Brain image segmentation based on firefly algorithm combined with k-means clustering

Romana Capor Hrosik, Eva Tuba, Edin Dolicanin, Raka Jovanovic, Milan Tuba

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

During the past few decades digital images have become an important part of numerous scientific fields. Digital images used in medicine enabled tremendous progress in the diagnostics, treatment determination process as well as in monitoring patient recovery. Detection of brain tumors represents one of the active research fields and an algorithm for brain image segmentation was developed with an aim to emphasize four different primary brain tumors: glioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma and sarcoma from PET, MRI and SPECT images. The proposed image segmentation method is based on the firefly algorithm whose solutions are improved by the k-means clustering algorithm when Otsu's criterion was used as the fitness function. The proposed combined algorithm was tested on commonly used images from Harvard Whole Brain Atlas and the results were compared to other method from literature. The method proposed in this paper achieved better segmentation considering standard segmentation quality metrics such as normalized root square mean error, peak signal to noise and structural similarity index metric.

Original languageEnglish
Pages (from-to)167-176
Number of pages10
JournalStudies in Informatics and Control
Volume28
Issue number2
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Image segmentation
Brain
Tumors
Patient monitoring
Clustering algorithms
Mean square error
Magnetic resonance imaging
Medicine
Recovery

Keywords

  • Brain tumor detection
  • Clustering
  • Firefly algorithm
  • Image segmentation
  • k-means
  • Medical digital images
  • Optimization
  • Swarm intelligence

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Brain image segmentation based on firefly algorithm combined with k-means clustering. / Capor Hrosik, Romana; Tuba, Eva; Dolicanin, Edin; Jovanovic, Raka; Tuba, Milan.

In: Studies in Informatics and Control, Vol. 28, No. 2, 01.01.2019, p. 167-176.

Research output: Contribution to journalArticle

Capor Hrosik, Romana ; Tuba, Eva ; Dolicanin, Edin ; Jovanovic, Raka ; Tuba, Milan. / Brain image segmentation based on firefly algorithm combined with k-means clustering. In: Studies in Informatics and Control. 2019 ; Vol. 28, No. 2. pp. 167-176.
@article{dea37e4d1aa44c5baef0b4308a09dda5,
title = "Brain image segmentation based on firefly algorithm combined with k-means clustering",
abstract = "During the past few decades digital images have become an important part of numerous scientific fields. Digital images used in medicine enabled tremendous progress in the diagnostics, treatment determination process as well as in monitoring patient recovery. Detection of brain tumors represents one of the active research fields and an algorithm for brain image segmentation was developed with an aim to emphasize four different primary brain tumors: glioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma and sarcoma from PET, MRI and SPECT images. The proposed image segmentation method is based on the firefly algorithm whose solutions are improved by the k-means clustering algorithm when Otsu's criterion was used as the fitness function. The proposed combined algorithm was tested on commonly used images from Harvard Whole Brain Atlas and the results were compared to other method from literature. The method proposed in this paper achieved better segmentation considering standard segmentation quality metrics such as normalized root square mean error, peak signal to noise and structural similarity index metric.",
keywords = "Brain tumor detection, Clustering, Firefly algorithm, Image segmentation, k-means, Medical digital images, Optimization, Swarm intelligence",
author = "{Capor Hrosik}, Romana and Eva Tuba and Edin Dolicanin and Raka Jovanovic and Milan Tuba",
year = "2019",
month = "1",
day = "1",
doi = "10.24846/v28i2y201905",
language = "English",
volume = "28",
pages = "167--176",
journal = "Studies in Informatics and Control",
issn = "1220-1766",
publisher = "National Institute for R & D in Informatics",
number = "2",

}

TY - JOUR

T1 - Brain image segmentation based on firefly algorithm combined with k-means clustering

AU - Capor Hrosik, Romana

AU - Tuba, Eva

AU - Dolicanin, Edin

AU - Jovanovic, Raka

AU - Tuba, Milan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - During the past few decades digital images have become an important part of numerous scientific fields. Digital images used in medicine enabled tremendous progress in the diagnostics, treatment determination process as well as in monitoring patient recovery. Detection of brain tumors represents one of the active research fields and an algorithm for brain image segmentation was developed with an aim to emphasize four different primary brain tumors: glioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma and sarcoma from PET, MRI and SPECT images. The proposed image segmentation method is based on the firefly algorithm whose solutions are improved by the k-means clustering algorithm when Otsu's criterion was used as the fitness function. The proposed combined algorithm was tested on commonly used images from Harvard Whole Brain Atlas and the results were compared to other method from literature. The method proposed in this paper achieved better segmentation considering standard segmentation quality metrics such as normalized root square mean error, peak signal to noise and structural similarity index metric.

AB - During the past few decades digital images have become an important part of numerous scientific fields. Digital images used in medicine enabled tremendous progress in the diagnostics, treatment determination process as well as in monitoring patient recovery. Detection of brain tumors represents one of the active research fields and an algorithm for brain image segmentation was developed with an aim to emphasize four different primary brain tumors: glioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma and sarcoma from PET, MRI and SPECT images. The proposed image segmentation method is based on the firefly algorithm whose solutions are improved by the k-means clustering algorithm when Otsu's criterion was used as the fitness function. The proposed combined algorithm was tested on commonly used images from Harvard Whole Brain Atlas and the results were compared to other method from literature. The method proposed in this paper achieved better segmentation considering standard segmentation quality metrics such as normalized root square mean error, peak signal to noise and structural similarity index metric.

KW - Brain tumor detection

KW - Clustering

KW - Firefly algorithm

KW - Image segmentation

KW - k-means

KW - Medical digital images

KW - Optimization

KW - Swarm intelligence

UR - http://www.scopus.com/inward/record.url?scp=85069789246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069789246&partnerID=8YFLogxK

U2 - 10.24846/v28i2y201905

DO - 10.24846/v28i2y201905

M3 - Article

AN - SCOPUS:85069789246

VL - 28

SP - 167

EP - 176

JO - Studies in Informatics and Control

JF - Studies in Informatics and Control

SN - 1220-1766

IS - 2

ER -