Abstract
Background
The macula is an important part of the human visual system and is responsible for clear and colour vision. Macular oedema happens when fluid and protein deposit on or below the macula of the eye and cause the macula to thicken and swell. Normally, it occurs due to diabetes called diabetic macular oedema. Diabetic macular oedema (DME) is one of the main causes of visual impairment in patients.
Aim
The aims of the present study are to detect and localize abnormalities in blood vessels with respect to macula in order to prevent vision loss for the diabetic patients.
Methods
In this work, a novel fully computerized algorithm is used for the recognition of various diseases in macula using both fundus images and optical coherence tomography (OCT) images. Abnormal blood vessels are segmented using thresholding algorithm. The classification is performed by three different classifiers, namely, the support vector machine (SVM), cascade neural network (CNN) and partial least square (PLS) classifiers, which are employed to identify whether the image is normal or abnormal.
Conclusion
The results of all of the classifiers are compared based on their accuracy. The classifier accuracies of the SVM, cascade neural network and partial least square are 98.33, 97.16 and 94.34%, respectively. While analysing DME using both images, OCT produced efficient output than fundus images. Information about the severity of the disease and the localization of the pathologies is very useful to the ophthalmologist for diagnosing disease and choosing the proper treatment for a patient to prevent vision loss.
Similar content being viewed by others
References
Acharya UR, Chua KC, Ng EYK (2008) Application of higher order spectra for the identification of diabetes retinopathy stages. J Med Syst 32:481–488
Agurto C, Murray V, Barriga E (2010) Multiscale AM-FM methods for diabetic retinopathy lesion detection. IEEE Trans Med Imaging 29:502–512
Spharak A, Uyyanonvara B, Barman S (2009) Automatic exudates detection from non-dilated diabetic retinopathy retinal images using fuzzy C-means clustering. Sensors 9:2148–2161
Aliaa Abdel-Haleim Abdel-Razik Youssif, Atef Zaki Ghalwash, and Amr Ahmed Sabry Abdel-Rahman Ghoneim (2008). Optic disc detection from normalized digital fundus images by means of a vessels direction matched filter, IEEE TRANSACTIONS ON MEDICAL IMAGING, 27.
Tariq A, Usman Akram M, Shaukat A, Shoab Khan A (2013) Automated detection and grading of diabetic maculopathy in digital retinal images. J Digit Imaging 4:803–812
Antal B, Hajdu A (2012) An ensemble-based system for microaneurysm detection and diabetic retinopathy grading. IEEE Trans Biomed Eng 59:1720–1726
Brankin, E. Muldrew, A., Black, N. (2006) The optimization of thresholding technique for the identification of choroidal neovascular membranes in exudative age-related macular degeneration. IEEE Symp Computer Based Medical System, Salt Lake City, US, Lee DJ, Nutter B, Antani S (eds.) IEEE Computer Society Press. 430–435.
Browning DJ, McOwen MD, Bowen RM Jr, O’Marah TL (2004) Comparison of the clinical diagnosis of diabetic macular edema with diagnosis by optical coherence tomography. Ophthalmology 111:712–715
Davis MD, Bressler SB, Aiello LP, Bressler NM, Browning DJ (2008) Comparison of time-domain OCT and fundus photographic assessments of retinal thickening in eyes with diabetic macular edema. Investig Ophthalmol 49:1745–1752
Clara IS, Maria G, Mayo A, Maria IL, Hornero R (2009) Retinal image analysis based on mixture models to detect hard exudates. Med Image Anal 13(4):650–658
Deepak K, Sivaswamy J (2012) Automatic assessment of macular oedema from colour retinal images. IEEE Trans Med Imag 31:766–776
Ege BM, Hejlese OK, Larsen OV, Moller K, Jennings B, Kerr D, Cavan DA (2000) Screening for diabetic retinopathy using computer based image analysis and statistical classification. Comput Meth Prog Bio 62:165–175
Foracchia, M., Grisan, E., and Ruggeri, A. (2004) Detection of optic disc in retinal images by means of a geometrical model of vessel structure, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 23, NO. 10
Gardner KG, Williamson D, Elliot AT (1996) Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool. Brit J Ophthalmol 11:940–944
Giancardo L, Ruggeri A, Chaum E (2011) A textureless macula swelling detection with multiple retinal fundus images. IEEE Trans Biomed Eng 58:795–799
Grisan, E., Ruggeri A, (2007). Segmentation of candidate dark lesions in fundus images based on local thresholding and pixel density, 29th Annual Int Conf IEEE EMBS, Lyon, France, Rousseau J, Delhomme G, Akay M (eds.) IEEE Engineering in Medicine and Biological Society 6735–6738.
Soares JVB, Leandro JJG, Cesar RM Jr, Jelinek HF, Michael Cree J (2006) Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE T Med Imaging 25:1214–1222
Kande, G.B., Subbaiah, V., Savithri, T.S. (2008) Segmentation of exudates and optic disc in retinal images, IEEE Conf Computer Vision, Graphics and Image Processing, Kolkata, India, Sural S (ed.) IEEE Computer Society. 535–542.
Ram K, Joshi GD, Sivaswamy J (2011) A successive clutter rejection based approach for early detection of diabetic retinopathy. IEEE Trans Biomed Eng 58:664–673
Kenneth, W., Tobin Edward Chaum V., Priya Govindasamy, Thomas Karnowski, P (2007) Detection of anatomic structures in human retinal imagery, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 26, NO. 12.
Krishnan, J.D.R., Kumar, A.S. (2008) Neural network based retinal image analysis. IEEE Conference on Image and Signal Processing, Sanya, China. 49–53.
Noronha K, Navya KT, Nayak PK (2013) Hypertensive retinopathy. International Journal of Computer Applications 1:7–11
Mahendran G, Dhanasekaran R (2015) Investigation of abnormalities for diabetic retinopathy. Int J Appl Eng Res 10:963–967
Murugeswari S, Sukanesh R (2015) Investigations on diabetic macular edema using motion pattern estimation to prevent vision loss ARPN. Journal of Engineering and Applied Sciences 10(7):2940–2947
Osareh, A. Mirmehdi, M., Thomas, B. (2002). Comparative exudates classification using support vector machine and neural networks. 5th International Conference on Medical Image Computing-Assisted Intervention, Tokyo, Japan. 413–420.
Meer P, Comaniciu D (2002) Mean shift robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603–619
Reza AW, Hati CES (2008) Automatic tracing of optic disc and exudates from colour fundus images using fixed and variables thresholds. J Med Syst 33:73–80
Shijian Lu (2011) Accurate and Efficient Optic Disc Detection and Segmentation by a Circular Transformation” IEEE Transactions on Medical Imaging 30(12):2126–2133
Tang L, Niemeijer M, Reinhardt JM (2013) Splat feature classification with application to retinal haemorrhage detection in fundus images. IEEE Trans Med Imaging 32:364–375
Usher D, Dumsky M, Himaga M (2004) Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening. Diabet Med 21:84–90
Murugeswari, S., Sukanesh, R. (2016), Assessment of severity level for diabetic macular oedema using machine learning algorithms circuits and systems, 7, 1098–1105.
Akram, MU, Khalid, S, Tariq, A, Khan, SA & Azam, F 2014, ‘Detection and Classification of Retinal Lesions for Grading of Diabetic Retinopathy’, Computers in Biology and Medicine 45(1):161–171
Priya, R & Aruna, P (2012) SVM and neural network based diagnosis of diabetic retinopathy’, International Journal of Computer Applications 41(1):6–12
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Murugeswari, S., Sukanesh, R. Investigations of severity level measurements for diabetic macular oedema using machine learning algorithms. Ir J Med Sci 186, 929–938 (2017). https://doi.org/10.1007/s11845-017-1598-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11845-017-1598-8