Predicting Severity of Diabetic Retinopathy using Deep Learning Models

Shivsharan, Nitin; Ganorkar, S. R.

doi:10.47392/irjash.2021.022

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison was done based on the maximum accuracy. The proposed model achieved an accuracy of 91% for five class classifications, outperforming the Simple CNN, VGG16 and DenseNet models used in [34] which had an accuracy of 81.7%. The proposed extended ResNet model performed around 10% better when compared to the Modified Xception model proposed in [24] and ensemble of CNN model [36].…”

Section: Comparing the Model Performancementioning

confidence: 91%

“…• Next, positive and negative weighted Gaussian filter were combined to form a custom Gaussian based mask. Gaussian blur or Gaussian smoothing is used to blur the images using a Gaussian function [34]. This is used in order to remove noise from the images.…”

Section: Image Pre-processingmentioning

confidence: 99%

“…The proposed extended ResNet model performed around 10% better when compared to the Modified Xception model proposed in [24] and ensemble of CNN model [36]. Simple CNN [34] 73% VGG16 [34] 5 81.9% DenseNet [34] 81.7% 2022 Proposed ResNet2.0 5 91%…”

Section: Comparing the Model Performancementioning

confidence: 99%

See 2 more Smart Citations

Gaussian Blur Masked ResNet2.0 Architecture for Diabetic Retinopathy燚etection

Boruah¹,

Dehloo²,

Gupta³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is a serious hazard that can result in irreversible blindness if not addressed in a timely manner. Hence, numerous techniques have been proposed for the accurate and timely detection of this disease. Out of these, Deep Learning (DL) and Computer Vision (CV) methods for multiclass categorization of color fundus images diagnosed with Diabetic Retinopathy have sparked considerable attention. In this paper, we attempt to develop an extended ResNet152V2 architecture-based Deep Learning model, named ResNet2.0 to aid the timely detection of DR. The APTOS-2019 dataset was used to train the model. This consists of 3662 fundus images belonging to five different stages of DR: no DR (Class 0), mild DR (Class 1), moderate DR (Class 2), severe DR (Class 3), and proliferative DR (Class 4). The model was gauged based on ability to detect stage-wise DR. The images were pre-processed using negative and positive weighted Gaussian-based masks as feature engineering to further enhance the quality of the fundus images by removing the noise and normalizing the images. Upsampling and data augmentation methods were used to address the skewness of the original dataset. The proposed model achieved an overall accuracy of 91% and an area under the receiver-operating characteristic curve (AUC) score of 95.1%, outperforming existing Deep Learning models by around 10%. Furthermore, the class-wise F1 score for No DR was 92%, Mild DR was 82%, Moderate DR was 66%, Severe was DR 89% and Proliferative DR was 80%.

show abstract

Section: Comparing the Model Performancementioning

confidence: 91%

Section: Image Pre-processingmentioning

confidence: 99%

See 1 more Smart Citation

Gaussian Blur Masked ResNet2.0 Architecture for Diabetic Retinopathy燚etection

Boruah¹,

Dehloo²,

Gupta³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

Predicting Diabetic Retinopathy Severity with Deep Learning: A Survey of Fundus Image Analysis Technique

Sornil,

Sheeja Herobin Rani,

Sheeba

2024

2024 10th International Conference on Communication and Signal Processing (ICCSP)

View full text Add to dashboard Cite

A Deep Exposition of GAN and its applications

Azahad¹,

Hameeda²

2023

IJETMS

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have revolutionized the field of machine learning and artificial intelligence by providing a powerful framework for generating realistic and high-quality synthetic data. GANs consist of two networks, a generator that produces synthetic data and a discriminator that distinguishes between the synthetic data and real data. The two networks are trained together in a game-theoretic setting, where the generator tries to produce synthetic data that is similar to the real data, while the discriminator tries to distinguish between the two. This paper provides a deep exposition of GAN and its applications, starting with the basics of GANs, their architecture, and how they work. We then discuss the training process of GAN, the challenges associated with it, and the techniques used to address these issues. We also describe the different variants of GANs, including conditional GAN, progressive GAN, and style-based GAN, and their applications. Next, we provide a comprehensive overview of the various domains where GANs have been successfully applied, such as image and video synthesis, text generation, and music composition. We discuss the potential future directions of GANs and their applications, including research areas that need further investigation. Finally, we highlight the challenges and limitations associated with GANs, such as mode collapse, vanishing gradients, and instability, and the ethical and legal issues associated with their applications. We conclude by summarizing the key points of the paper and highlighting the potential of GANs as a tool for generating realistic and high-quality synthetic data.

show abstract

Predicting Severity of Diabetic Retinopathy using Deep Learning Models

Cited by 3 publications

References 7 publications

Gaussian Blur Masked ResNet2.0 Architecture for Diabetic Retinopathy燚etection

Gaussian Blur Masked ResNet2.0 Architecture for Diabetic Retinopathy燚etection

Predicting Diabetic Retinopathy Severity with Deep Learning: A Survey of Fundus Image Analysis Technique

A Deep Exposition of GAN and its applications

Contact Info

Product

Resources

About