Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC)

Das, Dolly; Biswas, Saroj Kumar; Bandyopadhyay, Sivaji

doi:10.1007/s11042-022-14165-4

Cited by 37 publications

(8 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the three models, ResNet50 produced the best classification accuracy. On the contrary, in separate research [32], Das et al found that ResNet50 is the most overfitted model among the 26 state-of-the-art deep learning models. According to the experiments, EfficientNetB4 is the most optimal model for DR classification, followed by Inception-ResNet-v2 and NASNetLarge in the second and third positions, respectively.…”

Section: Related Workmentioning

confidence: 96%

Toward Lightweight Diabetic Retinopathy Classification: A Knowledge Distillation Approach for Resource-Constrained Settings

Islam,

Jony,

Hasan

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Diabetic retinopathy (DR), a consequence of diabetes, is one of the prominent contributors to blindness. Effective intervention necessitates accurate classification of DR; this is a need that computer vision-based technologies address. However, using large-scale deep learning models for DR classification presents difficulties, especially when integrating them into devices with limited resources, particularly in places with poor technological infrastructure. In order to address this, our research presents a knowledge distillation-based approach, where we train a fusion model, composed of ResNet152V2 and Swin Transformer, as the teacher model. The knowledge learned from the heavy teacher model is transferred to the lightweight student model of 102 megabytes, which consists of Xception with a customized convolutional block attention module (CBAM). The system also integrates a four-stage image enhancement technique to improve the image quality. We compared the model against eight state-of-the-art classifiers on five evaluation metrics; the experiments show superior performance of the model over other methods on two datasets (APTOS and IDRiD). The model performed exceptionally well on the APTOS dataset, achieving 100% accuracy in binary classification and 99.04% accuracy in multi-class classification. On the IDRiD dataset, the results were 98.05% for binary classification accuracy and 94.17% for multi-class accuracy. The proposed approach shows promise for practical applications, enabling accessible DR assessment even in technologically underdeveloped environments.

show abstract

Section: Related Workmentioning

confidence: 96%

Toward Lightweight Diabetic Retinopathy Classification: A Knowledge Distillation Approach for Resource-Constrained Settings

Islam,

Jony,

Hasan

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The model built in [14] can be implemented as a mobile application to support doctors in the treatment of patients with diabetic retinopathy. A complex model using several models of neural networks is proposed in [15]. In [16] and [17], the advantages of the DenseNet architecture in determining the degree of diabetic retinopathy are given.…”

Section: Fig 1: Comparison Between Normal and Diabetic Retinal Images...mentioning

confidence: 99%

Features of the Modification of the Inceptionresnetv2 Architecture and the Creation of a Diagnostic System for Determining the Degree of Damage to Retinal Vessels

PROCHUKHAN

2024

CSIT

View full text Add to dashboard Cite

Diabetic retinopathy is a retinal disease caused by diabetes. The progression of this disease can lead to blindness. Every year, the number of patients with this disease increases. Diabetic retinal damage can be slowed if it is diagnosed early. The article describes the features of the creation of a neural network model and the development of a system with high accuracy rates for the recognition of diabetic retinopathy. The advantages of the InceptionResNetv2 convolutional neural network architecture are considered. This network uses residual connections that help facilitate the learning process. InceptionResNetv2 uses different methods to reduce the dimensionality of the feature map, making it more economical in terms of memory and computation. This model has a number of advantages compared to other networks. InceptionResNetv2 can be applied to blood vessel segmentation in eye images with different resolutions. In the study, modification of InceptionResNetv2 was carried out. The use of additional MaxPooling and Dense layers improved the speed and accuracy of the InceptionResNetv2 convolutional neural network. The Dropout layer is effectively used to prevent overtraining. The system for determining the degree of retinal damage of diabetic origin is implemented in the Python programming language. Model layers are built using the Keras library. Images from the set of EyePacs were processed by methods of cropping the black frames with a Gaussian blur filter and minimizing the effect of changing the position of the images. During the research, it was found that 21 epochs are needed to achieve maximum accuracy. The program calculates the probability of an image belonging to a certain class with high accuracy. The recognition accuracy rate for class 1 was 98.6%, for class 2 - 98.5%, for class 3 - 98.3%, for class 4 - 98.15%, for class 5 - 98.1%.

show abstract

“…By studying the style classification of ink painting works [1][2], we can gain a deeper understanding of the historical background, creative motivation, and artistic techniques of these art works, providing more accurate and comprehensive information and analysis for art history and cultural research [3]. Therefore, the background and significance of studying the style classification of ink painting works lies in inheriting and protecting traditional art, promoting the development of art history and cultural research, and enhancing people's understanding and appreciation of traditional art.…”

Section: Introductionmentioning

confidence: 99%

A style classification algorithm for ink painting based on deep network feature aggregation

Zhang

2024

International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023)

View full text Add to dashboard Cite

This study proposes a style classification algorithm for ink painting works based on deep network feature aggregation. Introduce the deep classification regression tree feature aggregation method, use Bayes discriminant criterion, obtain probability density function, and extract the style features of ink painting works. Based on this, a sample dataset for ink painting style classification is constructed, and the Apriori association rule is used to use the corresponding ink painting style category as the final output result of the classifier to complete the classification. The experimental results show that the research method has good performance in extracting style features of ink painting, with short time consumption, low classification error, and high fault tolerance.

show abstract

Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC)

Cited by 37 publications

References 78 publications

Toward Lightweight Diabetic Retinopathy Classification: A Knowledge Distillation Approach for Resource-Constrained Settings

Toward Lightweight Diabetic Retinopathy Classification: A Knowledge Distillation Approach for Resource-Constrained Settings

Features of the Modification of the Inceptionresnetv2 Architecture and the Creation of a Diagnostic System for Determining the Degree of Damage to Retinal Vessels

A style classification algorithm for ink painting based on deep network feature aggregation

Contact Info

Product

Resources

About