A Hybrid Deep Learning-Metaheuristic Model for Diagnosis of Diabetic Retinopathy

Abstract

International Diabetes Federation (IDF) reports that diabetes is a rapidly growing illness. About 463 million adults between 20-79 years have diabetes. There are also millions of undiagnosed patients. It is estimated that there will be about 578 million diabetics by 2030 [1]. Diabetes reasons different eye diseases. Diabetic retinopathy (DR) is one of them and is also one of the most common vision loss or blindness worldwide. DR progresses slowly and has few indicators in the early stages. It makes the diagnosis of DR a problematic task. Automated systems promise to support the diagnosis of DR. Many deep learning-based models have been developed for DR classification. This study aims to support ophthalmologists in the diagnosis process and increase the diagnosis performance of DR through a hybrid model. A publicly available Messidor-2 dataset was used in this study, comprised of retinal images. In the proposed model, images were pre-processed, and a deep learning model, namely, InceptionV3, was used in feature extraction, where a transfer learning approach is applied. Next, the number of features in obtained feature vectors was decreased with feature selection by Simulated Annealing. Lastly, the best representation features were used in the XGBoost model. The XGBoost algorithm gives an accuracy of 92.55% in a binary classification task. This study shows that a pre-trained ConvNet with a metaheuristic algorithm for feature selection gives a satisfactory result in the diagnosis of DR. 

Keywords

• Deep learning
• Metaheuristic
• XGBoost
• Diabetic Retinopath
• Optimization

References

1. [1] https://www.diabetesatlas.org/upload/resources/material/20200302_133351_IDFATLAS9e-final-web.pdf. Access date: 02.03.2021
2. [2] https://apps.who.int/iris/bitstream/handle/10665/336660/9789289055321-eng.pdf. Access date: 02.03.2021
3. [3] Wong, T. Y., Sabanayagam, C., “Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence”, Ophthalmologica, 243(1): 9-20, (2020).
4. [4] Kandel, I., Castelli, M., “Transfer learning with convolutional neural networks for diabetic retinopathy image classification. A review”, Applied Sciences, 10(6): 1-24, (2021).
5. [5] Yazici, I., Beyca, O. F., Gurcan, O. F., Zaim, H., Delen, D., Zaim, S., “A comparative analysis of machine learning techniques and fuzzy analytic hierarchy process to determine the tacit knowledge criteria”, Annals of Operations Research, 1-24, (2020).
6. [6] Şenyiğit, E., Atici, U., “Artificial neural network models for lot-sizing problem: a case study”, Neural Computing and Applications, 22(6): 1039-1047, (2013).
7. [7] Buyya, R., Calheiros, R. N., Dastjerdi, A. V., “Big data: principles and paradigms”, Morgan Kaufmann, India, (2016).
8. [8] Kızılkaya Aydoğan, E., Delice, Y., Özcan, U., Gencer, C., Bali, O., “Balancing stochastic U-lines using particle swarm optimization”, Journal of Intelligent Manufacturing, 30: 97-111, (2019).

9. [9] Abdel-Basset, M., Abdel-Fatah, L., Sangaiah, A. K., “Metaheuristic Algorithms: A Comprehensive Review”, In A. K. Sangaiah, M. Sheng & Z. Zhang, Computational Intelligence for Multimedia Big Data on the Cloud with Engineering Applications, Cham., (2018).
10. [10] Paranjpe, M. J., Kakatkar, M. N., “Automated diabetic retinopathy severity classification using support vector machine”, International Journal for Research in Science & Advanced Technologies, 3(3): 86-91, (2013).
11. [11] Harini, R., Sheela, N., “Feature extraction and classification of retinal images for automated detection of Diabetic Retinopathy”, Second International Conference on Cognitive Computing and Information Processing, Mysuru, India, (2016).
12. [12] Punithavathi, I. H., Kumar, P. G., “Severity grading of diabetic retinopathy using extreme learning machine”, International Conference on Intelligent Techniques in Control, Optimization and Signal Processing, Krishnankoil, India, (2017).
13. [13] Colomer, A., Igual, J., Naranjo, V., “Detection of early signs of diabetic retinopathy based on textural and morphological information in fundus images”, Sensors, 20(4): 1-21, (2020).
14. [14] Johari, M. H., Hassan, H. A., Yassin, A. I. M., Tahir, N. M., Zabidi, A., Rizman, Z. I., Wahab, N. A., “Early detection of diabetic retinopathy by using deep learning neural network”, International Journal of Engineering and Technology, 7(4): 198-201, (2018).
15. [15] Takahashi, H., Tampo, H., Arai, Y., Inoue, Y., Kawashima, H., “Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy”, Plos One, 12(6): e0179790, (2017).
16. [16] Choi, J. Y., Yoo, T. K., Seo, J. G., Kwak, J., Um, T. T., Rim, T. H., “Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database”, Plos One, 12(11): e0187336, (2017).
17. [17] Zhang, W., Zhong, J., Yang, S., Gao, Z., Hu, J., Chen, Y., Yi, Z., “Automated identification and grading system of diabetic retinopathy using deep neural networks”, Knowledge-Based Systems, 175: 12-25, (2019).
18. [18] Bodapati, J. D., Veeranjaneyulu, N., Shareef, S. N., Hakak, S., Bilal, M., Maddikunta, P. K. R., Jo, O., “Blended multi-modal deep convnet features for diabetic retinopathy severity prediction”, Electronics, 9(6): 914-930, (2020).
19. [19] Pratt, H., Coenen, F., Broadbent, D. M., Harding, S. P., Zheng, Y., “Convolutional neural networks for diabetic retinopathy”, Procedia Computer Science, 90: 200-205, (2016).
20. [20] Dener, M., Akcayol, M. A., Toklu, S., Bay, Ö. F., “Genetic algorithm based a new algorithm for time dynamic shortest path problem”, Journal of The Faculty of Engineering and Architecture of Gazi University, 26(4): 915-928, (2011).
21. [21] Utku, A., Muhammet A. A., “Deep Learning Based Prediction Model for The Next Purchase”, Advances in Electrical and Computer Engineering, 20: 35-44, (2020).
22. [22] Çerçioğlu, H., Özcan, U., Gökçen, H., Toklu, B., “A Simulated Annealing Approach for Parallel Assembly Line Balancing Problem”, Journal of The Faculty of Engineering and Architecture of Gazi University, 24(2): 331-341, (2009).
23. [23] Moorthy, R. S., Pabitha, P. A., “Study on Meta Heuristic Algorithms for Feature Selection”, International Conference on Intelligent Data Communication Technologies and Internet of Things, Springer, Cham., (2018).
24. [24] Canayaz, M., “MH-COVIDNet: Diagnosis of COVID-19 using deep neural networks and meta-heuristic-based feature selection on X-ray images”, Biomedical Signal Processing and Control, 64: 102257, (2021).
25. [25] Voets, M., Møllersen, K., Bongo, L. A., “Reproduction study using public data of: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs”, Plos One, 14(6): 0217541, (2019).
26. [26] Li, F., Liu, Z., Chen, H., Jiang, M., Zhang, X., Wu, Z., “Automatic detection of diabetic retinopathy in retinal fundus photographs based on deep learning algorithm”, Translational Vision Science & Technology, 8(6): 4-4, (2019).
27. [27] Toledo-Cortés, S., De La Pava, M., Perdomo, O., González, F. A., “Hybrid Deep Learning Gaussian Process for Diabetic Retinopathy Diagnosis and Uncertainty Quantification”, In International Workshop on Ophthalmic Medical Image Analysis, Springer, Cham., (2020).
28. [28] Gurcan, O. F., Beyca, O. F., Dogan, O., “A Comprehensive Study of Machine Learning Methods on Diabetic Retinopathy Classification”, International Journal of Computational Intelligence Systems, 14(2): 1132-1141, (2021).
29. [29] Abràmoff, M. D., Folk, J. C., Han, D. P., Walker, J. D., Williams, D. F., Russell, S. R., Massin, P., Cochener, B., Gain, P., Tang, L., Lamard, M., Moga, D. C., Quellec, G., & Niemeijer, M., “Automated analysis of retinal images for detection of referable diabetic retinopathy”. JAMA Ophthalmology, 131(3): 351-357, (2013).
30. [30] Decencière, E., Zhang, X., Cazuguel, G., Lay, B., Cochener, B., Trone, C., Gain, P., Ordonez, R., Massin, P., Erginay, A., Charton, B., Klein, J. C., “Feedback on a publicly distributed image database: the messidor database”, Image Analysis & Stereology, 33(3): 231-234, (2014).
31. [31] http://www.adcis.net/en/thirdparty/messidor2/. Access date: 01.02.2021.
32. [32] Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C., “A survey on deep transfer learning”, In International Conference on Artificial Neural Networks, Springer, Cham., 270-279, (2018).
33. [33] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z., “Rethinking the inception architecture for computer vision”, IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, (2016).
34. [34] https://deepai.org/machine-learning-glossary-and-terms/inception-module. Access date: 01.02.2021.
35. [35] Li, F., Liu, Z., Chen, H., Jiang, M., Zhang, X., Wu, Z., “Automatic detection of diabetic retinopathy in retinal fundus photographs based on deep learning algorithm”, Translational Vision Science & Technology, 8(6): 4-4, (2019).
36. [36] Wu, C. C., Hsu, P. H., Lai, K., “Simulated-annealing heuristics for the single-machine scheduling problem with learning and unequal job release times”, Journal of Manufacturing Systems, 30(1): 54-62, (2011).
37. [37] Kim, D. W., Kim K. H., Jang, W., Chen, F. F., “Unrelated parallel machine scheduling with setup times using simulated annealing”, Robotics and Computer-Integrated Manufacturing, 18(3): 223-231, (2002).
38. [38] Kuhn, M., Johnson, K., Applied predictive modeling, Springer, New York, (2013).
39. [39] Chen, T., Guestrin, C., “Xgboost: A scalable tree boosting system”, 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, (2016).
40. [40] Brownlee, J., “XGBoost With Python: Gradient Boosted Trees with XGBoost and Scikit-Learn”. Machine Learning Mastery, (2016).
41. [41] Rokach, L., “Ensemble learning: Pattern classification using ensemble methods”, World Scientific, (2019).