DeepDiabetic An Identification System of Diabetic Eye Diseases Using Deep Neural Networks
ABSTARCT :
Diabetic retinopathy (DR) produces bleeding, exudation, and new blood vessel formation conditions. DR can damage the retinal blood vessels and cause vision loss or even blindness.
If DR is detected early, ophthalmologists can use lasers to create tiny burns around the retinal tears to inhibit bleeding and prevent the formation of new blood vessels, in order to prevent deterioration of the disease.
The rapid improvement of deep learning has made image recognition an effective technology; it can avoid misjudgments caused by different doctors’ evaluations and help doctors to predict the condition quickly. The aim of this paper is to adopt visualization and preprocessing in the ResNet-50 model to improve module calibration, to enable the model to predict DR accurately.
EXISTING SYSTEM :
The survey of various existing techniques provides a platform for the development of the novel techniques in this area as future work.
Existing Diabetic Eye recognition systems are heavily dependent on specific conditions, such as the distance of image acquisition and the stop-and-stare environment, which require significant user cooperation.
Most existing Diabetic Eye recognition algorithms are designed for highly controlled cooperative environments, which is the cause of their failure in non-cooperative environments, i.e., those that include noise, off-angles, motion blurs, glasses, hairs, specular reflection (SR), eyelids and eyelashes incorporation, and partially open eyes.
If the dark pixel exists inside the box because the dark pupil can be included in the box, the box position is adaptively moved into the lower direction until it does not include the dark pixel, and the average RGB value is extracted box.
When applying Machine Learning, false positive errors (non-Diabetic Eye pixel is incorrectly classified into Diabetic Eye pixel) exist in the pupil area.
DISADVANTAGE :
Diabetic Eye DenseNet is an end-to-end segmentation network that uses the complete image without prior pre-processing or other conventional image processing techniques with the best information gradient flow, which prevents the network from overfitting and vanishing gradient problem.
To address the issues of accurate segmentation without prior pre-processing and to develop a robust scheme for all types of environments, this study presents a densely connected fully convolutional network (Diabetic EyeDenseNet)-based approach to detect an accurate Diabetic Eye boundary with better information gradient flow due to dense connectivity.
To address the Diabetic Eye segmentation issues in challenging situations by visible light and near-infrared light camera sensors, this paper proposes a densely connected fully convolutional network (Diabetic EyeDenseNet), which can determine the true Diabetic Eye boundary even with inferior-quality images by using better information gradient flow between the dense blocks.
PROPOSED SYSTEM :
Diabetic Retinopathy (DR) is a leading cause of blindness among adults, and its early detection is essential for preventing irreversible vision loss. Manual screening for DR is time-consuming, requiring highly trained professionals to examine retinal images. Artificial Intelligence (AI), particularly Deep Learning (DL) models, offers an opportunity to automate this process, enabling faster and more accurate diagnosis.
ResNet-50 (Residual Network with 50 layers) is one of the most successful deep learning architectures used for image classification tasks. Its deep residual structure helps in mitigating the vanishing gradient problem, making it well-suited for training on large-scale image datasets like those used for DR detection.
ADVANTAGE :
Interpretable models allow users and stakeholders to understand how decisions are made, which builds trust and facilitates validation of the model’s results.
In fields like healthcare and finance, interpretable models help meet regulatory requirements that demand explainability in automated decision-making processes.
High accuracy ensures that the framework provides dependable and precise diagnoses, which is critical in high-stakes applications such as medical diagnosis.
Accurate diagnoses can lead to better decision-making and improved outcomes, whether in healthcare, predictive maintenance, or other applications.
|