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 12/11/2015 14:18:31  •  1037 Views


SEGMENTASI SEL DARAH PUTIH PADA CITRA MIKROSKOPIS LEUKEMIA BERDASARKAN INFORMASI WARNA DAN REGION OF INTEREST MENGGUNAKAN K-MEANS DAN OPERASI MORFOLOGI

SEGMENTATION OF WHITE BLOOD CELLS FROM MICROSCOPIC LEUKEMIA IMAGES BASED ON COLOR AND REGION OF INTEREST INFORMATION USING K-MEANS AND MATHEMATICAL MORPHOLOGY

Author :
SYIDADA, SHOFIYA ( 5112201048 )




ABSTRAK

Pada bidang medis analisis citra mikroskopis sel darah merupakan suatu hal yang penting untuk mendiagnosa penyakit yang sedang diderita oleh pasien seperti leukemia. Diagnosa penyakit leukemia dilakukan dengan pengamatan terhadap bentuk populasi dan jenis sel darah. Segmentasi citra sel leukemia menjadi area inti sel dan sitoplasma merupakan tahap paling penting untuk mengenali jenis sel leukemia. Beberapa metode untuk melakukan segmentasi sel leukemia telah dikembangkan. Secara umum metode-metode yang digunakan adalah clustering thresholding watershed operasi morfologi citra dan metode hybrid. Metode hybrid merupakan kombinasi dari beberapa metode seperti clustering dan thresholding clustering dan operasi morfologi. Metode-metode segmentasi citra sel leukemia sebelumnya mampu melakukan segmentasi inti sel dan sitoplasma pada citra mikroskopis sel darah. Namun metode-metode segmentasi tersebut belum fleksibel terhadap adanya variasi warna akibat proses staining serta terhadap variasi nilai perbesaran ukuran sel saat pengamatan pada mikroskop. Oleh karena itu pada penelitian ini akan dikembangkan metode segmentasi sel darah putih leukemia untuk mendapatkan area inti sel dan sitoplasma secara otomatis yang fleksibel terhadap variasi warna serta variasi ukuran sel. Metode usulan ini melakukan clustering warna menggunakan K-means dengan penentuan area klaster berdasarkan informasi region of interest yang diperoleh dari operasi morfologi citra. Data uji yang digunakan adalah 15 citra mikroskopis leukemia dengan variasi skala ukuran sel yang berbeda dan 20 citra mikroskopis leukemia dengan variasi warna yang berbeda. Berdasarkan hasil uji coba yang telah dilakukan penggunaan ukuran structuring element SE dinamis meningkatkan performa segmentasi sel darah putih dengan nilai rata-rata akurasi TPR dan FPR adalah 98.38 81.89 dan 0.55. Metode usulan dapat melakukan segmentasi sel darah putih pada data citra dengan variasi warna yang berbeda secara lebih baik yaitu dengan nilai rata-rata akurasi TPR dan FPR adalah 93.07 84.14 dan 2.86


ABSTRACT

In the medical field microscopic image analysis of blood cells is an important procedure for diagnosis of various diseases. Leukemia is one of such diseases that can be identified by observing the microscopic images of blood cells. Diagnosis of leukemia involves the observation of the shape and the number of leucocytes in the blood cell images. This observation is done manually by pathologists. Since this task is time consuming and highly dependent on the skill and experience of the pathologist automation of the task would be of great help to pathologists in detecting types of leukemia. Segmentation of a leukemia cell image into nucleus cytoplasm and background is the most important step to identify the type of leukemia cells. Several methods for segmenting leukemia cells have been proposed previously. These include clustering thresholding watershed mathematical morphology and hybrid method. Hybrid method is a combination of several methods such as clustering and thresholding or clustering and mathematical morphology. These previous methods have been able to segment the nucleus and cytoplasm. However they are not flexible to variation of color tones and variation of cell size. Variation of color tones occur due to differences in conditions when the staining process is done. Variation of cell size also occurs due to magnification during the observation on the microscope. This study thus proposes a method for segmentation of leukemic cell images automatically which is flexible to variation of color tones and variations of cell size. This segmentation method performs color clustering using K-means in which a cluster area is determined based on information of region of interest. The region of interest is derived from the mathematical morphology of the image. The experiment data used consists of 15 microscopic image of leukemia varying in different cell sizes and 20 microscopic image of leukemia with different color variations. Based on the experiment the use of dynamic size of structuring element increased the performance of white blood cells segmentation with the value 9838 81.89 and 0.55 for average of accuracy TPR and FPR. The proposed method is able to do white blood cell segmentation on images with different color variations with the value of 93.07 84.14 and 2.86 for average of accuracy TPR and FPR.



Keywordsclustering; morfologi citra; region of interest; segmentasi
 
Subject:  Rekayasa Perangkat Lunak
Contributor
  1. Dr. Eng. Nanik Suciati, S.Kom, M.Kom
  2. Dr. Eng. Chastine Fatichah, S.Kom, M.Kom
Date Create: 12/11/2015
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Master-51103150001537
Collection ID: 51103150001537
Call Number: RTIf 005.1 Syi s


Source
Master Theses of Informatics Engineering, RTIf 005.1 Syi s, 2015

Coverage
ITS Community

Rights
Copyright @2015 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-39508-5112201048-abstract_id.pdf - 359 KB
  2.  ITS-Master-39508-5112201048-abstract_en.pdf - 360 KB
  3.  ITS-Master-39508-5112201048-conclusion.pdf - 452 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 107.23.129.77
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