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 » Paper and Presentation » Teknik Elektro - Telematika S2
Posted by tondoindra@gmail.com at 18/12/2012 10:10:21  •  1701 Views


SEGMENTASI JARINGAN OTAK MRI MENGGUNAKAN HYBRID K-MEANS CLUSTERING DAN PARTICLE SWARM OPTIMIZATION

MRI BRAIN TISSUE SEGMENTATION USING HYBRID K-MEANS CLUSTERING AND PARTICLE SWARM OPTIMIZATION

Author :
CHARIS, MUCHAMAD AZWAR ( 2210206002 )




ABSTRAK

Dalam analisa citra medis untuk diagnosa yang berbantukan kamputer proses segmentasi sering diperlukan sebagai tahap dalam diagnosa citra medis. Magnetic Resonance Imaging MRI merupakan teknik pencitraan diagnostik yang sangat bermanfaat dalam mendeteksi dini perubahan abnormal pada jaringan dan organ yang tidak melibatkan paparan radiasi seperti X-ray. Penggunaan algoritma K-Means Clustering dan Particle Swarm Optimization dalam penelitian ini diharapkan mampu memperbaiki pendeteksian antar jaringan otak supaya bisa dibedakan maupun dikenali dengan mudah. Proses Segmentasi untuk pemisahan lapisan jaringan otak Brain Tissue antara White Matter Grey Matter dan Cerebrospinal Fluid pengelompokkan dilakukan dengan mengukur kemiripan ciri segmen. Adapun ciri yang digunakan adalah 1 Rata-rata nilai keabuan citra 2 Nilai minimal keabuan citra 3 Nilai maksimal keabuan citra dan 4 Rentang nilai keabuan citra 5 Interval keabuan citra. Dalam penelitian ini diujicobakan sebuah data awal MRI yang berekstensi dcm yang akan dikonvesi menjadi tif sebanyak 30 buah supaya dapat dilakukan proses lebih lanjut. serta dianalisa dan divisualisasikan menggunakan Matlab 7 dengan menggunakan metode yang diusulkan. Output yang dihasilkan akan dibandingkan dengan proses secara manual dan dilakukan proses verifikasi dan validasi dengan menggunakan analisa Jaccard Similarity dan Receiver Operating Characteristic sehingga bisa dapatkan nilai akurasi sensifisitas dan spesifisitasnya. Setelah dilakukan pengujian terhadap 30 data citra otak MRI yang keseluruhannya memiliki bentuk dan tekstur otak yang berbeda-beda didapatkan prosentasi hasil akurasi pada area White Matter dan Gray Matter menggunakan K-Means Clustering berturut-turut adalah 77.66 dan 75.82 dan untuk metode K-Means yang dioptimasi PSO berturut-turut sebesar 85.35 dan 82.33. Dalam analisa ROC didapatkan nilai probabilitas dibawah kurva AUC pada area White Matter dan Gray Matter menggunakan K-Means Clustering berturut-turut adalah 0.95 dan 0.82 dan menggunakan PSO berturut-turut adalah 0.66 dan 0.81.


ABSTRACT

In analysis of medical imaging for diagnosis of computer-aided the process of segmentation is often required as a step in medical image diagnosis. Magnetic Resonance Imaging MRI is a diagnostic imaging technique that is very useful in detecting early changes in abnormal tissues and organs that does not involve exposure to radiation like a X-ray scanning. The use of K-Means Clustering and Particle Swarm Optimization algorithm in this study are expected to improve the detection of brain tissue that can be easily distinguished and identified. Segmentation process to separation of brain tissue layer between the White Matter Gray Matter and Cerebrospinal Fluid the grouping is done by measuring the similarity of segment characteristics. As for The characteristics used are 1 the average value of gray image 2 the minimum intensity value of gray image 3 the maximum intensity value of gray image and 4 the Range value of gray image 5 the Interval of gray image. In this study the preliminary data from MRI will be converted from dicom files to tif extension as 30 pieces in order to further processing to be analyzed and visualized by Matlab 7 using the proposed method. The resulting output will be compared with the process manually and the process of verification and validation by using the Jaccard Similarity and Receiver Operating Characteristic analysis so they can get the value of accuracy sensitivity and specificity. After testing the brain image of MRI as much as 30 files which has the overall shape and size of different brain the percentage of accuracy obtained in the area of White Matter and Gray Matter using K-Means Clustering in a row at 77.66 and 75.82 and for K-Means method with optimized by PSO algorithm in a row at 85.35 and 82.33. In ROC analysis the probability value obtained area under curve AUC in the area of White Matter and Gray Matter using K-Means Clustering in a row at 0.95 and 0.82 and PSO optimized at 0.66 and 0.81.



KeywordsCitra Medis; Jaringan Otak MRI; Segmentasi; K-Means Clustering; Particle Swarm Optimization; Region Growing; Jaccard Similarity; Receiver Operating Characteristic
 
Subject:  Cluster analisis, kecerdasan berkelompok, gambar sistem dalam kedokteran, otak - pencitraan - teknik digital
Contributor
  1. Mochamad Hariadi, ST., M.Sc., Ph.D.
Date Create: 18/12/2012
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-paper-220211120001511
Collection ID: 220211120001511
Call Number: RTE 519.53 Cha s


Source
Paper and presentation of Electrical Engineering ,RTE 519.53 Cha s, 2012

Coverage
ITS COMMUNITY

Rights
Copyright @2012 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 - Summary ]

ITS-paper-220211120001511-22730.pdf




 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 34.226.244.70
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2020 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan