Abstract
Diabetic retinopathy (DR) is the leading cause of avertable blindness globally. Retinal scanning of eyes is critical for examining the disease at an early stage. The concern of this study is to develop a robust mechanism to automate the process of diabetic retinopathy detection. A person suffering from DR must be referred to an ophthalmologist for an early evaluation in order to reduce the rate of vision loss hence enabling early treatment and prevention of vision loss. The proposed methodology introduces a data-driven novel algorithm using Deep learning for creating a tool for detecting DR. The approach uses DR colored fundus images and classifies them into multiple classes as stages or levels to which the eye is infected. Set of 170 colored fundus images of diabetic patients were used to train and test the model for distinguishing images into multiple classes. Entire simulation is divided into primarily two phases-firstly, the preprocessing phase where the resizing operation is performed since the input layer of the network requires predefined size. Size of 77 × 100 and channel of size 3 is used, indicating RGB image. Gaussian Filtering is used to tackle noise (De-noising) if any within the image. Secondly, the MSVM for segmentation and Classification phase where Multi-class SVM is used to extract critical and non-critical segments from within the training images. After extracting the features, classification is performed on the test images. Parameters used for optimization includes Accuracy, sensitivity, and specificity. Simulation is conducted in MATLAB using image processing and neural network toolbox. The proposed mechanism shows improvement in terms of classification accuracy by the margin of 5–6% which is significant, thereby enhancing the recognition rate.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Gargeya, R., Leng, T.: Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124, 962–969 (2017)
Haleem, M.S., Han, L., Van Hemert, J., Li, B., Fleming, A.: Retinal area detector from Scanning Laser Ophthalmoscope (SLO) images for diagnosing retinal diseases. IEEE J. Biomed. Health Inform. 19, 1472–1482 (2015)
Rubini, S.S., Kunthavai, A.: Diabetic retinopathy detection based on eigenvalues of the Hessian matrix. Procedia Comput. Sci. 47, 311–318 (2014)
Maher, R., Dhopeshwarkar, M.: Automatic detection non-proliferative diabetic retinopathy using image processing techniques. J. Eng. Res. Appl. 6, 122–127 (2016)
Shveta, S., Kaur, G.: Review on: detection of diabetic retinopathy using SVM and MDA. Int. J. Comput. Appl. 117(20), 975–987 (2015)
Paranjpe, M.J., Kakatkar, P.M.N.: Automated diabetic retinopathy severity classification using support vector machine. Int. J. Res. Sci. Technol. 3(3), 86–91 (2013)
Ramya, V.: SVM based detection for diabetic retinopathy. Int. J. Res. Sci. Innov. V, 11–13 (2018)
Adarsh, P., Jeyakumari, D.: Multiclass SVM-based automated diagnosis of diabetic retinopathy. In: International Conference on Communications Signal Processing, pp. 206–210 (2013)
Zhou, L., Zhao, Y., Yang, J., Yu, Q., Xu, X.: Deep multiple instance learning for automatic detection of diabetic retinopathy in retinal images. IET Image Process. 12, 563–571 (2018)
Jothi, N., Rashid, N.A., Husain, W.: Data mining in healthcare - a review. Procedia Comput. Sci. 72, 306–313 (2015)
Santosh, K.C., Vajda, S., Antani, S., Thoma, G.R.: Edge map analysis in chest X-rays for automatic pulmonary abnormality screening. Int. J. Comput. Assist. Radiol. Surg. 11, 1637–1646 (2016)
Santosh, K.C., Wendling, L., Antani, S., Thoma, G.R.: Overlaid arrow detection for labeling regions of interest in biomedical images. IEEE Intell. Syst. 31, 66–75 (2016)
Saini, M., Yadav, S., Rewri, S.: A hybrid filtering techniques for noise removal in color images. Int. J. Innov. Eng. Technol. 5, 172–178 (2015)
Ma, Y., Lin, D., Zhang, B., Liu, Q., Gu, J.: A novel algorithm of image gaussian noise filtering based on PCNN time matrix. In: 2007 IEEE International Conference on Signal Processing and Communications, pp. 1499–1502. IEEE (2007)
Bulsara, V., Bothra, S., Sharma, P., Rao, K.M.M.: Low cost medical image processing system for rural/semi urban healthcare. In: IEEE Access, pp. 724–728 (2011)
Shetty, S., Kari, K.B., Rathod, J.A.: Detection of diabetic retinopathy using support vector machine (SVM). Int. J. Emerg. Technol. Comput. Sci. Electron. 23, 207–211 (2016)
Naraei, P., Abhari, A., Sadeghian, A.: Application of multilayer perceptron neural networks and support vector machines in classification of healthcare data. In: Future Technologies Conference (FTC), pp. 848–852. IEEE (2016)
Chaudhari, V.V., Salunkhe, P.P.: Diabetic retinopathy classification using SVM classifier. Int. J. Appl. Innov. Eng. Manag. 6, 7–11 (2017)
Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., Chouvarda, I.: Machine learning and data mining methods in diabetes research. Comput. Struct. Biotechnol. J. 15, 104–116 (2017)
Huang, F., Wang, S., Chan, C.: Predicting disease by using data mining based on healthcare information system. In: 2012 IEEE International Conference on Granular Computing Predict, pp. 12–15 (2012)
Karargyris, A., et al.: Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays. Int. J. Comput. Assist. Radiol. Surg. 11, 99–106 (2016)
Vajda, S., Santosh, K.C.: A fast k-nearest neighbor classifier using unsupervised clustering. In: Santosh, K.C., Hangarge, M., Bevilacqua, V., Negi, A. (eds.) RTIP2R 2016. CCIS, vol. 709, pp. 185–193. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-4859-3_17
Panayides, A.S., Pattichis, C.S., Pattichis, M.S.: The promise of big data technologies and challenges for image and video analytics in healthcare. In: 50th Asilomar Conference on Signals, Systems and Computers, pp. 1278–1282. IEEE (2016)
Ukil, S., Ghosh, S., Obaidullah, S., Santosh, K.C., Roy, K., Das, N.: Deep learning for word-level handwritten Indic script identification
Al-ayyoub, M., Alzu, S.M., Jararweh, Y., Alsmirat, M.A.: A GPU-based breast cancer detection system using single pass fuzzy C-means clustering algorithm. In: 5th International Conference on Multimedia Computing and Systems, pp. 650–654. IEEE (2016)
Abe, S., Inoue, T.: Fuzzy support vector machines for pattern classification. In: International Joint Conference on Neural Networks, pp. 1449–1454. IEEE (2001)
Ruikar, D.D., Santosh, K.C., Hegadi, R.S.: Automated fractured bone segmentation and labeling from CT images. J. Med. Syst. 43(3), 60 (2019). https://doi.org/10.1007/s10916-019-1176-x
Ruikar, D.D., Santosh, K.C., Hegadi, R.S.: Segmentation and analysis of CT images for bone fracture detection and labeling. In: Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques, Chap. 7. CRC Press (2019). ISBN 9780367139612
Hegadi, R.S., Navale, D.I., Pawar, T.D., Ruikar, D.D.: Multi feature-based classification of osteoarthritis in knee joint X-ray images. In: Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques, Chap. 5. CRC Press (2019). ISBN 9780367139612
Ruikar, D.D., Sawat, D.D., Santosh, K.C., Hegadi, R.S.: 3D imaging in biomedical applications: a systematic review. In: Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques, Chap. 8. CRC Press (2019). ISBN 9780367139612
Ruikar, D.D., Hegadi, R.S., Santosh, K.C.: A systematic review on orthopedic simulators for psycho-motor skill and surgical procedure training. J. Med. Syst. 42(9), 168 (2018)
Jagtap, A.B., Hegadi, R.S.: Feature learning for offline handwritten signature verification using convolution neural network. Int. J. Technol. Hum. Interact. (IJTHI). ISSN 1548–3908
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bhatti, E., Kaur, P. (2019). DRAODM: Diabetic Retinopathy Analysis Through Optimized Deep Learning with Multi Support Vector Machine for Classification. In: Santosh, K., Hegadi, R. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2018. Communications in Computer and Information Science, vol 1036. Springer, Singapore. https://doi.org/10.1007/978-981-13-9184-2_16
Download citation
DOI: https://doi.org/10.1007/978-981-13-9184-2_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9183-5
Online ISBN: 978-981-13-9184-2
eBook Packages: Computer ScienceComputer Science (R0)