Research PapersNo Access

INTEGRATING FUZZY C-MEANS AND MAHALANOBIS METRIC CLASSIFICATION FOR EXUDATE DETECTION IN COLOR FUNDUS IMAGING

MADHURI TASGAONKAR

Cummins College of Engineering for Women, Pune 411052, India

Corresponding author.

Search for more papers by this author

and

MADHURI KHAMBETE

Cummins College of Engineering for Women, Pune 411052, India

Search for more papers by this author

https://doi.org/10.1142/S0219519415500852Cited by:2 (Source: Crossref)

Abstract

Diabetes affects retinal structure of a diabetic patient by generating various lesions. Early detection of these lesions can avoid the loss of vision. Automation of detection process can be made easily feasible to masses by the use of fundus imaging. Detection of exudates is significant in diabetic retinopathy (DR) as they are earlier signs and can cause blindness. Finding the exact location as well as correct number of exudates play vital role in the overall treatment of a patient. This paper presents an algorithm for automatic detection of exudates for DR. The algorithm combines the advantages of supervised and unsupervised techniques. It uses fuzzy-C means (FCM) segmentation on coarse level and mahalanobis metric for finer classification of segmented pixels. Mahalanobis criterion gives significance to most relevant features and thus proves a better classifier. The results are validated using DIARETDB0 and DIARETDB1 databases and the ground truth provided with it. This evaluation provided 95.77% detection accuracy.

Keywords:

AMSC: 22E46, 53C35, 57S20

References

K. Ramasamy , R. Raman and M. Tandon , Curr. Diab. Rep. 13 , 460 ( 2013 ) . Web of Science, Google Scholar
M. R. K. Mookiah et al. , Comput. Biol. Medi. 43 , 2136 ( 2013 ) . Web of Science, Google Scholar
O. Faust et al. , J. Med. Syst. 36 , 145 ( 2012 ) . Web of Science, Google Scholar
T. J. MacGillivray et al. , Brit. J. Radiol. 87 , 1040 ( 2014 ) . Web of Science, Google Scholar
C. Sinthanayothin et al. , Bri. J. Ophthalmol. 83 , 902 ( 1999 ) . Web of Science, Google Scholar
A. Osarehet al., Classification and localisation of diabetic-related eye disease, Comput VisionECCV 2002 (Springer, 2006) pp. 502–516. Google Scholar
P. Sharma , S. R. Nirmala and K. K. Sarma , J. Med. Imag. Health. Inf. 3 , 341 ( 2013 ) . Web of Science, Google Scholar
A. Feroui et al. , J. Mech. Med. Biol. 13 , ( 2013 ) . Link, Web of Science, Google Scholar
N. Yang et al. , J. Circuits. Syst. Comput. 22 , ( 2013 ) . Link, Web of Science, Google Scholar
V. Zeljkovicet al., Classification algorithm of retina images of diabetic patients based on exudates detection, Int. Conf. High Performance Computing and Simulation (HPCS) (IEEE, 2012) pp. 167–173. Google Scholar
H. F. Jaafar , A. K. Nandi and W. Al-Nuaimy , DETECTION OF EXUDATES FROM DIGITAL FUNDUS IMAGES USING A REGION-BASED SEGMENTATION TECHNIQUE , 19th European Signal Processing Conference (EUSIPCO 2011) ( 2011 ) . Google Scholar
A. Sopharak et al. , Comput. Med. Imag. Graphics. 32 , 720 ( 2008 ) . Web of Science, Google Scholar
W. Bu et al. , J. Softw. 8 , 2723 ( 2013 ) . Google Scholar
A. Osareh , B. Shadgar and R. Markham , IEEE. Trans. Inform. Technol. Biomed. IEEE. 13 , 535 ( 2009 ) . Web of Science, Google Scholar
M. García et al. , Comput. Meth. Prog. Bio. 93 , 9 ( 2009 ) . Web of Science, Google Scholar
A. Sopharak , B. Uyyanonvara and S. Barman , Sensors 9 , 2148 ( 2009 ) . Web of Science, Google Scholar
K. Wisaeng , N. Hiransakolwong and E. Pothiruk , Appl. Med. Inform. 32 , 33 ( 2013 ) . Google Scholar
R. Gonzalez and R. Woods , Digital Image Processing ( Pearson Education , 2003 ) . Google Scholar
C. M. Bishop , Pattern Recognition and Machine Learning ( Springer , 2006 ) . Google Scholar
A. Coates and A. Y. Ng, Neural Networks: Tricks of the Trade, LNCS (Springer, 2012) pp. 561–580. Google Scholar
X.-Y. Zhang, K. Huang and C.-L. Liu, Feature transformation with class conditional decorrelation, IEEE 13th Int. Conf. Data Mining (ICDM) (IEEE, 2013) pp. 887–896. Google Scholar
H.-K. Hsiao et al. , Expert. Syst. Appl. 39 , 10600 ( 2012 ) . Web of Science, Google Scholar
Agurto Rios CP, Detection and Classification of Diabetic Retinopathy Pathologies in Fundus Images, 2013 . Google Scholar
W. Hsuet al., The role of domain knowledge in the detection of retinal hard exudates, Proc. 2001 IEEE Comput. Soc. Conf. Comput. Vis. Pattern. Recognit. (CVPR)2 (2001) pp. II–246. Google Scholar
Ekstróm J, Mahalanobis' Distance Beyond Normal Distribution, 2011 . Google Scholar
S. Xiang , F. Nie and C. Zhang , Pattern. Recognit. 41 , 3600 ( 2008 ) . Web of Science, Google Scholar
DIARETDB0: Evaluation database and methodology for diabetic retinopathy algorithm, Available at: http://www.it.lut.fi/project/imageret/diaretdb0/ . Google Scholar
DIARETDB1–Diabetic Retinopathy Database and Evaluation Protocol, Version 2.1, Available at: http://www.it.lut.fi/project/imageret/diaretdb1_v2_1/ . Google Scholar