Identifying Retinal blood vessels is widely used for diagnosing eye diseases such as diabetic retinopathy, and glaucoma. Currently, doctors manually extract these vessels, which is a challenging and time-consuming process that often leads to errors. In this paper, a new method is proposed for Retinal blood vessel extraction, which includes three basic parts. First, the noise in the image is removed. Next, the center lines of the vessel are extracted. Finally, the blood vessels of the Retinal Images are extracted using the area expansion and noise removal method. The proposed method is applied to the Images of the DRIVE test set and its efficiency is evaluated using four different metrics: sensitivity, specificity, accuracy, and precision. The average results for accuracy, specificity, sensitivity, and accuracy in the proposed method are 0.92896, 0.98965, 0.91756, and 0.96578, respectively.

Diabetic Retinopathy is one of the most important reasons of blindness which causes serious damage in the retina. The aim of this research is to detect one lesions of the retina, named Exudates automatically with Image processing techniques.Preprocessing is the first step of proposed algorithm. After preprocessing, the optic disc was detected and removed from the Retinal image due to the same color of OD and the exudates. Next, the HSV format of image has been used where the H and V channels, standard deviation on green channel of Retinal image and the background removal features were used as input of the system. The Fuzzy C-mean algorithm is used for classification. In this research the databases were Diaretdb0 and Diaretdb1. The results show 88.86% for Sensitivity and 99.98% for Specificity.Also, the result for PPV was 95.66% and the Accuracy was 99.90%.

To stop vision loss from glaucoma, early identification and regular screening are crucial. Convolutional neural networks (CNN) have been effectively used in recent years to diagnose glaucoma automatically from color fundus pictures. CNNs can extract distinctive characteristics directly from the fundus pictures, as opposed to the current automatic screening techniques. In this study, a CNN-based deep learning architecture is created for the categorization of normal and glaucomatous fundus pictures. In this paper, we propose a deep learning-based framework for the detection of glaucoma based on Retinal Images. Our proposed approach utilizes the two CNN-based models, namely Inception and DenseNet, in order to classify the input Images. We also show the impact of transfer learning on the training and the validation processes and put forward an effective pipeline with lower trainable parameters for the target task. Our experiments on a collected dataset demonstrate the efficacy of the proposed model by achieving an accuracy of 93. 84%, a precision of 92. 83%, and a recall of 95. 00%.

Purpose: To present a novel automated method for tracking and detection of Retinal blood vessels in funds Images. Methods: For every pixel in Retinal Images, a feature vector was computed utilizing multiscale analysis based on Gabor filters. To classify the pixels based on their extracted features as vascular or non-vascular, various classifiers including Quadratic Gaussian (QG), K-Nearest Neighbors (KNN), and Neural Networks (NN) were investigated. The accuracy of classifiers was evaluated using Receiver Operating Characteristic (ROC) curve analysis in addition to sensitivity and specificity measurements. We opted for an NN model due to its superior performance in classification of Retinal pixels as vascular and non-vascular.Results: The proposed method achieved an overall accuracy of 96.9%, sensitivity of 96.8%, and specificity of 97.3% for identification of Retinal blood vessels using a dataset of 40 Images. The area under the ROC curve reached a value of 0.967. Conclusion: Automated tracking and identification of Retinal blood vessels based on Gabor filters and neural network classifiers seems highly successful. Through a comprehensive optimization process of operational parameters, our proposed scheme does not require any user intervention and has consistent performance for both normal and abnormal Images.

This paper presents an automated method for detecting microaneurysms in the Retinal angiographic Images by using image processing techniques. In the presented method, in order to fade or remove the pseudo Images, first Retinal Images are pre-processed. Then microaneurysms are identified by circular Hough transform. In the existing methods of detecting microaneurysms, it is necessary to identify the vessels in the surface of the retina and to remove them from the background of the image. But in the proposed method, first by using the circular Hough transform the central point of the microaneurysms lesion is identified. Then by using the region growing technique, the total areas of pixels associated with these lesions are identified. In this proposed method due to the removal of the vascular diagnosis which has been very time consuming, the speed of the algorithm has significantly been increased. Results received from the Retinal Images of five patients show that the accuracy of the proposed method in detecting microaneurysms is about %88.5 that in comparison with other existing methods has higher speed and more accuracy.

The development of automated diagnostic tools is essential for efficiently analyzing medical data, especially for conditions like diabetic retinopathy, a leading cause of vision impairment and blindness in adults. The APTOS 2019 blindness detection dataset, with its comprehensive Retinal Images, is critical for developing these tools. This study leverages the Pyramid Vision Transformer (PVT) to enhance accuracy and efficiency in detecting diabetic retinopathy. Unlike the Vision Transformer (ViT), which incurs high computational costs and yields low-resolution outputs due to its single-scale structure, PVT’s pyramid architecture enables efficient multi-scale feature representation. This allows for effective management of large feature maps and improved resolution, both essential for precise image-based diagnoses. By implementing PVT, our approach demonstrates improved accuracy and resource efficiency, outperforming traditional CNN methods. Extensive experiments demonstrate that PVT significantly improves detection and classification accuracy, making it a valuable tool for clinical applications. The model achieved 92.38% accuracy and an AUC of 99.58%. Future research will focus on optimizing the model and exploring clinical integration.