Skripsi

SEGMENTASI PEMBULUH DARAH RETINA PADA PENYAKIT DIABETIC RETINOPATHY MENGGUNAKAN METODE FRACTALNET CONVOLUTIONAL NEURAL NETWORK

---

Penilaian

---

The retina is a very crucial organ in the human eye. The retina has a blood vessel section which in every human has a different form of blood vessels. Early detection of retinal disease can be done through sections of the retinal blood vessels. In order to facilitate the medical world in detecting diabetic retinopathy on the retina, a retinal image segmentation study was carried out in order to distinguish between retinal images that have the disease or not. This study presents retinal segmentation using the Fractalnet Convolutional Neural Network method. The first step is to prepare the data used, namely DRIVE. Then proceed with data processing using Color Channel Separation, Grayscale, CLAHE (Contrast Limited Adaptive Histogram Equalization), and data Augmentation. Followed by the segmentation process using the Fractalnet architecture, after that the best model is selected by looking at the parameters. From the results of the research conducted to get the best model with parameters Accuracy value of 96.15%, Sensitivity 74.89%, Specificity 77.49% and F1 Score of 77.01%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107004746	T58418	T584182021	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T584182021

Publisher

Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer., 2021

Collation

xiv, 58 hlm. : ilus. ; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.407

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Metode Convolutional Neural Network (CNN)

Specific Detail Info

-

Statement of Responsibility

DS

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment