Convolutional Neural Network for Classification of Diabetic Retinopathy Grade

2020 ◽  
pp. 104-118
Author(s):  
Vanessa Alcalá-Rmz ◽  
Valeria Maeda-Gutiérrez ◽  
Laura A. Zanella-Calzada ◽  
Adan Valladares-Salgado ◽  
José M. Celaya-Padilla ◽  
...  
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network

scholarly journals Comparison of Convolutional Neural Network Model in Classification of Diabetic Retinopathy

2019 ◽  
Vol 9 (2) ◽  
pp. 141
Author(s):  
Hartanto Ignatius ◽  
Ricky Chandra ◽  
Nicholas Bohdan ◽  
Abdi Dharma
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Contrast Enhancement ◽  
Neural Network Model ◽  
Reasonable Accuracy ◽  
Deep Architecture

<p class="JGI-AbstractIsi">Untreated diabetes mellitus will cause complications, and one of the diseases caused by it is Diabetic Retinopathy (DR). Machine learning is one of the methods that can be used to classify DR. Convolutional Neural Network (CNN) is a branch of machine learning that can classify images with reasonable accuracy. The Messidor dataset, which has 1,200 images, is often used as a dataset for the DR classification. Before training the model, we carried out several data preprocessing, such as labeling, resizing, cropping, separation of the green channel of images, contrast enhancement, and changing image extensions. In this paper, we proposed three methods of DR classification: Simple CNN, Le-Net, and DRnet model. The accuracy of testing of the several models of test data was 46.7%, 51.1%, and 58.3% Based on the research, we can see that DR classification must use a deep architecture so that the feature of the DR can be recognized. In this DR classification, DRnet achieved better accuracy with an average of 9.4% compared to Simple CNN and Le-Net model.</p>

scholarly journals EfficientNetB3 Architecture for Diabetic Retinopathy Assessment using  Fundus Images

2021 ◽  
Author(s):  
Abdelali ELMOUFIDI ◽  
Hind Amoun
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Fundus Images ◽  
Retinal Area ◽  
Hard Exudate ◽  
Retinal Blood Vessels

Abstract Classification of the stages of diabetic retinopathy (DR) is considered a key step in the assessment and management of diabetic retinopathy. Due to the damage caused by high blood sugar to the retinal blood vessels, different microscopic structures can be occupied in the retinal area, such as micro-aneurysms, hard exudate and neovascularization. The convolutional neural network (CNN) based on deep learning has become a promising method for the analysis of biomedical images. In this work, representative images of diabetic retinopathy (DR) are divided into five categories according to the professional knowledge of ophthalmologists. This article focuses on the use of convolutional neural networks to classify background images of DR according to disease severity and on the application of pooling, Softmax Activation to achieve greater accuracy. The aptos2019-blindness-detection database makes it possible to verify the performance of the proposed algorithm.

scholarly journals Comparison of Convolutional Neural Network Model in Classification of Diabetic Retinopathy

2019 ◽  
Vol 9 (2) ◽  
pp. 141-150
Author(s):  
Hartanto Ignatius ◽  
Ricky Chandra ◽  
Nicholas Bohdan ◽  
Abdi Dharma
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Contrast Enhancement ◽  
Neural Network Model ◽  
Reasonable Accuracy ◽  
Deep Architecture

Untreated diabetes mellitus will cause complications, and one of the diseases caused by it is Diabetic Retinopathy (DR). Machine learning is one of the methods that can be used to classify DR. Convolutional Neural Network (CNN) is a branch of machine learning that can classify images with reasonable accuracy. The Messidor dataset, which has 1,200 images, is often used as a dataset for the DR classification. Before training the model, we carried out several data preprocessing, such as labeling, resizing, cropping, separation of the green channel of images, contrast enhancement, and changing image extensions. In this paper, we proposed three methods of DR classification: Simple CNN, Le-Net, and DRnet model. The accuracy of testing of the several models of test data was 46.7%, 51.1%, and 58.3% Based on the research, we can see that DR classification must use a deep architecture so that the feature of the DR can be recognized. In this DR classification, DRnet achieved better accuracy with an average of 9.4% compared to Simple CNN and Le-Net model.

scholarly journals Automated Diabetic Retinopathy Identification Using Convolutional Neural Network

2021 ◽  
Vol 10 (3) ◽  
pp. 1872-1882
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Convolution Neural Network ◽  
Phase Classification ◽  
Kappa Value

Classification phase is one of the important step for determining, analysing as well as diagnosing the diabetic retinopathy disorder. Nanostructures include red lesions, retinal hard macular exudates as well as Neovascularization would take up space aroundretina by the reason of devastation of veins. In order to computerise the technique pertaining to diabetic retinopathy phases categorization, a convolution neural network grounded method could be utilized. Colour fundus pictures of retina are collected during this work with aim of diabetic retinopathy classification among 5 phases by utilizing a convolution neural network. Convolution neural network with EfficientNet B5 network is employed for the phase classification of diabetic retinopathy disorder, a Kappa value (classification accuracy) of 88.48% is achieved.

LENS CLASSIFICATION ACCORDING TO THE TYPE OF LIGHT SPOT USING A NEURAL NETWORK

2020 ◽  
Vol 2020 (4) ◽  
pp. 4-14
Author(s):  
Vladimir Budak ◽  
Ekaterina Ilyina
Keyword(s):  
Neural Network ◽  
Light Intensity ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network ◽  
Beam Angle ◽  
New Model ◽  
Technical Parameters ◽  
Transfer Training ◽  
Trained Network

The article proposes the classification of lenses with different symmetrical beam angles and offers a scale as a spot-light’s palette. A collection of spotlight’s images was created and classified according to the proposed scale. The analysis of 788 pcs of existing lenses and reflectors with different LEDs and COBs carried out, and the dependence of the axial light intensity from beam angle was obtained. A transfer training of new deep convolutional neural network (CNN) based on the pre-trained GoogleNet was performed using this collection. GradCAM analysis showed that the trained network correctly identifies the features of objects. This work allows us to classify arbitrary spotlights with an accuracy of about 80 %. Thus, light designer can determine the class of spotlight and corresponding type of lens with its technical parameters using this new model based on CCN.

Method of determination of the text direction on the image with the use of convolutional neural network

2020 ◽  
pp. 96-99
Author(s):  
P.L. Nikolaev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Binary Classification ◽  
Synthetic Data ◽  
Real Data ◽  
Method Of Determination ◽  
Classification Of Images

This article deals with method of binary classification of images with small text on them Classification is based on the fact that the text can have 2 directions – it can be positioned horizontally and read from left to right or it can be turned 180 degrees so the image must be rotated to read the sign. This type of text can be found on the covers of a variety of books, so in case of recognizing the covers, it is necessary first to determine the direction of the text before we will directly recognize it. The article suggests the development of a deep neural network for determination of the text position in the context of book covers recognizing. The results of training and testing of a convolutional neural network on synthetic data as well as the examples of the network functioning on the real data are presented.

Sign in / Sign up

Export Citation Format

Share Document