Abstract
This paper presents a machine learning classifier, namely, Random Forest to detect abnormalities in retina arising from Diabetic Retinopathy. This is an effort to obtain a computer-aided diagnosis procedure to substitute manual detection. Fundus images from public datasets are used for this purpose. A set of statistical and geometric features were extracted from images in the database which contains the different physical manifestations of the disease. Classification through machine learning can help a physician by giving an indication of the level of the disease. The experimental results show 99.275% of accuracy in prediction of the disease, which is promising.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I (2017) Machine learning and data mining methods in diabetes research. Comput Struct Biotechnol J 15:104–116
Jingar R, Verma M (2012) Semantic segmentation of an image using random forest and single histogram class model. Technical report, Indian Institute of Technology Kanpur
Kausar N, Majid A (2016) Random forest based scheme using feature and decision levels information for multi-focus image fusion. Pattern Anal Appl 19:221–236
Saiprasad G, Chang C, Safdar N, Saenz N, Seigel E (2013) Adrenal gland abnormality detection using random forest classification. J Digit Imaging 26:891–897
Almayyan W (2016) Lymph disease prediction using random forest and particle swarm optimization. J Intell Learn Syst and Appl 8:51–62
Csillik O (2017) Fast segmentation and classification of very high resolution remote sensing data using SLIC superpixels. Remote Sens 9(3):243
Roychowdhury A, Banerjee S, Machine learning in the classification of diabetic retinopathy lesions from abnormal retina images (submitted)
Kauppi T, Kalesnykiene V, Kamarainen J-K, Lensu L, Sorri I, Uusitalo H, Klviinen H, Pietil J, DIARETDB0: evaluation database and methodology for diabetic retinopathy algorithms, Technical report
Kauppi T, Kalesnykiene V, Kamarainen J-K, Lensu L, Sorri I, Raninen A, Voutilainen R, Uusitalo H, Klviinen H, Pietil J, DIARETDB1: diabetic retinopathy database and evaluation protocol, Technical report
Frank E, Hall MA, Witten IH (2016) The Weka Workbench, Online Appendix for Data Mining : Practical Machine Learning Tools and Techniques, 4th edn. Morgan Kaufman
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Roychowdhury, A., Banerjee, S. (2018). Random Forests in the Classification of Diabetic Retinopathy Retinal Images. In: Bhattacharyya, S., Gandhi, T., Sharma, K., Dutta, P. (eds) Advanced Computational and Communication Paradigms. Lecture Notes in Electrical Engineering, vol 475. Springer, Singapore. https://doi.org/10.1007/978-981-10-8240-5_19
Download citation
DOI: https://doi.org/10.1007/978-981-10-8240-5_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8239-9
Online ISBN: 978-981-10-8240-5
eBook Packages: EngineeringEngineering (R0)