Skripsi
DETEKSI PENYAKIT DIABETIC RETINOPATHY PADA CITRA RETINA MENGGUNAKAN RETINANET DENGAN BACKBONE RESNET-50
This research aims to develop a method for detecting Diabetic Retinopathy (DR) in retinal images using the RETINANET architecture with a ResNet-50 backbone. DR is a serious complication in individuals with diabetes mellitus, leading to damage to the blood vessels in the retina and, in severe cases, blindness. ResNet (Residual Network) is chosen as the neural network architecture to deepen the model and enhance detection accuracy. The approach utilizes the STARE dataset and involves data annotation processes using labeling applications and Roboflow to identify disease characteristics in retinal images. The proposed method achieves satisfactory results, with an precision value of 84.7% for Diabetic Retinopathy, an average precision of 74.4%, and an intersection over union value of 84.7%. Regular monitoring and early detection of DR are crucial in preventing permanent eye damage, and this approach significantly contributes to these efforts through the application of image processing technology and artificial neural networks.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407000546 | T138497 | T1384972023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available