Skripsi

KLASIFIKASI DIABETIK RETINOPATI DIABETES MELITUS MELALUI CITRA FUNDUS RETINA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK

---

Diabetic retinopathy (DR) is a major complication of diabetes mellitus, characterized by damage to the retinal blood vessels and a high risk of blindness, particularly among individuals of productive age. Early detection of DR is essential, as the disease often presents no noticeable symptoms in its initial stages but can progress to permanent vision impairment if left untreated. This study aims to develop an automated classification model for diabetic retinopathy using deep learning methods based on retinal fundus images. The dataset used consists of 4,217 fundus images obtained from a public platform, with preprocessing steps including image quality filtering, resizing to 224×224 pixels, and data augmentation through horizontal flip, vertical flip, and 90-degree rotation. The data were split into training (80%), validation (10%), and testing (10%) sets. Four Convolutional Neural Network (CNN) architectures were employed: ResNet-50, VGG-19, DenseNet-121, and EfficientNet-B0, each trained over 50 epochs using the Adam optimizer and CrossEntropyLoss function. The results showed varying levels of accuracy across architectures, with the best kinerjance reaching 91.25%. This study demonstrates that integrating deep learning approaches with an understanding of DR progression based on diabetes duration can support the development of more accurate, efficient, and targeted early screening systems for diabetic patients. Keywords: Eye Diseases, Diabetic Retinopathy, Diabetes Mellitus, Fundus Images, Deep Learning, Convolutional Neural Network (CNN).

---

Availability

Detail Information

Series Title

-

Call Number

T1900622025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvii, 158 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

616.460 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Diabetes Melitus
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment