Enhanced Eye Disease Detection with YOLOv10 and Convolutional Neural Networks (CNN) in Deep Learning

In this study, we present an eye disease detection and prevention solution based on deep learning techniques, CNN and YOLOv10. The main objective of this system is to detect multiple localized eye viruses such as Cataracts, Squint and Chalazion from retinal images and OCT scans using YOLOv10. The system provides an initial accuracy of almost 97%, which should not be underestimated as a first attempt. From a clinical perspective, the false positive rate is 5% for diagnosing diabetic retinopathy, 94.0.3% for diagnosing cataracts, 2%, 92% for other clinical indications and the accuracy of diagnosing age- related mandibular degeneration exposure is 1%. Secondly, it has a real-time detection system, which means that the patient can be treated immediately at the time when the first symptoms of the disease appear. The proposed methods of transfer learning, data enrichment and optimization make the model more efficient. The proposed system from the above model will have an impact on the fields of clinical practice, telemedicine and personalized medicine which helping to ensure better eye health management in all circumstances. In this study, You Only Look Once version 10 algorithm used for eye determine disease detection. Transfer learning, data enrichment and fine-tuning are used in the framework to improve the predictive model. However, Eye diseases can be difficult to detect in its early stages and the diagnostic process can be time- consuming even for experienced experts.