IJSTR

International Journal of Scientific & Technology Research

Home Contact Us
ARCHIVES
ISSN 2277-8616











 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

IJSTR >> Volume 9 - Issue 4, April 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Hyper Parameter Tuned Deep Learning Based Lenet Architecture For Detection And Classification Of Diabetic Retinopathy Images

[Full Text]

 

AUTHOR(S)

K. Yazhini, Dr. D. Loganathan

 

KEYWORDS

Classification, Diabetic Retinopathy, Gradient, Kaggle, LeNet.

 

ABSTRACT

Diabetic retinopathy (DR) is a sickness appearing in the eye because of a rise in blood glucose level. Amongst the people under the age group of 70, half of the death is connected to diabetes. The earlier detection and medication could result in minimal loss of sight in various DR patients. When the signs of DR are detected, the seriousness of the disease needs to be validated for providing appropriate treatment. This study develops a new classification model for DR images by the use of deep learning based LetNet model. The proposed model involves a gradient descent (GD) based Hyper parameter tuned LeNet-5 model called GD-LeNet-5 model for the classification of DR images. The GD-LeNet-5 model involves a series of processes namely preprocessing, segmentation, feature extraction and finally classification. The presented model is tested using a DR dataset from Kaggle. The extensive experimental study clearly portrayed the superior outcome of the GD-LeNet-5 model with the maximum accuracy, sensitivity and specificity of 72.80%, 51.50% and 81.82% respectively.

 

REFERENCES

[1] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM 2017;60(May (6)):84–90.
[2] Whiting DR, Guariguata L, Weil C, Shaw J. IDF diabetes atlas: global estimates of the prevalence of diabetes for 2011 and 2030. Diabetes Res Clin Pract 2011;94(Dec (3)):311–21.
[3] Giacinto G , Roli F . “Design of effective neural network ensembles for image classification purposes”. Image Vision Comput 2001;19(9–10):699–707 .
[4] Singh N , Tripathi RC . Automated early detection of diabetic retinopathy using image analysis techniques. Int J Comput Appl 2010;8(Oct (2)):18–23 .
[5] SB S , Singh V . Automatic detection of diabetic retinopathy in non-dilated RGB retinal fundus images. Int J Comput Appl 2012;47(Jun (19)):26–32 .
[6] Bhatia K , Arora S , Tomar R . Diagnosis of diabetic retinopathy using machine learning classification algorithm. 2016 2nd international conference on next generation computing technologies (NGCT), October; 2016.
[7] Cunha-Vaz BSPJG . Measurement and mapping of retinal leakage and retinal thickness - surrogate outcomes for the initial stages of diabetic retinopathy. Curr Med Chem-Immunol EndocrMetab Agents 2002;2(Jun (2)):91–108 .
[8] Anandakumar H, Umamaheswari K. Supervised machine learning techniques in cognitive radio networks during cooperative spectrum handovers. Cluster Comput 2017;20:1–11. doi: 10.1007/s10586- 017- 0798- 3 .
[9] Omar M , KhelifiF , Tahir MA . Detection and classification of retinal fundus images exudates using region based multiscale LBP texture approach. 2016 international conference on control, decision and information technologies (CoDIT), April; 2016 .
[10] Welikala RA , Fraz MM , Williamson TH , Barman SA . The automated detection of proliferative diabetic retinopathy using dual ensemble classification. Int J Diagn Imaging 2015;2(Jun (2)) .
[11] Haldorai A , Ramu A , Chow C-O . Editorial: big data innovation for sustainable cognitive computing. Mob Netw Appl 2019;24(Jan):221–3 .
[12] Purandare M , Noronha K . Hybrid system for automatic classification of Diabetic Retinopathy using fundus images. 2016 online International conference on green engineering and technologies (IC-GET); Nov. 2016 .
[13] Bhatkar AP , Kharat GU . Detection of diabetic retinopathy in retinal images using MLP classifier. 2015 IEEE international symposium on nanoelectronic and information systems, December; 2015 .
[14] Partovi M , Rasta SH , Javadzadeh A . Automatic detection of retinal exudates in fundus images of diabetic retinopathy patients. J Anal Res Clin Med 2016;4(May (2)):104–9 .
[15] https://www.kaggle.com/c/diabetic-retinopathy-detection/data