scholarly journals Prediction diabetic retinopathy from retinal fundus images via artificial neural network

2021 ◽  
Author(s):  
M. Akif Yenikaya ◽  
Erdal Güvenoğlu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Diabetic Retinopathy ◽  
Fundus Images ◽  
Retinal Fundus Images ◽  
Artificial Neural ◽  
Retinal Fundus

scholarly journals Transfer Learning Based MA Detection (TL-MAD)

2020 ◽  
Vol 9 (3) ◽  
pp. 3653-3656
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Automatic Detection ◽  
Microvascular Complication ◽  
Fundus Images ◽  
Main Symptom ◽  
Retinal Fundus Images ◽  
Retinal Fundus

Diabetic Retinopathy (DR) is a microvascular complication of Diabetes that can lead to blindness if it is severe. Microaneurysm (MA) is the initial and main symptom of DR. In this paper, an automatic detection of DR from retinal fundus images of publicly available dataset has been proposed using transfer learning with pre-trained model VGG16 based on Convolutional Neural Network (CNN). Our method achieves improvement in accuracy for MA detection using retinal fundus images in prediction of Diabetic Retinopathy.

scholarly journals Image Analysis of Diabetic Retinopathy Disease Based on Artificial Neural Network Algorithms

2020 ◽  
Vol 4 (2) ◽  
pp. 201-209
Author(s):  
Tri Astuti ◽  
Gesha Agus Setiawan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Diabetic Retinopathy ◽  
Gabor Filter ◽  
Fundus Images ◽  
Feature Extraction Method ◽  
Comparison Results ◽  
Network Methods ◽  
Artificial Neural ◽  
F Measure

Diabetic retinopathy is a complication of diabetes in the form of damage to the retina of the eye. High levels of glucose in the blood are the cause of small capillary blood vessels to rupture and can cause blindness. The signs of this disease can only be seen using retinal fundus images. To identify diabetic retinopathy, a computerized process and analysis are needed, one of which uses artificial neural network methods to determine its performance so that it will help the doctor in analyzing the disease and diagnosing whether a patient suffering from diabetic retinopathy or not. Texture feature extraction method using Gabor filter can represent feature value information that is skewness, kurtosis, mean, entrophy, and variance to be processed at the identification stage using artificial neural network methods. The comparison results of the DIARETDB0 dataset testing with the total of 130 fundus images using the backpropagation ANN method before randomizing the data yielded an accuracy value of 82.30%, a precision value of 71.28%, a recall value of 82.30%, and an f-measure of 76.39%. Whereas after randomizing the data for 30 times, the results of accuracy value were higher than before randomizing the data, namely the accuracy value of 83.07%, the precision value of 71.39%, the recall value of 83.07% and f-measure value of 76.78%. The tests carried out included in good classification.  

scholarly journals Pengaruh Preprocessing Terhadap Klasifikasi Diabetic Retinopathy dengan Pendekatan Transfer Learning Convolutional Neural Network

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Juan Elisha Widyaya ◽  
Setia Budi
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Early Stage ◽  
Careful Examination ◽  
Fundus Images ◽  
Fundus Image ◽  
Retinal Fundus Image ◽  
Retinal Fundus Images ◽  
Retinal Fundus

Diabetic retinopathy (DR) is eye diseases caused by diabetic mellitus or sugar diseases. If DR is detected in early stage, the blindness that follow can be prevented. Ophthalmologist or eye clinician usually decide the stage of DR from retinal fundus images. Careful examination of retinal fundus images is time consuming task and require experienced clinicians or ophthalmologist but a computer which has been trained to recognize the DR stages can diagnose and give result in real-time manner. One approach of algorithm to train a computer to recognize an image is deep learning Convolutional Neural Network (CNN). CNN allows a computer to learn the features of an image, in our case is retinal fundus image, automatically. Preprocessing is usually done before a CNN model is trained. In this study, four preprocessing were carried out. Of the four preprocessing tested, preprocessing with CLAHE and unsharp masking on the green channel of the retinal fundus image give the best results with an accuracy of 79.79%, 82.97% precision, 74.64% recall, and 95.81% AUC. The CNN architecture used is Inception v3.

Two-Tier Grading System for NPDR Severities of Diabetic Retinopathy in Retinal Fundus Images

2020 ◽  
Vol 14 ◽  
Author(s):  
Charu Bhardwaj ◽  
Shruti Jain ◽  
Meenakshi Sood
Keyword(s):  
Diabetic Retinopathy ◽  
Statistical Analysis ◽  
Early Stage ◽  
Image Feature ◽  
Grading System ◽  
Fundus Images ◽  
Fundus Image ◽  
Retinal Fundus Images ◽  
Retinal Fundus ◽  
Timely Treatment

: Diabetic Retinopathy is the leading cause of vision impairment and its early stage diagnosis relies on regular monitoring and timely treatment for anomalies exhibiting subtle distinction among different severity grades. The existing Diabetic Retinopathy (DR) detection approaches are subjective, laborious and time consuming which can only be carried out by skilled professionals. All the patents related to DR detection and diagnoses applicable for our research problem were revised by the authors. The major limitation in classification of severities lies in poor discrimination between actual lesions, background noise and other anatomical structures. A robust and computationally efficient Two-Tier DR (2TDR) grading system is proposed in this paper to categorize various DR severities (mild, moderate and severe) present in retinal fundus images. In the proposed 2TDR grading system, input fundus image is subjected to background segmentation and the foreground fundus image is used for anomaly identification followed by GLCM feature extraction forming an image feature set. The novelty of our model lies in the exhaustive statistical analysis of extracted feature set to obtain optimal reduced image feature set employed further for classification. Classification outcomes are obtained for both extracted as well as reduced feature set to validate the significance of statistical analysis in severity classification and grading. For single tier classification stage, the proposed system achieves an overall accuracy of 100% by k- Nearest Neighbour (kNN) and Artificial Neural Network (ANN) classifier. In second tier classification stage an overall accuracy of 95.3% with kNN and 98.0% with ANN is achieved for all stages utilizing optimal reduced feature set. 2TDR system demonstrates overall improvement in classification performance by 2% and 6% for kNN and ANN respectively after feature set reduction, and also outperforms the accuracy obtained by other state of the art methods when applied to the MESSIDOR dataset. This application oriented work aids in accurate DR classification for effective diagnosis and timely treatment of severe retinal ailment.

scholarly journals Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3922
Author(s):  
Sheeba Lal ◽  
Saeed Ur Rehman ◽  
Jamal Hussain Shah ◽  
Talha Meraj ◽  
Hafiz Tayyab Rauf ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Feature Fusion ◽  
Speckle Noise ◽  
Fundus Images ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Adversarial Attack ◽  
Retinal Fundus Images ◽  
Attacks And Defenses ◽  
Retinal Fundus

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for the Diabetic Retinopathy recognition problem, which is considered a state-of-the-art endeavor. Results obtained on the retinal fundus images, which are prone to adversarial attacks, are 99% accurate and prove that the proposed defensive model is robust.

Sign in / Sign up

Export Citation Format

Share Document