Severity Classification of Non-Proliferative Diabetic Retinopathy Using Support Vector Machine (SVM)

Authors

  • Siti Salamah Universitas Islam Negeri Sunan Gunung Djati
  • Khoerun Nisa Syaja'ah Universitas Islam Negeri Sunan Gunung Djati
  • Yudha Satya Perkasa Universitas Islam Negeri Sunan Gunung Djati

DOI:

https://doi.org/10.26740/jpfa.v12n2.p167-179

Keywords:

Retinal Fundus Image, GLCM Feature Extraction, Diabetic Retinopathy, Segmentation, Support Vector Machine

Abstract

Diabetic Retinopathy (DR) is an eye disease that is the main cause of blindness in developed countries. Treatment of DR and prevention of blindness depend heavily on regular monitoring, early-stage diagnosis, and timely treatment. Vision loss can be effectively prevented by the automated diagnostic system that assists ophthalmologists who otherwise practice manual lesion detection processes which are tedious and time-consuming. Therefore, the purpose of this research is to design a system that can detect the presence of DR and be able to classify it based on its severity. In this proposed, the classification process is carried out based on image discovery by extracting GLCM texture features from 454 retinal fundus images in the IDRID database which are classified into 4 severity levels, namely normal, mild NPDR, moderate NPDR, and severe NPDR. The features obtained from each image will be used as input for the classification process using SVM. As a result, the classification system that has been trained is able to classify 4 levels of DR severity with an average accuracy of 89.55%, a sensitivity of 81.03%, and a specificity of 92.89%. Based on the results of the evaluation of the performance of this classification system, it can be concluded that the specificity value is higher than the specificity value, this indicates that the system that has been trained has a good ability to identify negative samples or those that indicate a class.

References

Kanungo YS, Srinivasan B, and Choudhary S. Detecting Diabetic Retinopathy Using Deep Learning. RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology (RTEICT). Bangalore, India; 2017: 801–804. DOI: https://doi.org/10.1109/RTEICT.2017.8256708.

Abdelsalam MM and Zahran MA. A Novel Approach of Diabetic Retinopathy Early Detection Based on Multifractal Geometry Analysis for OCTA Macular Images Using Support Vector Machine. IEEE Access. 2021; 9: 22844–22858. DOI: https://doi.org/10.1109/ACCESS.2021.3054743.

Handayani OWK, Nugroho E, and Hermawati B. Determinant of Diabetes Mellitus Focusing on Differences of Indonesian Culture: Case Studies in the Java and Outer Java Region in Indonesia. The Open Public Health Journal. 2020; 13(1): 323–340. DOI: https://doi.org/10.2174/1874944502013010323.

Alyoubi WL, Abulkhair MF, and Shalash WM. Diabetic Retinopathy Fundus Image Classification and Lesions Localization System Using Deep Learning. Sensors. 2021; 21(11): 1–22. DOI: https://doi.org/10.3390/s21113704.

Bhardwaj C, Jain S, and Sood M. Hierarchical Severity Grade Classification of Non-Proliferative Diabetic Retinopathy. Journal of Ambient Intelligence and Humanized Computing. 2021; 12(2): 2649–2670. DOI: https://doi.org/10.1007/s12652-020-02426-9.

Roychowdhury S, Koozekanani DD, and Parhi KK. DREAM: Diabetic Retinopathy Analysis Using Machine Learning. IEEE Journal of Biomedical and Health Informatics. 2014; 18(5): 1717–1728. DOI: https://doi.org/10.1109/JBHI.2013.2294635.

Yadav D, et al. Microaneurysm Detection Using Color Locus Detection Method. Measurement: Journal of the International Measurement Confederation. 2021; 176: 109084. DOI: https://doi.org/10.1016/j.measurement.2021.109084.

Amiruddin R, Stang, Ansar J, Sidik D, and Rahman AW. Diabetic Mellitus Type 2 in Wajo South Sulawesi, Indonesia. International Journal of Current Research & Academic Review. 2014; 2(12): 1–8. Available from: http://www.ijcrar.com/vol-2-12/Ridwan%20Amiruddin,%20et%20al.pdf.

Mahendran G and Dhanasekaran R. Investigation of the Severity Level of Diabetic Retinopathy Using Supervised Classifier Algorithms. Computers and Electrical Engineering. 2015; 45: 312–323. DOI: https://doi.org/10.1016/j.compeleceng.2015.01.013.

Hemavathi S and Padmapriya S. Detection of Diabetic Retinopathy on Retinal Images Using Support Vector Machine. SSRG International Journal of Computer Science and Engineering (SSRG–IJCSE). 2019: 2019(special issue ICMR); 5–8. Available from: https://www.internationaljournalssrg.org/uploads/specialissuepdf/ICMR-2019/2019/CSE/IJCSE-ICMR-P102.pdf.

Koh JEW, Ng EYK, Bhandary SV, Laude A, and Acharya UR. Automated Detection of Retinal Health Using PHOG and SURF Features Extracted from Fundus Images. Applied Intelligence. 2018; 48(5): 1379–1393. DOI: https://doi.org/10.1007/s10489-017-1048-3.

Fayiza KT and Jabbar S. Red Lesion Detection Using Hough Transform and KNN Classifier for Diabetic Retinopathy Screening. International Journal of Science and Research (IJSR). 2017; 6(7): 473–478. DOI: https://doi.org/10.21275/art20174218.

Zhang X, Cui J, Wang W, and Lin C. A Study for Texture Feature Extraction of High-Resolution Satellite Images Based on a Direction Measure and Gray Level Co-Occurrence Matrix Fusion Algorithm. Sensors. 2017; 17(7): 1474. DOI: https://doi.org/10.3390/s17071474.

Wang H, et al. Hard Exudate Detection Based on Deep Model Learned Information and Multi-Feature Joint Representation for Diabetic Retinopathy Screening. Computer Methods and Programs in Biomedicine. 2020; 191: 105398. DOI: https://doi.org/10.1016/j.cmpb.2020.105398.

Orlando JI, Prokofyeva E, del Fresno M, and Blaschko MB. An Ensemble Deep Learning Based Approach for Red Lesion Detection in Fundus Images. Computer Methods and Programs in Biomedicine. 2018; 153: 115–127. DOI: https://doi.org/10.1016/j.cmpb.2017.10.017.

Liu Q, et al. A Location-to-Segmentation Strategy for Automatic Exudate Segmentation in Colour Retinal Fundus Images. Computerized Medical Imaging and Graphics. 2017; 55: 78–86. DOI: https://doi.org/10.1016/j.compmedimag.2016.09.001.

Aziza EZ, El Amine LM, Mohamed M, and Abdelhafid B. Decision Tree CART Algorithm for Diabetic Retinopathy Classification. Proceedings - 2019 6th International Conference on Image and Signal Processing and their Applications, ISPA 2019. 2019: 1–5. DOI: https://doi.org/10.1109/ISPA48434.2019.8966905.

Paing MP, Choomchuay S, and Yodprom MDR. Detection of Lesions and Classification of Diabetic Retinopathy Using Fundus Images. 2016 9th Biomedical Engineering International Conference (BMEiCON). Laung Prabang, Laos; 2016: 1-5. DOI: https://doi.org/10.1109/BMEiCON.2016.7859642.

Nayak J, Bhat PS, Acharya R, Lim CM, and Kagathi M. Automated Identification of Diabetic Retinopathy Stages Using Digital Fundus Images. Journal of Medical Systems. 2008; 32(2): 107–115. DOI: https://doi.org/10.1007/s10916-007-9113-9.

Porwal P, et al. Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research. Data. 2018; 3(3): 25. DOI: https://doi.org/10.3390/data3030025.

Wilkinson CP, et al. Proposed International Clinical Diabetic Retinopathy and Diabetic Macular Edema Disease Severity Scales. Ophthalmology. 2003; 110(9): 1677–1682. DOI: https://doi.org/10.1016/S0161-6420(03)00475-5.

Mishra PK, et al. A Computational Modeling for the Detection of Diabetic Retinopathy Severity. Bioinformation. 2014; 10(9): 556–561. DOI: https://doi.org/10.6026/97320630010556.

Muztaba R, Malasan HL, and Djamal M. Development of an Automated Moon Observation System Using the ALTS-07 Robotic Telescope: 2. Progress Report on Standard Contrast Enhancement of Moon Crescent Image with OpenCV. Journal of Physics: Conference Series. 2022; 2214: 012004. DOI: https://doi.org/10.1088/1742-6596/2214/1/012004.

Hana FM and Maulida ID. Analysis of Contrast Limited Adaptive Histogram Equalization (CLAHE) Parameters on Finger Knuckle Print Identification. Journal of Physics: Conference Series. 2021; 1764: 012049. DOI: https://doi.org/10.1088/1742-6596/1764/1/012049.

Zhang P and Li F. A New Adaptive Weighted Mean Filter for Removing Salt-and-Pepper Noise. IEEE Signal Processing Letters. 2014; 21(10): 1280–1283. DOI: https://doi.org/10.1109/LSP.2014.2333012.

Faisal M, Wahono D, Purnomo IKE, Hariadi M, and Purnomo MH. Classification of Diabetic Retinopathy Patients Using Support Vector Machines (SVM) Based on Digital Retinal Image. Journal of Theoretical and Applied Information Technology. 2014; 59(1): 197–204. Available from: http://www.jatit.org/volumes/Vol59No1/22Vol59No1.pdf.

Raid AM, Khedr WM, El-dosuky MA, and Aoud M. Image Restoration Based on Morphological Operations. International Journal of Computer Science, Engineering and Information Technology (IJCSEIT). 2014; 4(3): 9–21. DOI: https://doi.org/10.5121/ijcseit.2014.4302.

Selvathi D, Parakash NB, and Balagopal N. Automated Detection of Diabetic Retinopathy for Early Diagnosis Using Feature Extraction and Support Vector Machine. International Journal of Emerging Technology and Advanced Engineering. 2012; 2(11): 103–108.

Zeng M, Li J, and Peng Z. The Design of Top-Hat Morphological Filter and Application to Infrared Target Detection. Infrared Physics and Technology. 2006; 48(1): 67–76. DOI: https://doi.org/10.1016/j.infrared.2005.04.006.

Miyamoto E and Jr. TM. Fast Calculation of Haralick Texture Features. Pittsburgh PA: Department of Electrical and Computer Engineering Carnegie Mellon University; 2005.

Available from: http://users.ece.cmu.edu/~pueschel/teaching/18-799B-CMU-spring05/material/eizan-tad.pdf.

Zulpe NS and Pawar VP. GLCM Textural Features for Brain Tumor Classification. International Journal of Computer Science Issues. 2012; 9(3): 354–359. Available from: http://ijcsi.org/articles/Glcm-textural-features-for-brain-tumor-classification.php.

Campbell C and Ying Y. Learning with Support Vector Machines. In C. Campbell and Y. Ying, Synthesis Lectures on Artificial Intelligence and Machine Learning. Switzerland: Springer Cham; 2011. DOI: https://doi.org/10.1007/978-3-031-01552-6.

Ben-hur A and Weston J. A User’s Guide to Support Vector Machines. In O. Carugo and F. Eisenhaber (eds), Data Mining Techniques for the Life Sciences. Methods in Molecular Biology, vol 609. New Jersey: Humana Press; 2010: 223–239. DOI: https://doi.org/10.1007/978-1-60327-241-4_13.

Gayathri S, Krishna AK, Gopi VP, and Palanisamy P. Automated Binary and Multiclass Classification of Diabetic Retinopathy Using Haralick and Multiresolution Features. IEEE Access. 2020; 8: 57497–57504. DOI: https://doi.org/10.1109/access.2020.2979753.

Tharwat A. Classification Assessment Methods. Applied Computing and Informatics. 2018; 17(1): 168–192. DOI: https://doi.org/10.1016/j.aci.2018.08.003.

Rosadi MI, Sanjaya CB, and Hakim L. Klasifikasi Diabetic Retinopathy Menggunakan Seleksi Fitur Dan Support Vector Machine. Jurnal RESISTOR (Rekayasa Sistem Komputer). 2018; 1(2): 109–117. DOI: https://doi.org/10.31598/jurnalresistor.v1i2.312.

Chen PN, et al. General Deep Learning Model for Detecting Diabetic Retinopathy. BMC Bioinformatics. 2021; 22: 1–14. DOI: https://doi.org/10.1186/s12859-021-04005-x.

Owhal MRR, Vaghasiya S, Tenkale A, and Pokale A. SVM for Diabetic Detection System. International Journal of Scientific Research & Engineering Trends. 2022; 8(3): 1235–1237.

Available from: https://ijsret.com/wp-content/uploads/2022/05/IJSRET_V8_issue3_325.pdf.

Ranjan GSK, Verma AK, and Radhika S. K-Nearest Neighbors and Grid Search CV Based Real Time Fault Monitoring System for Industries. 2019 IEEE 5th International Conference for Convergence in Technology; 2019: 9–13. DOI: https://doi.org/10.1109/I2CT45611.2019.9033691.

Eagan B, Misfeldt M, and Siebert-Evenstone A. Advances in Quantitative Ethnography. Proceedings of First Internasional Conference, ICQE 2019; 2019. DOI: https://doi.org/10.1007/978-3-030-33232-7.

Foster KR, Koprowski R, and Skufca JD. Machine Learning, Medical Diagnosis, and Biomedical Engineering Research-Commentary. BioMedical Engineering Online. 2014; 13(94): 1–9. DOI: https://doi.org/10.1186/1475-925X-13-94.

Nasteski V. An Overview of the Supervised Machine Learning Methods. Horizons. 2017; 4: 51–62. DOI: https://doi.org/10.20544/horizons.b.04.1.17.p05.

Ruuska S, et al. Evaluation of the Confusion Matrix Method in the Validation of an Automated System for Measuring Feeding Behaviour of Cattle. Behavioural Processes. 2018; 148: 56–62. DOI: https://doi.org/10.1016/j.beproc.2018.01.004.

Seoud L, Chelbi J and Cheriet F. Automatic Grading of Diabetic Retinopathy on a Public Database. Proceeding of Opthalmic Medical Image Analysis (OMIA) International Workshop. 2015; 2(2015): 97–104. DOI: https://doi.org/10.17077/omia.1032.

Downloads

Published

2022-12-30

How to Cite

Salamah, S., Syaja’ah, K. N. and Perkasa, Y. S. (2022) “Severity Classification of Non-Proliferative Diabetic Retinopathy Using Support Vector Machine (SVM)”, Jurnal Penelitian Fisika dan Aplikasinya (JPFA), 12(2), pp. 167–179. doi: 10.26740/jpfa.v12n2.p167-179.

Issue

Section

Articles
Abstract views: 186 , PDF Downloads: 201