EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Master Theses » Teknik Informatika - S2
Posted by aprill@is.its.ac.id at 23/02/2016 15:27:52  •  1809 Views


SEGMENTASI MICROANEURYSM PADA CITRA FUNDUS RETINA UNTUK DETEKSI DINI DIABETIC RETINOPATHY

MICROANEURYSM SEGMENTATION OF FUNDUS RETINAL IMAGES FOR EARLY DETECTION OF DIABETIC RETINOPATHY

Author :
WHARDANA, ADITHYA KUSUMA ( 5112201005 )




ABSTRAK

Diabetic RetinopathyDR merupakan kelainan retina akibat dari komplikasi diabetes yang menyebabkan kebutaan. Diabetic retinopathy adalah penyakit mata kritis yang dapat dianggap sebagai manifestasi dari diabetes pada retina. Salah satu cara untuk mengetahui bahwa ada diabetic retinopathy dapat dilihat dari adanya kemunculan microaneurysm pada retina yang bisa dilihat melalui alat kedokteran kamera fundus. Penelitian ini mengajukan suatu langkah untuk segmentasi microaneurysm pada citra retina untuk deteksi secara dini diabetic retinopathy. Tahap-tahap dalam penelitian ini adalah me-resize ulang citra merubah citra original ke citra kanal merah rekonstruksi morfologi kemudian memperbaiki citra tersebut dengan metode morfologi mendeteksi microaneurysm dengan menggunakan filter laplacian of gaussian. Microaneurysm diperjelas dengan menggunakan tophat filtering kemudian segmentasi dengan menggunakan thresholding T dan pada tahap akhir untuk segmentasi menggunakan region properties scalar EccentricityE. Segmentasi menggunakan beberapa tahapan skenario tahapan skenario adalah dengan menggunakan T0.4 E0.4 T0.5 E0.5 T0.6 E0.6 T0.7 E0.7T0.8 E0.8 dengan hasil akhir dari E0.4 tersegmentasi 9 citra dari 20 citra yang diujikan E0.5 tersegmentasi 15 dari 20 citra yang diujikan E0.6 tersegmentasi 18 dari 20 citra yang diujikan E0.7 tersegmentasi 20 dari 20 citra yang diujikan E0.8 tersegmentasi 19 dari 20 citra yang diujikan. Hasil yang terbagus dengan menggunakan nilai parameter T0.7 E0.7. Adapun dari parameter nilai T0.4E0.4 merupakan hasil terburuk dalam segmentasi yang berhasil ada 9 citra dengan cukup banyak noise.


ABSTRACT

Diabetic retinopathy DR is a disorder of the retina caused by complications of diabetes that cause blindness. Diabetic retinopathy is a critical eye disease that can be considered as a manifestation of diabetes in the retina. One way to of identifying diabetic retinopathy is through the presence of micro-aneurysms in the retina that can be seen through a fundus medical camera. This study proposes a method for segmentation of retinal micro-aneurysm in an image for early detection of diabetic retinopathy. The stages in the proposed method include resizing the image converting the original image to red channel morphological reconstruction followed by morphological enhancement of the image. Then there is microaneurysm detection using Laplacian of Gaussian filter. The microaneurysm area is clarified by using top-hat filtering. Segmentation is done using thresholding and at the final stage further segmentation using region properties eccentricity scalar is applied. Segmentation is carried out based on several test scenarios stages the various threshold and eccentricity parameters used include T 0.4 E 0.4 T 0.5 E 0.5 T 0.6 E 0.6 T 0.7 E 0.7 T 0.8 E 0.8. The final result of E 0.4 is used to segment image 9 of 20 tested images that of E 0.5 is used to segment image 15 of 20 of the tested images while that of E 0.6 is used to segment image 18 of 20 of the tested images. Likewise E 0.7 segments image 20 of 20 tested images while E 0.8 segments image 19 of the 20tested. Excellent results by using the parameter values T 0.7 E 0.7. The value of the parameter T 0.4 E 0.4 is the worst result in segmentation there are 9 image successful with quite a lot of noise.



KeywordsDiabetic Retinopathy; citra Fundus; deteksi microaneurysm; metode morfologi; Laplacian of gaussian; Thresholding; Eccentricity
 
Subject:  Pengolahan citra - teknik digital
Contributor
  1. Prof.Ir. Handayani Tjandrasa, M.Sc, Ph.D
Date Create: 23/02/2016
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Master-51103150001583
Collection ID: 51103150001583
Call Number: RTIf 621.367 Wha s


Source
Master Theses of Informatics Engineering, RTIf 621.367 Wha s, 2015

Coverage
ITS Community

Rights
Copyright @2016 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library




[ Download - Open Access ]

  1.  ITS-Master-40319-5112201005-Abstract_id.pdf - 198 KB
  2.  ITS-Master-40319-5112201005-Abstract_en.pdf - 199 KB
  3.  ITS-Master-40319-5112201005-Conclusion.pdf - 187 KB




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 35.175.248.25
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2019 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan