FEATURE SELECTION METHOD WITH ATOM SEARCH OPTIMIZATION FOR DETECTION OF DIABETIC RETINOPATHY

Year 2022, Volume: 9 Issue: 16, 88 - 104, 14.04.2022

Feyza Altunbey Özbay , Erdal Özbay

https://doi.org/10.54365/adyumbd.1021738

Cited By: 3

Abstract

Diabetic Retinopathy (DR) is the leading cause of vision loss and blindness, affecting millions of people worldwide. There are many different scientific and medical approaches that use retinal fundus images for DR detection. In most of these approaches, various machine learning and deep learning approaches have been applied to diabetic retinopathy datasets without the feature selection step. The DR dataset obtained from the UCI machine learning repository was used in the study. In this article, Atom Search Optimization (ASO) algorithm, a new population-based metaheuristic method proposed by utilizing atom dynamics, is used for the first time as a feature selection method for the DR dataset. Applied the ASO algorithm to the normalized dataset, the new dataset was tested by six classification algorithms: Bagging, CvR, Ibk, JRip, Kstar, and SimpleCart. The same classification algorithms were applied to the original DR dataset. The results obtained were compared with the data set that was selected with the ASO algorithm. The performance of the proposed model was evaluated in terms of accuracy, sensitivity, specificity, precision, f-measure, and roc curve values. The results show that better values were obtained with Bagging, CvR, Ibk, JRip, Kstar, and SimpleCart algorithms on the dataset selected with the ASO algorithm. In this regard, an increase of 2.7% for the average accuracy, 3.5% for the sensitivity, and 2% for the specificity were achieved in the classification rates obtained without feature selection of the algorithms with the proposed feature selection.

Keywords

Atom search optimization algorithm, Diabetic Retinopathy, Feature selection, Classification

DİYABETİK RETİNOPATİ TESPİTİ İÇİN ATOM ARAMA OPTİMİZASYONU İLE ÖZELLİK SEÇİMİ YÖNTEMİ

Abstract

Diyabetik Retinopati (DR), dünya genelinde milyonlarca insanı etkileyen görme kaybı ve körlüğün başlıca nedenidir. DR tespiti için retinal fundus görüntülerini kullanan birçok farklı bilimsel ve tıbbi yaklaşımlar bulunmaktadır. Bu yaklaşımların çoğunda, özellik seçimi aşaması yapılmadan diyabetik retinopati veri kümelerine çeşitli makine öğrenimi ve derin öğrenme yaklaşımları uygulanmıştır. Çalışmada UCI makine öğrenmesi deposundan elde edilen DR veri kümesi kullanılmıştır. Bu makalede, atom dinamiklerinden faydalanılarak önerilmiş popülasyon temelli yeni bir metasezgisel yöntem olan Atom Arama Optimizasyon (AAO) algoritması, ilk kez DR veri kümesi için bir özellik seçim yöntemi olarak kullanılmıştır. Normalize edilen veri kümesine AAO algoritmasının uygulanmasının ardından elde edilen yeni veri kümesi Bagging, CvR, IBk, JRip, Kstar ve SimpleCart olmak üzere altı sınıflandırma algoritması ile test edilmiştir. Aynı sınıflandırma algoritmaları, orijinal DR veri kümesine de uygulanmıştır. Elde edilen sonuçlar AAO algoritması ile özellik seçimi yapılmış veri kümesi ile karşılaştırılmıştır. Önerilen modelin performansı doğruluk, duyarlılık, özgüllük, kesinlik, f-ölçütü ve roc alanı değerleri bakımından değerlendirilmiştir. Elde edilen sonuçlar, AAO algoritması ile özellik seçimi yapılmış veri kümesi üzerinde Bagging, CvR, IBk, JRip, Kstar ve SimpleCart algoritmaları ile daha iyi değerler elde edildiğini göstermektedir. Bu bakımdan önerilen özellik seçimi ile algoritmaların özellik seçimi olmadan elde edilen sınıflandırma oranlarında doğruluk için ortalama %2.7, duyarlılık için %3.5, özgüllük için %2’lik bir artış sağlanmıştır.

Keywords

Atom arama optimizasyon algoritması, Diyabetik Retinopati, Özellik seçimi, Sınıflandırma

References

• Taylor R, Batey D. Handbook of retinal screening in diabetes: diagnosis and management. John Wiley & Sons.
• Lin X, Xu Y, Pan X, Xu J, Ding Y, Sun X, Shan PF. Global, regional, and national burden and trend of diabetes in 195 countries and territories: an analysis from 1990 to 2025. Scientific reports 2020; 10(1): 1-11.
• Murray CJ, Lopez A. Mortality by cause for eight regions of the world: Global Burden of Disease Study. The Lancet 1997; 349(9061): 1269-1276.
• Bourne RR, Stevens GA, White RA, Smith JL, Flaxman SR, Price H. Causes of vision loss worldwide, 1990–2010: a systematic analysis. The lancet global health 2013;1(6): 339-e349.
• Harper CA, Keeffe JE. Diabetic retinopathy management guidelines. Expert review of ophthalmology 2012; 7(5): 417–39.
• Khurana DAK. Comprehensive ophthalmology: With supplementary book. Review of Ophthalmology. JP Medical Ltd, editor 2015.
• Patel S, Lohakare M, Prajapati S, Singh, S, Patel N. DiaRet: A browser-based application for the grading of Diabetic Retinopathy with Integrated Gradients. arXiv preprint arXiv:2103.08501, 2021.
• Qummar S, Khan FG, Shah S, Khan A, Shamshirband S, Rehman ZU, Jadoon W. A deep learning ensemble approach for diabetic retinopathy detection. IEEE Access 2019; 7: 150530-150539.
• Haneda S, Yamashita H. International clinical diabetic retinopathy disease severity scale. Nihon rinsho. Japanese journal of clinical medicine 2010; 68: 228-235.
• Sahlsten J, Jaskari J, Kivinen J, Turunen L, Jaanio E, Hietala K, Kaski K. Deep learning fundus image analysis for diabetic retinopathy and macular edema grading. Scientific reports 2019; 9: 1–11.
• Gondal WM, Köhler JM, Grzeszick R Fink GA, Hirsch M, Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images. Paper presented at: IEEE international conference on image processing (ICIP) 2017: 2069-2073.
• Li X, Pang T, Xiong B. Liu W, Liang P. Wang T, Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification. Paper presented at: 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). IEEE 2017: 1–11.
• Gulshan V, Peng L. Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama 2016; 316: 2402–2410.
• Castellano G, Castiello C, Mencar, C.; Vessio, G. Crowd Detection for Drone Safe Landing Through Fully-Convolutional Neural Networks. International Conference on Current Trends in Theory and Practice of Informatics. Springer, 2020, pp. 301–312.
• Raman V, Then P, Sumari P. Proposed retinal abnormality detection and classification approach: Computer-aided detection for diabetic retinopathy by machine learning approaches. Paper presented at: 8th IEEE International Conference on Communication Software and Networks (ICCSN) 2016: 636-641.
• Porwal P, Pachade S, Kokare M, Giancardo L, Meriaudeau F. Retinal image analysis for disease screening through local tetra patterns. Computers in biology and medicine 2018; 102: 200-210.
• Hemanth DJ, Deperlioglu O, Kose U. An enhanced diabetic retinopathy detection and classification approach using deep convolutional neural network. Neural Computing and Applications 2020; 32(3): 707-721.
• Shahin EM, Taha TE, Al-Nuaimy W, El Rabaie S, Zahran OF, El-Samie FEA. Automated detection of diabetic retinopathy in blurred digital fundus images. Paper presented at: 8th International Computer Engineering Conference (ICENCO) 2013; 20–25.
• Jaafar HF, Nandi AK, Al-Nuaimy W. Automated detection and grading of hard exudates from retinal fundus images. Paper presented at: 19th European signal processing conference 2011: 66–70.
• Casanova R, Saldana S, Chew EY, Danis RP, Greven CM, Ambrosius WT. Application of random forests methods to diabetic retinopathy classification analyses. PLoS One 2014; 9(6).
• Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology 2017; 124(7): 962–969.
• Akram MU, Shahzad K, Shoaib AK. Identification and classification of micro aneurysms for early detection of diabetic retinopathy. Pattern Recogn 2013; 46:107–116.
• Welikala RA, Dehmeshki J, Hoppe A, Tah V, Mann S, Williamson TH. Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification. Computer methods and programs in biomedicine 2014; 114(3): 247-261
• Waheed A, Waheed Z, Usman Akram M, Shaukat A. Removal of false blood vessels using shape based features and image inpainting. Journal of Sensors 2015.
• Zhang X, Thibault G, Decencière E, Marcotegui B, Laÿ B, Danno R. Exudate detection in color retinal images for mass screening of diabetic retinopathy. Medical image analysis 2014; 18(7): 1026-1043.
• Gadekallu TR, Khare N, Bhattacharya S, Singh S, Maddikunta PKR, Srivastava G. (2020). Deep neural networks to predict diabetic retinopathy. Journal of Ambient Intelligence and Humanized Computing 2020; 1-14.
• Zhao W, Wang L, Zhang, Z. Atom search optimization and its application to solve a hydrogeologic parameter estimation problem. Knowledge-Based Systems 2019; 163: 283-304.
• Zhao W, Wang L, Zhang Z. A novel atom search optimization for dispersion coefficient estimation in groundwater, Future Generation Computer Systems 2019; 91: 601-610.
• Breiman L. Bagging predictors, Machine Learning 1996; 24: 123-140.
• Ruan Y, Lin H, Tsai M. Improving Ranking Performance with Cost-Sensitive Ordinal Classification Via Regression. Information retrieval 2014; 17(1): 1-20.
• Kaladhar DSVGK, Pottumuthu BK, Rao PVN, Vadlamudi V, Chaitanya AK, Reddy RH. The elements of statistical learning in colon cancer data sets: data mining, inference and prediction. Algorithms Research 2013; 2: 8-17.
• Cohen WW. Fast effective rule induction. Paper presented in: Twelfth International Conference on Machine Learning 1995: 115-123.
• Breiman L, Friedman JH, Olshen RA, Stone C, Classification and regression trees. Wadsworth Books, 1984.
• University of California Irvine Machine Learning Repository. Accessed: Kasım. 5, 2021. [Online]. Available: https://archive.ics.uci.edu/ml/datasets/Diabetic+Retinopathy+Debrecen+Data+Set