An efficient adaptive histogram based segmentation and extraction model for the classification of severities on diabetic
- PDF / 901,690 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 21 Downloads / 202 Views
An efficient adaptive histogram based segmentation and extraction model for the classification of severities on diabetic retinopathy J. Vaishnavi 1 & S. Ravi 1
& A. Anbarasi
1
Received: 24 October 2019 / Revised: 24 June 2020 / Accepted: 29 June 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Diabetic retinopathy (DR) is an important retinal disease, which occurs commonly among diabetic patients. This disease severely injures the basic vision of the eye and results in blindness in several cases, which could be eliminated by earlier detection and medication. The existence of many classes in DR makes the diagnosis process difficult. To resolve this process, this paper introduces a new segmentation based classification model to classify the DR images effectively. The proposed model involves three main processes, namely, preprocessing, segmentation, feature selection and classification. The proposed method undergoes preprocessing and contrast-limited adaptive histogram equalization (CLAHE) model is applied for segmentation. AlexNet architecture is applied as a feature extractor to extract the useful set of feature vectors. Finally, softmax layer is utilized to classify the images into different stages of DR. The validation takes place using the publicly available Kaggle dataset. The experimental outcome indicates that the presented model achieves maximum classification rate with an accuracy of 95.86%, sensitivity of 92.00%, and specificity of 97.86% respectively. Keywords AlexNet . Classification . DR . Segmentation
* J. Vaishnavi [email protected] * S. Ravi [email protected] A. Anbarasi [email protected]
1
Department of Computer Science, School of Engineering and Technology, Pondicherry University, Pondicherry, India
Multimedia Tools and Applications
1 Introduction Diabetic retinopathy (DR) is a complication that affects the eye. The international diabetes federation estimated that 415 million people are living with diabetes in the world, which is estimated to be 1 in 11 of the world’s adult population [1]. To prevent from severe visual impairments, an early detection of the DR and prediction of its severity is most needed. To rule out the diabetic retinopathy, people with diabetes must have checked their vision atleast once annually. In India, around 61.3 million are suffering with diabetic mellitus. It is predicted that, by 2030, the estimation will increase to 101.2 million [28]. The two types of DR are Non-proliferative DR (NPDR) and Proliferative diabetic retinopathy (PDR). The NPDR is milder stage and its symptoms are less. The advanced stage of DR is PDR in which there exist new abnormal blood vessels in the retina. The signs of DR might be blurred vision, floaters, patches and may block the vision etc. Diabetic macular edema is another cause for the consequence of DR that causes swelling in the retinal area. DR may progress through four stages as mild non-proliferative, moderative non proliferative, severe non-proliferative and proliferative (Fig. 1). In mild
Data Loading...
