitivity Average FP % 0.6 Table 1. Final results for the proposed methodology in the first experiment drusen artificially is based on inserting real drusen in retinal images by means of a cloning process. The same process is used by specialists. We had obtained results similar to the previous experiment (see Table 2). Bench 1 Artificial drusen Real drusen Average FP Sensitivity % Bench 2 Artificial drusen Real drusen Average FP Sensitivity % Table 2. Final results for the proposed methodology in the second experiment These results can not be compared with previous work since there is no previous work devoted to detect drusen in initial stages. Also, it is too difficult to do a thorough testing process because of the shortage of images. Anyway, we have got a high sensitivity, more than 82%, and the number of false positives is practically zero.

8 4 Conclusions and Future Research In this work a method for the detection of drusen in initial stages has been presented, to support ophthalmologists in the prevention of the AMD. This method does a first detection of suspect areas and a later classification of them. We have developed a system that is able to automatically detect drusen in retinal images with a high sensitivity (over 80%) and without hardly detecting false lesions. The proposed system could be integrated into a screening system to prevent the AMD. This system could be improved in several ways. First, new drusen properties could be used to create new filters to eliminate spurious injuries. Furthermore, we could use aditional information by means of other kind of images, such as OCT images. It would be very important to create a database with images containing drusen marked by specialists in order to do a more exhaustive testing process. References 1. : Age-Related Macular Degeneration (AMD), National Eye Institute. Website 2. Sbeh, Z.B., Cohen, L.D., Mimoun, G., Coscas, G., Soubrane, G.: An adaptive contrast method for segmentation of drusen. In: ICIP 97: Proceedings of the 1997 International Conference on Image Processing (ICIP 97) 3-Volume Set-Volume 1, Washington, DC, USA, IEEE Computer Society (1997) Rapantzikos, K., Zervakis, M.: Nonlinear enhancement and segmentation Algorithm for the Detection of Age-related Macular Degeneration (AMD) in Human Eye s Retina, Proceedings of ICIP 2001, Thessaloniki, Greece, October 2001 (2001) 4. Brandon, L., Hoover, A.: Drusen Detection in a Retinal Image Using Multi-level Analysis. In: MICCAI (1). (2003) Mora, A., Vieira, P., Fonseca, J.: Drusen Deposits on Retina Images: Detection and Modeling. In: MEDSIP-2004, Malta (2004) 6. Garg, S., Sivasway, J., Joshi, G.D.: Automatic Drusen Detection from Colour Retinal Images. In: Proc. of Indian Conference on Medical Informatics and Telemedicine (ICMIT), Kharagpur (2006) Niemeijer, M., van Ginneken, B., Russel, S., Suttorp-Schulten, M., Abramoff, M.: Automated detection and differentiation of Drusen, exudates, and cotton-wool spots in digital color fundus photographs for early diagnosis of Diabetic Retinopathy. Investigative Ophthalmology & Visual Science 48 (2007) : Early Treatment Diabetic Retinopathy Study (ETDRS), National Eye Institute. Website 9. Mariño, C., Pena, S., Penedo, M.G., Rouco, J., Barja, J.M.: Macula precise localization using digital retinal angiographies. In: ICCOMP 07: Proceedings of the 11th WSEAS International Conference on Computers, Stevens Point, Wisconsin, USA, World Scientific and Engineering Academy and Society (WSEAS) (2007) Russ, J.C.: The image processing handbook (3rd ed.). CRC Press, Inc., Boca Raton, FL, USA (1999) 11. González, R., Woods, R.: Digital image processing. (1992)

Detection of Abnormalities of Retina Due to Diabetic Retinopathy and Age Related Macular Degeneration Using SVM

Detection of Abnormalities of Retina Due to Diabetic Retinopathy and Age Related Macular Degeneration Using SVM Science Journal of Circuits, Systems and Signal Processing 2016; 5(1): 1-7 http://www.sciencepublishinggroup.com/j/cssp doi: 10.11648/j.cssp.20160501.11 ISSN: 2326-9065 (Print); ISSN: 2326-9073 (Online)

More information

Detection Of Red Lesion In Diabetic Retinopathy Using Adaptive Thresholding Method

Detection Of Red Lesion In Diabetic Retinopathy Using Adaptive Thresholding Method Detection Of Red Lesion In Diabetic Retinopathy Using Adaptive Thresholding Method Deepashree Devaraj, Assistant Professor, Instrumentation Department RVCE Bangalore. Nagaveena M.Tech Student, BMSP&I,

More information

DETECTION OF DIABETIC MACULOPATHY IN HUMAN RETINAL IMAGES USING MORPHOLOGICAL OPERATIONS

DETECTION OF DIABETIC MACULOPATHY IN HUMAN RETINAL IMAGES USING MORPHOLOGICAL OPERATIONS Online Journal of Biological Sciences 14 (3): 175-180, 2014 ISSN: 1608-4217 2014 Vimala and Kajamohideen, This open access article is distributed under a Creative Commons Attribution (CC-BY) 3.0 license

More information

ISSN (Online): International Journal of Advanced Research in Basic Engineering Sciences and Technology (IJARBEST) Vol.4 Issue.

ISSN (Online): International Journal of Advanced Research in Basic Engineering Sciences and Technology (IJARBEST) Vol.4 Issue. This work by IJARBEST is licensed under a Creative Commons Attribution 4.0 International License. Available at https://www.ijarbest.com ISSN (Online): 2456-5717 SVM based Diabetic Retinopthy Classification

More information

Implementation of Automatic Retina Exudates Segmentation Algorithm for Early Detection with Low Computational Time

Implementation of Automatic Retina Exudates Segmentation Algorithm for Early Detection with Low Computational Time www.ijecs.in International Journal Of Engineering And Computer Science ISSN: 2319-7242 Volume 5 Issue 10 Oct. 2016, Page No. 18584-18588 Implementation of Automatic Retina Exudates Segmentation Algorithm

More information

1 Introduction. Fig. 1 Examples of microaneurysms

1 Introduction. Fig. 1 Examples of microaneurysms 3rd International Conference on Multimedia Technology(ICMT 2013) Detection of Microaneurysms in Color Retinal Images Using Multi-orientation Sum of Matched Filter Qin Li, Ruixiang Lu, Shaoguang Miao, Jane

More information

A Bag of Words Approach for Discriminating between Retinal Images Containing Exudates or Drusen

A Bag of Words Approach for Discriminating between Retinal Images Containing Exudates or Drusen A Bag of Words Approach for Discriminating between Retinal Images Containing Exudates or Drusen by M J J P Van Grinsven, Arunava Chakravarty, Jayanthi Sivaswamy, T Theelen, B Van Ginneken, C I Sanchez

More information

Automatic Screening of Fundus Images for Detection of Diabetic Retinopathy

Automatic Screening of Fundus Images for Detection of Diabetic Retinopathy Volume 02 No.1, Issue: 03 Page 100 International Journal of Communication and Computer Technologies Automatic Screening of Fundus Images for Detection of Diabetic Retinopathy 1 C. Sundhar, 2 D. Archana

More information

Diagnosis System for Diabetic Retinopathy to Prevent Vision Loss

Diagnosis System for Diabetic Retinopathy to Prevent Vision Loss Applied Medical Informatics Original Research Vol. 33, No. 3 /2013, pp: 1-11 Diagnosis System for Diabetic Retinopathy to Prevent Vision Loss Siva Sundhara Raja DHANUSHKODI 1,*, and Vasuki MANIVANNAN 2

More information

A Bit Plane based Filtering Technique for Drusen in Age-related Macular Degeneration

A Bit Plane based Filtering Technique for Drusen in Age-related Macular Degeneration Indian Journal of Science and Technology, Vol 9(48), DOI: 10.17485/ijst/2016/v9i48/103958, December 2016 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 A Bit Plane based Filtering Technique for Drusen

More information

ROI DETECTION AND VESSEL SEGMENTATION IN RETINAL IMAGE

ROI DETECTION AND VESSEL SEGMENTATION IN RETINAL IMAGE ROI DETECTION AND VESSEL SEGMENTATION IN RETINAL IMAGE F. Sabaz a, *, U. Atila a a Karabuk University, Dept. of Computer Engineering, 78050, Karabuk, Turkey - (furkansabaz, umitatila)@karabuk.edu.tr KEY

More information

Detection of Glaucoma and Diabetic Retinopathy from Fundus Images by Bloodvessel Segmentation

Detection of Glaucoma and Diabetic Retinopathy from Fundus Images by Bloodvessel Segmentation International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 8958, Volume-5, Issue-5, June 2016 Detection of Glaucoma and Diabetic Retinopathy from Fundus Images by Bloodvessel Segmentation

More information

7.1 Grading Diabetic Retinopathy

7.1 Grading Diabetic Retinopathy Chapter 7 DIABETIC RETINOPATHYGRADING -------------------------------------------------------------------------------------------------------------------------------------- A consistent approach to the

More information

A Novel Method for Automatic Optic Disc Elimination from Retinal Fundus Image Hetal K 1

A Novel Method for Automatic Optic Disc Elimination from Retinal Fundus Image Hetal K 1 IJSRD - International Journal for Scientific Research & Development Vol. 3, Issue 01, 2015 ISSN (online): 2321-0613 A Novel Method for Automatic Optic Disc Elimination from Retinal Fundus Image Hetal K

More information

Detection of Diabetic Retinopathy using Kirsch Edge Detection and Watershed Transformation Algorithm

Detection of Diabetic Retinopathy using Kirsch Edge Detection and Watershed Transformation Algorithm ISSN: 2454-132X (Volume1, Issue2) Detection of Diabetic Retinopathy using Kirsch Edge Detection and Watershed Transformation Algorithm Divya SN * Department of Computer Science and Engineering, Sri Sairam

More information

Automated Assessment of Diabetic Retinal Image Quality Based on Blood Vessel Detection

Automated Assessment of Diabetic Retinal Image Quality Based on Blood Vessel Detection Y.-H. Wen, A. Bainbridge-Smith, A. B. Morris, Automated Assessment of Diabetic Retinal Image Quality Based on Blood Vessel Detection, Proceedings of Image and Vision Computing New Zealand 2007, pp. 132

More information

Diabetic Retinopathy Classification using SVM Classifier

Diabetic Retinopathy Classification using SVM Classifier Diabetic Retinopathy Classification using SVM Classifier Vishakha Vinod Chaudhari 1, Prof. Pankaj Salunkhe 2 1 PG Student, Dept. Of Electronics and Telecommunication Engineering, Saraswati Education Society

More information

Automated Detection Of Glaucoma & D.R From Eye Fundus Images

Automated Detection Of Glaucoma & D.R From Eye Fundus Images Reviewed Paper Volume 2 Issue 12 August 2015 International Journal of Informative & Futuristic Research ISSN (Online): 2347-1697 Automated Detection Of Glaucoma & D.R Paper ID IJIFR/ V2/ E12/ 016 Page

More information

SEVERITY GRADING FOR DIABETIC RETINOPATHY

SEVERITY GRADING FOR DIABETIC RETINOPATHY SEVERITY GRADING FOR DIABETIC RETINOPATHY Mr.M.Naveenraj 1, K.Haripriya 2, N.Keerthana 3, K.Mohana Priya 4, R.Mounika 5 1,2,3,4,5 Department of ECE,Kathir College of Engineering Abstract: This paper presents

More information

Design and Implementation System to Measure the Impact of Diabetic Retinopathy Using Data Mining Techniques

Design and Implementation System to Measure the Impact of Diabetic Retinopathy Using Data Mining Techniques International Journal of Innovative Research in Electronics and Communications (IJIREC) Volume 4, Issue 1, 2017, PP 1-6 ISSN 2349-4042 (Print) & ISSN 2349-4050 (Online) DOI: http://dx.doi.org/10.20431/2349-4050.0401001

More information

Study And Development Of Digital Image Processing Tool For Application Of Diabetic Retinopathy

Study And Development Of Digital Image Processing Tool For Application Of Diabetic Retinopathy Study And Development O Digital Image Processing Tool For Application O Diabetic Retinopathy Name: Ms. Jyoti Devidas Patil mail ID: jyot.physics@gmail.com Outline 1. Aims & Objective 2. Introduction 3.

More information

A Survey on Localizing Optic Disk

A Survey on Localizing Optic Disk International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 14 (2014), pp. 1355-1359 International Research Publications House http://www. irphouse.com A Survey on Localizing

More information

Comparative Study on Localization of Optic Disc from RGB Fundus Images

Comparative Study on Localization of Optic Disc from RGB Fundus Images Comparative Study on Localization of Optic Disc from RGB Fundus Images Mohammed Shafeeq Ahmed 1, Dr. B. Indira 2 1 Department of Computer Science, Gulbarga University, Kalaburagi, 585106, India 2 Department

More information

Intelligent Diabetic Retinopathy Diagnosis in Retinal Images

Intelligent Diabetic Retinopathy Diagnosis in Retinal Images Journal of Advances in Computer Research Quarterly ISSN: 2008-6148 Sari Branch, Islamic Azad University, Sari, I.R.Iran (Vol. 4, No. 3, August 2013), Pages: 103-117 www.jacr.iausari.ac.ir Intelligent Diabetic

More information

International Journal of Engineering Research and General Science Volume 6, Issue 2, March-April, 2018 ISSN

International Journal of Engineering Research and General Science Volume 6, Issue 2, March-April, 2018 ISSN cernment of Retinal Anomalies in Fundus Images for Diabetic Retinopathy Shiny Priyadarshini J 1, Gladis D 2 Madras Christian College 1, Presidency College 2 shinymcc02@gmail.com Abstract Retinal abnormalities

More information

New algorithm for detecting smaller retinal blood vessels in fundus images

New algorithm for detecting smaller retinal blood vessels in fundus images New algorithm for detecting smaller retinal blood vessels in fundus images Robert LeAnder*, Praveen I. Bidari Tauseef A. Mohammed, Moumita Das, Scott E. Umbaugh Department of Electrical and Computer Engineering,

More information

1 Introduction. Abstract: Accurate optic disc (OD) segmentation and fovea. Keywords: optic disc segmentation, fovea detection.

1 Introduction. Abstract: Accurate optic disc (OD) segmentation and fovea. Keywords: optic disc segmentation, fovea detection. Current Directions in Biomedical Engineering 2017; 3(2): 533 537 Caterina Rust*, Stephanie Häger, Nadine Traulsen and Jan Modersitzki A robust algorithm for optic disc segmentation and fovea detection

More information

ACHIKO-D350: A dataset for early AMD detection and drusen segmentation

ACHIKO-D350: A dataset for early AMD detection and drusen segmentation ACHIKO-D350: A dataset for early AMD detection and drusen segmentation Huiying Liu 1, Yanwu Xu 1, Damon W. K. Wong 1, Augustinus Laude 2, Tock Han Lim 2, and Jiang Liu 1 1 Institute for Infocomm Research,

More information

AN APPROACH FOR IRIS SEGMENTATION AND MACULOPATHY DETECTION AND GRADING OF DIABETIC RETINAL IMAGES. Mahaboob Shaik

AN APPROACH FOR IRIS SEGMENTATION AND MACULOPATHY DETECTION AND GRADING OF DIABETIC RETINAL IMAGES. Mahaboob Shaik ARTICLE AN APPROACH FOR IRIS SEGMENTATION AND MACULOPATHY DETECTION AND GRADING OF DIABETIC RETINAL IMAGES Mahaboob Shaik Dept of ECE, JJT University, Jhunjhunu, Rajasthan, INDIA ABSTRACT Diabetic macular

More information

EXTRACTION OF RETINAL BLOOD VESSELS USING IMAGE PROCESSING TECHNIQUES

EXTRACTION OF RETINAL BLOOD VESSELS USING IMAGE PROCESSING TECHNIQUES EXTRACTION OF RETINAL BLOOD VESSELS USING IMAGE PROCESSING TECHNIQUES T.HARI BABU 1, Y.RATNA KUMAR 2 1 (PG Scholar, Dept. of Electronics and Communication Engineering, College of Engineering(A), Andhra

More information

A complex system for the automatic screening of diabetic retinopathy

A complex system for the automatic screening of diabetic retinopathy A complex system for the automatic screening of diabetic retinopathy András Hajdu Faculty of Informatics, University of Debrecen Hungary International Medical Informatics and Telemedicine IMIT 2014, 13-14

More information

Computer Aided Approach for Detection of Age Related Macular Degeneration from Retinal Fundus Images

Computer Aided Approach for Detection of Age Related Macular Degeneration from Retinal Fundus Images Computer Aided Approach for Detection of Age Related Macular Degeneration from Retinal Fundus Images VyshakhAsokan PG student, Dept of Biomedical Engineering, Noorul Islam University, Kumaracoil, Tamil

More information

Research Article. Automated grading of diabetic retinopathy stages in fundus images using SVM classifer

Research Article. Automated grading of diabetic retinopathy stages in fundus images using SVM classifer Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2016, 8(1):537-541 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Automated grading of diabetic retinopathy stages

More information

A New Approach for Detection and Classification of Diabetic Retinopathy Using PNN and SVM Classifiers

A New Approach for Detection and Classification of Diabetic Retinopathy Using PNN and SVM Classifiers IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 19, Issue 5, Ver. I (Sep.- Oct. 2017), PP 62-68 www.iosrjournals.org A New Approach for Detection and Classification

More information

REVIEW OF METHODS FOR DIABETIC RETINOPATHY DETECTION AND SEVERITY CLASSIFICATION

REVIEW OF METHODS FOR DIABETIC RETINOPATHY DETECTION AND SEVERITY CLASSIFICATION REVIEW OF METHODS FOR DIABETIC RETINOPATHY DETECTION AND SEVERITY CLASSIFICATION Madhura Jagannath Paranjpe 1, M N Kakatkar 2 1 ME student, Department of Electronics and Telecommunication, Sinhgad College

More information

FEATURE EXTRACTION OF RETINAL IMAGE FOR DIAGNOSIS OF ABNORMAL EYES

FEATURE EXTRACTION OF RETINAL IMAGE FOR DIAGNOSIS OF ABNORMAL EYES FEATURE EXTRACTION OF RETINAL IMAGE FOR DIAGNOSIS OF ABNORMAL EYES S. Praveenkumar Department of Electronics and Communication Engineering, Saveetha Engineering College, Tamil Nadu, India E-mail: praveenkumarsunil@yahoo.com

More information

RetCAD 1.3.0: White paper

RetCAD 1.3.0: White paper RetCAD 1.3.0: White paper 18 July 2018 Computer aided detection for Age-related Macular Degeneration and Diabetic Retinopathy About this white paper This white paper applies to RetCAD 1.3.0 and describes

More information

Grading System for Diabetic Retinopathy Disease

Grading System for Diabetic Retinopathy Disease Grading System for Diabetic Retinopathy Disease N. D. Salih, Marwan D. Saleh, C. Eswaran, and Junaidi Abdullah Centre for Visual Computing, Faculty of Computing and Informatics, Multimedia University,

More information

A Review on Automated Detection and Classification of Diabetic Retinopathy

A Review on Automated Detection and Classification of Diabetic Retinopathy A Review on Automated Detection and Classification of Diabetic Retinopathy Deepa R. Dept. of Computer Applications College of Engineering Vadakara deepashaaju@gmail.com Dr.N.K.Narayanan Dept. of IT College

More information

A Composite Architecture for an Automatic Detection of Optic Disc in Retinal Imaging

A Composite Architecture for an Automatic Detection of Optic Disc in Retinal Imaging A Composite Architecture for an Automatic Detection of Optic Disc in Retinal Imaging LEONARDA CARNIMEO, ANNA CINZIA BENEDETTO Dipartimento di Elettrotecnica ed Elettronica Politecnico di Bari Via E.Orabona,

More information

Artery/vein Classification of Blood Vessel Tree in Retinal Imaging

Artery/vein Classification of Blood Vessel Tree in Retinal Imaging Artery/vein Classification of Blood Vessel Tree in Retinal Imaging Joaquim de Moura 1, Jorge Novo 1, Marcos Ortega 1, Noelia Barreira 1 and Pablo Charlón 2 1 Departamento de Computación, Universidade da

More information

Detection of Glaucoma using Cup-to-Disc Ratio and Blood Vessels Orientation

Detection of Glaucoma using Cup-to-Disc Ratio and Blood Vessels Orientation International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue1 ISSN : 2456-3307 Detection of Glaucoma using Cup-to-Disc Ratio and

More information

Analysis of Diabetic Retinopathy from the Features of Color Fundus Images using Classifiers

Analysis of Diabetic Retinopathy from the Features of Color Fundus Images using Classifiers Analysis of Diabetic Retinopathy from the Features of Color Fundus Images using Classifiers Gandhimathi. K 1, Ponmathi. M 2, Arulaalan. M 3 and Samundeeswari. P 4 1,2 Assitant Professor/ CSE 3 Associate

More information

Automatic Detection of Age-related Macular Degeneration from Retinal Images

Automatic Detection of Age-related Macular Degeneration from Retinal Images Automatic Detection of Age-related Macular Degeneration from Retinal Images 1 R. Manjula Sri, 2 Ch.Madhubabu, 3 K.M.M.Rao 1,2 Department of EIE, VNR Vignana Jyothi IET, Hyderabad, India. 3 Department of

More information

International Journal of Advance Engineering and Research Development EARLY DETECTION OF GLAUCOMA USING EMPIRICAL WAVELET TRANSFORM

International Journal of Advance Engineering and Research Development EARLY DETECTION OF GLAUCOMA USING EMPIRICAL WAVELET TRANSFORM Scientific Journal of Impact Factor (SJIF): 4.72 International Journal of Advance Engineering and Research Development Volume 5, Issue 1, January -218 e-issn (O): 2348-447 p-issn (P): 2348-646 EARLY DETECTION

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY 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

More information

Automated Drusen Detection Technique for Age-Related Macular Degeneration

Automated Drusen Detection Technique for Age-Related Macular Degeneration VOLUME 2 ISSUE 1 Automated Drusen Detection Technique for Age-Related Macular Degeneration 1 Kajal Kumari and 2 Deepti Mittal Electrical and Instrumentation Engineering Department, Thapar University, Patiala

More information

EXUDATES DETECTION FROM DIGITAL FUNDUS IMAGE OF DIABETIC RETINOPATHY

EXUDATES DETECTION FROM DIGITAL FUNDUS IMAGE OF DIABETIC RETINOPATHY EXUDATES DETECTION FROM DIGITAL FUNDUS IMAGE OF DIABETIC RETINOPATHY Namrata 1 and Shaveta Arora 2 1 Department of EECE, ITM University, Gurgaon, Haryana, India. 2 Department of EECE, ITM University, Gurgaon,

More information

Detection of Hard Exudates from Diabetic Retinopathy Images using Fuzzy Logic R.H.N.G. Ranamuka and R.G.N. Meegama

Detection of Hard Exudates from Diabetic Retinopathy Images using Fuzzy Logic R.H.N.G. Ranamuka and R.G.N. Meegama Detection of Hard Exudates from Diabetic Retinopathy Images using Fuzzy Logic R.H.N.G. Ranamuka and R.G.N. Meegama Abstract Diabetic retinopathy, that affects the blood vessels of the retina, is considered

More information

Age-related Macular Degeneration Screening using Data Mining Approaches

Age-related Macular Degeneration Screening using Data Mining Approaches 2013 First International Conference on Artificial Intelligence, Modelling & Simulation Age-related Macular Degeneration Screening using Data Mining Approaches Mohd Hanafi Ahmad Hijazi, Frans Coenen and

More information

Automatic Early Diagnosis of Diabetic Retinopathy Using Retina Fundus Images

Automatic Early Diagnosis of Diabetic Retinopathy Using Retina Fundus Images EUROPEAN ACADEMIC RESEARCH Vol. II, Issue 9/ December 2014 ISSN 2286-4822 www.euacademic.org Impact Factor: 3.1 (UIF) DRJI Value: 5.9 (B+) Automatic Early Diagnosis of Diabetic Retinopathy Using Retina

More information

AUTOMATIC DIABETIC RETINOPATHY DETECTION USING GABOR FILTER WITH LOCAL ENTROPY THRESHOLDING

AUTOMATIC DIABETIC RETINOPATHY DETECTION USING GABOR FILTER WITH LOCAL ENTROPY THRESHOLDING AUTOMATIC DIABETIC RETINOPATHY DETECTION USING GABOR FILTER WITH LOCAL ENTROPY THRESHOLDING MAHABOOB.SHAIK, Research scholar, Dept of ECE, JJT University, Jhunjhunu, Rajasthan, India Abstract: The major

More information

Morphological Segmentation of Blood Vessels in Retinal Image

Morphological Segmentation of Blood Vessels in Retinal Image Morphological of Blood Vessels in Retinal Image Prof. Manjusha S. Borse 1 1 Department of Electronics & Telecommunication, Savitribai Phule Pune University, Late G. N. Sapkal COE Nashik, Maharashtra 422213,

More information

PROCEEDINGS OF SPIE. Automated microaneurysm detection method based on double ring filter in retinal fundus images

PROCEEDINGS OF SPIE. Automated microaneurysm detection method based on double ring filter in retinal fundus images PROCEEDINGS OF SPIE SPIEDigitalLibrary.org/conference-proceedings-of-spie Automated microaneurysm detection method based on double ring filter in retinal fundus images Atsushi Mizutani, Chisako Muramatsu,

More information

IMPROVEMENT OF AUTOMATIC HEMORRHAGES DETECTION METHODS USING SHAPES RECOGNITION

IMPROVEMENT OF AUTOMATIC HEMORRHAGES DETECTION METHODS USING SHAPES RECOGNITION Journal of Computer Science 9 (9): 1205-1210, 2013 ISSN: 1549-3636 2013 doi:10.3844/jcssp.2013.1205.1210 Published Online 9 (9) 2013 (http://www.thescipub.com/jcs.toc) IMPROVEMENT OF AUTOMATIC HEMORRHAGES

More information

AUTOMATIC DETECTION OF EXUDATES IN RETINAL IMAGES USING NEURAL NETWORK

AUTOMATIC DETECTION OF EXUDATES IN RETINAL IMAGES USING NEURAL NETWORK AUTOMATIC DETECTION OF EXUDATES IN RETINAL IMAGES USING NEURAL NETWORK FLÁVIO ARAÚJO, RODRIGO VERAS, ANDRÉ MACEDO, FÁTIMA MEDEIROS Department of Computing Federal University of Piauí Teresina, Piauí, Brazil

More information

Detection of Diabetic Retinopathy by Iterative Vessel Segmentation from Fundus Images

Detection of Diabetic Retinopathy by Iterative Vessel Segmentation from Fundus Images Detection of Diabetic Retinopathy by Iterative Vessel Segmentation from Fundus Images Shweta Patil 1, L.S. Admuthe 2 1Mtech Student, Dept of Electronics Engineering, DKTE Society s Textile & Engineering

More information

Extraction of Blood Vessels and Recognition of Bifurcation Points in Retinal Fundus Image

Extraction of Blood Vessels and Recognition of Bifurcation Points in Retinal Fundus Image International Journal of Research Studies in Science, Engineering and Technology Volume 1, Issue 5, August 2014, PP 1-7 ISSN 2349-4751 (Print) & ISSN 2349-476X (Online) Extraction of Blood Vessels and

More information

A Survey on Screening of Diabetic Retinopathy

A Survey on Screening of Diabetic Retinopathy International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue 3 ISSN : 2456-3307 A Survey on Screening of Diabetic Retinopathy Amrita

More information

CHAPTER 8 EVALUATION OF FUNDUS IMAGE ANALYSIS SYSTEM

CHAPTER 8 EVALUATION OF FUNDUS IMAGE ANALYSIS SYSTEM CHAPTER 8 EVALUATION OF FUNDUS IMAGE ANALYSIS SYSTEM Diabetic retinopathy is very common retinal disease associated with diabetes. Efforts to prevent diabetic retinopathy though have yielded some results;

More information

Comparative Study of Classifiers for Diagnosis of Microaneurysm

Comparative Study of Classifiers for Diagnosis of Microaneurysm International Journal of Computational Intelligence Research ISSN 0973-1873 Volume 12, Number 2 (2016), pp. 139-148 Research India Publications http://www.ripublication.com Comparative Study of Classifiers

More information

DETECTION OF RETINAL DISEASE BY LOCAL BINARY PATTERN

DETECTION OF RETINAL DISEASE BY LOCAL BINARY PATTERN Volume 119 No. 15 2018, 2577-2585 ISSN: 1314-3395 (on-line version) url: http://www.acadpubl.eu/hub/ http://www.acadpubl.eu/hub/ DETECTION OF RETINAL DISEASE BY LOCAL BINARY PATTERN N.P. Jeyashree [1],

More information

SEGMENTATION OF MACULAR LAYERS IN OCT DATA OF TOPOLOGICALLY DISRUPTED MACULA

SEGMENTATION OF MACULAR LAYERS IN OCT DATA OF TOPOLOGICALLY DISRUPTED MACULA SEGMENTATION OF MACULAR LAYERS IN OCT DATA OF TOPOLOGICALLY DISRUPTED MACULA Athira S C 1, Reena M Roy 2 1 P G Scholar, L.B.S Institute of Technology for women Poojappura Trivandrum, 2 Assistant Professor,

More information

VOTING BASED AUTOMATIC EXUDATE DETECTION IN COLOR FUNDUS PHOTOGRAPHS

VOTING BASED AUTOMATIC EXUDATE DETECTION IN COLOR FUNDUS PHOTOGRAPHS VOTING BASED AUTOMATIC EXUDATE DETECTION IN COLOR FUNDUS PHOTOGRAPHS Pavle Prentašić and Sven Lončarić Image Processing Group, Faculty of Electrical Engineering and Computing, University of Zagreb, Unska

More information

Automatic detection of diabetic retinopathies. Associate Professor Computer Science - UNICAMP Visiting Professor Medical Informatics - UNIFESP

Automatic detection of diabetic retinopathies. Associate Professor Computer Science - UNICAMP Visiting Professor Medical Informatics - UNIFESP Automatic detection of diabetic retinopathies Jacques Wainer (wainer@ic.unicamp.br) Associate Professor Computer Science UNICAMP Visiting Professor Medical Informatics UNIFESP Research team UNICAMP Faculty:

More information

EXTRACT THE BREAST CANCER IN MAMMOGRAM IMAGES

EXTRACT THE BREAST CANCER IN MAMMOGRAM IMAGES International Journal of Civil Engineering and Technology (IJCIET) Volume 10, Issue 02, February 2019, pp. 96-105, Article ID: IJCIET_10_02_012 Available online at http://www.iaeme.com/ijciet/issues.asp?jtype=ijciet&vtype=10&itype=02

More information

Image Processing and Data Mining Techniques in the Detection of Diabetic Retinopathy in Fundus Images

Image Processing and Data Mining Techniques in the Detection of Diabetic Retinopathy in Fundus Images I J C T A, 10(8), 2017, pp. 755-762 International Science Press ISSN: 0974-5572 Image Processing and Data Mining Techniques in the Detection of Diabetic Retinopathy in Fundus Images Payal M. Bante* and

More information

Automatic Arteriovenous Ratio Computation: Emulating the Experts

Automatic Arteriovenous Ratio Computation: Emulating the Experts Automatic Arteriovenous Ratio Computation: Emulating the Experts S. G. Vázquez 1, N. Barreira 1, M. G. Penedo 1, M. Rodriguez-Blanco 2, F. Gómez-Ulla 2, A. González 1, G. Coll de Tuero 3 1 Varpa Group,

More information

Diabetic Retinopathy Detection Using Eye Images

Diabetic Retinopathy Detection Using Eye Images CS365:Artificial Intelligence Course Project Diabetic Retinopathy Detection Using Eye Images Mohit Singh Solanki 12419 mohitss@iitk.ac.in Supervisor: Dr. Amitabha Mukherjee April 18, 2015 Abstract Diabetic

More information

A dynamic approach for optic disc localization in retinal images

A dynamic approach for optic disc localization in retinal images ISSN 2395-1621 A dynamic approach for optic disc localization in retinal images #1 Rutuja Deshmukh, #2 Karuna Jadhav, #3 Nikita Patwa 1 deshmukhrs777@gmail.com #123 UG Student, Electronics and Telecommunication

More information

Automated Blood Vessel Extraction Based on High-Order Local Autocorrelation Features on Retinal Images

Automated Blood Vessel Extraction Based on High-Order Local Autocorrelation Features on Retinal Images Automated Blood Vessel Extraction Based on High-Order Local Autocorrelation Features on Retinal Images Yuji Hatanaka 1(&), Kazuki Samo 2, Kazunori Ogohara 1, Wataru Sunayama 1, Chisako Muramatsu 3, Susumu

More information

OCT Image Analysis System for Grading and Diagnosis of Retinal Diseases and its Integration in i-hospital

OCT Image Analysis System for Grading and Diagnosis of Retinal Diseases and its Integration in i-hospital Progress Report for1 st Quarter, May-July 2017 OCT Image Analysis System for Grading and Diagnosis of Retinal Diseases and its Integration in i-hospital Milestone 1: Designing Annotation tool extraction

More information

Blood Vessel Segmentation for Retinal Images Based on Am-fm Method

Blood Vessel Segmentation for Retinal Images Based on Am-fm Method Research Journal of Applied Sciences, Engineering and Technology 4(24): 5519-5524, 2012 ISSN: 2040-7467 Maxwell Scientific Organization, 2012 Submitted: March 23, 2012 Accepted: April 30, 2012 Published:

More information

CHAPTER - 2 LITERATURE REVIEW

CHAPTER - 2 LITERATURE REVIEW CHAPTER - 2 LITERATURE REVIEW Currently, there is an increasing interest for establishing automatic systems that screens a huge number of people for vision threatening diseases like diabetic retinopathy

More information

AUTOMATIC FUNDUS IMAGE FIELD DETECTION AND QUALITY ASSESSMENT

AUTOMATIC FUNDUS IMAGE FIELD DETECTION AND QUALITY ASSESSMENT AUTOMATIC FUNDUS IMAGE FIELD DETECTION AND QUALITY ASSESSMENT Gajendra Jung Katuwal 1, John Kerekes 1, Rajeev Ramchandran 3, Christye Sisson 2, and Navalgund Rao 1 1 Chester F. Carlson Center for Imaging

More information

ON APPLICATION OF GAUSSIAN KERNEL TO RETINAL BLOOD TRACING

ON APPLICATION OF GAUSSIAN KERNEL TO RETINAL BLOOD TRACING ON APPLICATION OF GAUSSIAN KERNEL TO RETINAL BLOOD TRACING 1 MOHD ASYRAF ZULKIFLEY, 2 AIN NAZARI, 3 SITI KHADIJAH, 4 ADHI HARMOKO SAPUTRO 1, 2, 3 Department of Electrical, Electronic & Systems Engineering,

More information

A Review on Retinal Feature Segmentation Methodologies for Diabetic Retinopathy

A Review on Retinal Feature Segmentation Methodologies for Diabetic Retinopathy IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 19, Issue 2, Ver. I (Mar.-Apr. 2017), PP 01-06 www.iosrjournals.org A Review on Retinal Feature Segmentation

More information

An Approach for Detection of Abnormality and its Severity Classification in Colour Fundus Images

An Approach for Detection of Abnormality and its Severity Classification in Colour Fundus Images An Approach for Detection of Abnormality and its Severity Classification in Colour Fundus Images Nandhini V Post Graduate, Dept of Electronics & Communication Engg., E.G.S Pillay Engineering College, Nagapattinam,

More information

Analyzing Macular Edema In Diabetic Patients

Analyzing Macular Edema In Diabetic Patients International Journal of Computational Engineering Research Vol, 03 Issue, 6 Analyzing Macular Edema In Diabetic Patients Deepika.K.G 1, Prof.Prabhanjan.S 2 1 MTech 4 th Sem, SET, JAIN University 2 Professor,

More information

implications. The most prevalent causes of blindness in the industrialized world are age-related macular degeneration,

implications. The most prevalent causes of blindness in the industrialized world are age-related macular degeneration, ISSN: 0975-766X CODEN: IJPTFI Available Online through Research Article www.ijptonline.com AUTOMATIC LOCALIZATION OF OPTIC DISC AND BLOOD VESSELS USING SELFISH GENE ALGORITHM P.Anita*, F.V.Jayasudha UG

More information

Diabetic Retinopathy using Computer Vision

Diabetic Retinopathy using Computer Vision Diabetic Retinopathy using Computer Vision Netra Yaradoni 1, Manjunath R Raikar 2 M.Tech (CSE), AIET, Moodbidri, India 1 M.Tech, Assistant Professor, Department of CSE, AIET, Moodbidri, India 2 Abstract:

More information

Diabetic Retinopathy-Early Detection Using Image Processing Techniques

Diabetic Retinopathy-Early Detection Using Image Processing Techniques Diabetic Retinopathy-Early Detection Using Image Processing Techniques V.Vijaya Kumari, Department of ECE, V.L.B. Janakiammal College of Engineering and Technology Coimbatore 641 042, India. N.SuriyaNarayanan

More information

Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques

Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques Thomas Walter and Jean-Claude Klein Centre de Morphologie Mathématique,

More information

Extraction of the Retinal Blood Vessels and Detection of the Bifurcation Points

Extraction of the Retinal Blood Vessels and Detection of the Bifurcation Points Extraction of the Retinal Blood Vessels and Detection of the Bifurcation Points Manjiri B. Patwari Institute Of Management Studies & Vivekanand Information technology college campus, Aurangabad (MS), India

More information

Published in A R DIGITECH

Published in A R DIGITECH Localization of Optic Disc in Retinal Fundus Images for Glaucoma and Diabetes Chaitali D. Dhumane*1, Prof. S. B. Patil*2 *1(Student of Electronics & Telecommunication Department, Sinhgad College of Engineering,

More information

Telemedicine Diagnostic Challenges for Diabetic Retinopathy

Telemedicine Diagnostic Challenges for Diabetic Retinopathy Telemedicine Diagnostic Challenges for Diabetic Retinopathy Ingrid Zimmer-Galler, M.D. Johns Hopkins Office of Telemedicine Financial Disclosures None 1 Telemedicine Diabetic Retinopathy Screening Performed

More information

Cancer Cells Detection using OTSU Threshold Algorithm

Cancer Cells Detection using OTSU Threshold Algorithm Cancer Cells Detection using OTSU Threshold Algorithm Nalluri Sunny 1 Velagapudi Ramakrishna Siddhartha Engineering College Mithinti Srikanth 2 Velagapudi Ramakrishna Siddhartha Engineering College Kodali

More information

Detection and Classification of Diabetic Retinopathy in Fundus Images using Neural Network

Detection and Classification of Diabetic Retinopathy in Fundus Images using Neural Network Detection and Classification of Diabetic Retinopathy in Fundus Images using Neural Network 1 T.P. Udhaya Sankar, 2 R. Vijai, 3 R. M. Balajee 1 Associate Professor, Department of Computer Science and Engineering,

More information

QUANTIFICATION OF PROGRESSION OF RETINAL NERVE FIBER LAYER ATROPHY IN FUNDUS PHOTOGRAPH

QUANTIFICATION OF PROGRESSION OF RETINAL NERVE FIBER LAYER ATROPHY IN FUNDUS PHOTOGRAPH QUANTIFICATION OF PROGRESSION OF RETINAL NERVE FIBER LAYER ATROPHY IN FUNDUS PHOTOGRAPH Hyoun-Joong Kong *, Jong-Mo Seo **, Seung-Yeop Lee *, Hum Chung **, Dong Myung Kim **, Jeong Min Hwang **, Kwang

More information

Automated Detection of Vascular Abnormalities in Diabetic Retinopathy using Morphological Entropic Thresholding with Preprocessing Median Fitter

Automated Detection of Vascular Abnormalities in Diabetic Retinopathy using Morphological Entropic Thresholding with Preprocessing Median Fitter IJSTE - International Journal of Science Technology & Engineering Volume 1 Issue 3 September 2014 ISSN(online) : 2349-784X Automated Detection of Vascular Abnormalities in Diabetic Retinopathy using Morphological

More information

The Role of Domain Knowledge in the Detection of Retinal Hard Exudates

The Role of Domain Knowledge in the Detection of Retinal Hard Exudates The Role of Domain Knowledge in the Detection of Retinal Hard Exudates Wynne Hsu 1,2 P M D S Pallawala 1 Mong Li Lee 1 Kah-Guan Au Eong 3 1 School of Computing, National University of Singapore {whsu,

More information

GLCM based FNN for Automated Drusen Detection in Fundus Images

GLCM based FNN for Automated Drusen Detection in Fundus Images GLCM based FNN for Automated Drusen Detection in Fundus Images Rama Prasath.A 1*, M.M.Ramya 2 and Kim.R 3 1 Assistant Professor,Department of Computer Applications, Hindustan Institute of Technology &

More information

Review on Optic Disc Localization Techniques

Review on Optic Disc Localization Techniques Review on Optic Disc Localization Techniques G.Jasmine PG Scholar Department of computer Science and Engineering V V College of Engineering Tisaiyanvilai, India jasminenesathebam@gmail.com Dr. S. Ebenezer

More information

Exudates Segmentation in Retinal Fundus Images for the Detection of Diabetic Retinopathy

Exudates Segmentation in Retinal Fundus Images for the Detection of Diabetic Retinopathy Exudates Segmentation in Retinal Fundus Images for the Detection of Diabetic Retinopathy Soumil Chugh Student, ECE Department Chandigarh College of Engineering and Technology Chandigarh, India Jaskirat

More information

Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods

Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods Available online at www.sciencedirect.com Computerized Medical Imaging and Graphics 32 (2008) 720 727 Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical

More information

Analogization of Algorithms for Effective Extraction of Blood Vessels in Retinal Images

Analogization of Algorithms for Effective Extraction of Blood Vessels in Retinal Images Analogization of Algorithms for Effective Extraction of Blood Vessels in Retinal Images P.Latha Research Scholar, Department of Computer Science, Presidency College (Autonomous), Chennai-05, India. Abstract

More information

OCT Angiography in Primary Eye Care

OCT Angiography in Primary Eye Care OCT Angiography in Primary Eye Care An Image Interpretation Primer Julie Rodman, OD, MS, FAAO and Nadia Waheed, MD, MPH Table of Contents Diabetic Retinopathy 3-6 Choroidal Neovascularization 7-9 Central

More information

Detection of ARMD and Grading of Maculopathy Severity Levels from Retinal Fundus Images

Detection of ARMD and Grading of Maculopathy Severity Levels from Retinal Fundus Images Detection of ARMD and Grading of Maculopathy Severity Levels from Retinal Fundus Images G Rajinikanth Reddy, M Narsing Yadav, R Raja Kishore (PG Scholar) 1 (Professor, Ph.D) 2 (M.Tech, Assistant Professor)

More information