Volume 15, Issue 6 And S7 (Artificial Intelligence- In Press 2025)
J Research Health 2025, 15(6 And S7): 4-4 |
Back to browse issues page
Ethics code: 0
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Chellapandi A, Rengaraj A, Kaliannan S. Analyzing the Model Performances of Dot Hemorrhages Pattern Recognition Using Deep Neural Networks. J Research Health 2025; 15 (6) :4-4
URL: http://jrh.gmu.ac.ir/article-1-2889-en.html
URL: http://jrh.gmu.ac.ir/article-1-2889-en.html
1- SRM Institute of Science and Technology Ramapuram Campus, Tamilnadu, India
2- SRM Institute of Science and Technology Ramapuram Campus, Tamilnadu, India ,arthir2@srmist.edu.in
2- SRM Institute of Science and Technology Ramapuram Campus, Tamilnadu, India ,
Abstract: (30 Views)
Background: Diabetic Retinopathy (DR) is a leading cause of blindness, and DR progression can be avoided by detecting dot hemorrhages (DH) early. Manual diagnosis is frequently subjective and time-consuming, which emphasizes the necessity for automated methods.
Methods: Using machine learning (ML) and artificial intelligence (AI), this work suggests an automated DH detection system. After preprocessing retinal fundus images with CLAHE, a modified VGG-16 Convolutional Neural Network (CNN) is used to extract features. Support Vector Machine (SVM), Random Forest (RF), and Linear Regression (LR) models are used to classify both local and global features.
Results: The proposed approach is highly effective in detecting and classifying Dot Hemorrhages (DH) associated with Diabetic Retinopathy (DR). When tested on the APTOS dataset, the model obtains an overall accuracy of 93.26% for DH identification and classification. This shows that the Convolutional Neural Network (CNN) is extremely good in learning the distinguishing characteristics of hemorrhagic lesions from retinal fundus images. To confirm the suggested approach's efficiency, comparative research was carried out using three traditional machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and Linear Regression (LR). Among them, the Random Forest classifier has the greatest accuracy of 92.4%, surpassing both SVM and LR.
Conclusion: The research work introduces a VGG16-based convolutional neural network (CNN) that detects retinal hemorrhages in the APTOS dataset with an accuracy of 93.26%. Experimental results show that the Leaky ReLU activation function improves image classification performance, whereas the Adam and Adadelta optimizers consistently improve CNN-based learning. Finally, the research shows that deep learning-driven dynamic image analysis is a reliable and effective method for automated identification and categorization of dot hemorrhages, paving the way for early and accurate diabetic retinopathy screening systems.
Methods: Using machine learning (ML) and artificial intelligence (AI), this work suggests an automated DH detection system. After preprocessing retinal fundus images with CLAHE, a modified VGG-16 Convolutional Neural Network (CNN) is used to extract features. Support Vector Machine (SVM), Random Forest (RF), and Linear Regression (LR) models are used to classify both local and global features.
Results: The proposed approach is highly effective in detecting and classifying Dot Hemorrhages (DH) associated with Diabetic Retinopathy (DR). When tested on the APTOS dataset, the model obtains an overall accuracy of 93.26% for DH identification and classification. This shows that the Convolutional Neural Network (CNN) is extremely good in learning the distinguishing characteristics of hemorrhagic lesions from retinal fundus images. To confirm the suggested approach's efficiency, comparative research was carried out using three traditional machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and Linear Regression (LR). Among them, the Random Forest classifier has the greatest accuracy of 92.4%, surpassing both SVM and LR.
Conclusion: The research work introduces a VGG16-based convolutional neural network (CNN) that detects retinal hemorrhages in the APTOS dataset with an accuracy of 93.26%. Experimental results show that the Leaky ReLU activation function improves image classification performance, whereas the Adam and Adadelta optimizers consistently improve CNN-based learning. Finally, the research shows that deep learning-driven dynamic image analysis is a reliable and effective method for automated identification and categorization of dot hemorrhages, paving the way for early and accurate diabetic retinopathy screening systems.
Keywords: Diabetic Retinopathy (DR), Dot Hemorrhages (DH), Convolutional Neural Networks (CNN), Deep Learning (DL), VGG-16.
Type of Study: Orginal Article |
Subject:
● Artificial Intelligence
Received: 2025/08/22 | Accepted: 2025/11/1 | Published: 2025/11/1
Received: 2025/08/22 | Accepted: 2025/11/1 | Published: 2025/11/1
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
This is an open access article distributed under the terms of the Creative Commons Attribution License (CC-By-NC), which permits use, distribution, and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Contact Information
