Text

DETEKSI PENYAKIT DIABETIC RETINOPATHY PADA CITRA RETINA MENGUNAKAN RETINANET DENGAN BACKBONE RESNET 101

---

Penilaian

---

The retina is the thinnest cell part on the inside of the eye which has 2 cell parts, namely rod and cone cells. The retina consists of two structures: the blood vessels and the macula. Diabetic Retinopathy (DR) is a disease that occurs due to too high sugar levels in the blood so that it can clog blood vessels and stop blood supply. Diabetic retinopathy attacks the vision, more precisely occurs in the retinal blood vessels and can cause vision problems. Residual Network (ResNet) is an artificial neural network created to anticipate low accuracy. For this reason, ResNet is used to create artificial neural networks with deep layers to get high accuracy. This study presents a method for disease detection in retinal images using the STARE dataset and RETINANET architecture with backbone ResNet-101. The data annotation process is carried out to identify the characteristics of the disease in retinal images using the labelimg application. The proposed method with the STARE dataset gets an average value with a precision for diabetic retinopathy of 84.706% , average precision of 74.48% and intersection over union of 84.7%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207004277	T80570	T805702022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T805702022

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xIii, 48 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.680 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Local Area Network
Jurusan Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment