Automated Framework for Screening of Glaucoma Through Cloud Computing
In recent times, the use of computer aided diagnosis for detection of Glaucoma from fundus images has been prevalent. In the proposed work, a cloud based system is proposed for automatic and real-time screening of Glaucoma with the use of automatic image processing techniques. The proposed system offers scalability to the developers and easy accessibility to the consumers. The proposed system is device and location independent. The input digital image is analyzed and a comprehensive diagnostic report is generated consisting of detailed analysis of indicative medical parameters like optic-cup-to-disc ratio, optic neuro-retinal rim, ISNT rules making the report informative and clinically significant. With recent advances in the field of communication technologies, the internet facilities are available that make the proposed system an efficient and economical method for initial screening and offer preventive and diagnostic steps in early disease intervention and management. The proposed system can perform an initial screening test in an average time of 6 s on high resolution fundus images. The proposed system has been tested on a fundus database and an average sensitivity of 93.7% has been achieved for Glaucoma cases. In places where there is scarcity of trained ophthalmologists and lack of awareness of such diseases, the cloud based system can be used as an effective diagnostic assistive tool.
KeywordsGlaucoma Optic disc Retinal vessels ISNT rule Fundus images Cloud computing Web application Docker Heroku Django Base64 encoding OpenCV
This work was supported in part by the Grants from Department of Science and Technology, No. DST/TSG/ICT/2013/37. Also, the authors express their thankfulness to Dr. S.C. Gupta, Medical Director of Venu Eye Research Centre for his contribution in classification of the images.
- 1.Tsai, J. C., How to evaluate the suspicious optic disc. Rev. Ophthalmol. 2005.Google Scholar
- 2.Tuominen, V. J., Ruotoistenmäki, S., Viitanen, A., Jumppanen, M. and Isola, J., ImmunoRatio: a publicly available web application for quantitative image analysis of estrogen receptor (ER), progesterone receptor (PR), and Ki-67”, in 12:R56.Google Scholar
- 5.Nowakowski, P., Bubak, M., Tomasz BartyÅ„ski, Tomasz GubaÅ‚a, Harezlak, D., Kasztelnik, M., Malawski, M., and Meizner, J., Cloud computing infrastructure for the VPH community, J. Comput. Sci., 2017. ISSN 1877-7503.Google Scholar
- 7.Shakil, K. A., Zareen, F. J., Alam, M., and Jabin, S., BAMHealthCloud: A biometric authentication and data management system for healthcare data in cloud. J. King Saud University - Computer and Information Sciences, 2017, ISSN 1319-1578.Google Scholar
- 11.Yin, F. et al., A cloud-based system for automatic glaucoma screening. 37th Ann. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Milan 2015:1596–1599, 2015.Google Scholar
- 17.Issac, A., Parthasarthi, M., and Dutta, M. K., An adaptive threshold based algorithm for optic disc and cup segmentation in fundus images. 2nd Int. Conf. Sign. Process. Integ. Netw. (SPIN), Noida 2015:143–147, 2015.Google Scholar
- 19.Issac, A., Sengar, N., Singh, A., Sarathi, M. P., and Dutta, M. K., Automated computer vision method for optic disc detection from non-uniform illuminated digital fundus images. 2nd Int. Conf. Commun. Control Intell. Syst. (CCIS), Mathura 2016:76–80, 2016. https://doi.org/10.1109/CCIntelS.2016.7878204.
- 20.Partha Sarathi, M., Dutta, M. K., Singh, A., and Travieso, C. M., Blood vessel inpainting based technique for efficient localization and segmentation of optic disc in digital fundus images. Biomed. Sign. Process. Contrl 25:108–117, ISSN 1746-8094, 2016. https://doi.org/10.1016/j.bspc.2015.10.012.CrossRefGoogle Scholar
- 23.Soorya, M., Issac, A., and Dutta, M. K., An automated and robust image processing algorithm for glaucoma diagnosis from fundus images using novel blood vessel tracking and bend point detection. Int. J. Med. Inform. 110:52–70.Google Scholar