Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images

Wan Mimi Diyana Wan Zaki, M. Faizal A Fauzi, R. Besar, W. S H Munirah W Ahmad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper presents qualitative and quantitative comparisons of our proposed Multi-level Local Segmentation Approach (MLSA) to segment intracranial structures of the CT brain images for haemorrhage detection. The proposed method is able to overcome the main problem in our database images; the inconsistency of grey level values due to different parameter settings during the scanning process that leads to different objects segmented within the same intensity level, as well as helps to automate the segmentation process. One hundred and fifty haemorrhage CT brain images of thirty one patients from Hospital Serdang and Hospital Putrajaya are used in this work. Performance of the segmentation method is quantitatively and qualitatively compared with available automated methods which are watershed and expectation maximization methods. The results show that the MLSA gives the best segmentation of average Percentage of Correct Classification, PCC = 97.1% with 93% of the haemorrhage cases excellently segmented. Besides, qualitatively, it also portrays good segmentation results. The MLSA proves to be accurate and reliable that would provide a strong basis for the application in content-based medical image retrieval.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Pages369-373
Number of pages5
DOIs
Publication statusPublished - 2011
Event2011 IEEE Region 10 Conference: Trends and Development in Converging Technology Towards 2020, TENCON 2011 - Bali
Duration: 21 Nov 201124 Nov 2011

Other

Other2011 IEEE Region 10 Conference: Trends and Development in Converging Technology Towards 2020, TENCON 2011
CityBali
Period21/11/1124/11/11

Fingerprint

Brain
Image retrieval
Watersheds
Scanning

Keywords

  • brain
  • CBMIR
  • Computed Tomography
  • intracranial haemorrhage
  • multi-level thresholding method

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications

Cite this

Wan Zaki, W. M. D., Fauzi, M. F. A., Besar, R., & Ahmad, W. S. H. M. W. (2011). Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (pp. 369-373). [6129127] https://doi.org/10.1109/TENCON.2011.6129127

Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images. / Wan Zaki, Wan Mimi Diyana; Fauzi, M. Faizal A; Besar, R.; Ahmad, W. S H Munirah W.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2011. p. 369-373 6129127.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wan Zaki, WMD, Fauzi, MFA, Besar, R & Ahmad, WSHMW 2011, Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images. in IEEE Region 10 Annual International Conference, Proceedings/TENCON., 6129127, pp. 369-373, 2011 IEEE Region 10 Conference: Trends and Development in Converging Technology Towards 2020, TENCON 2011, Bali, 21/11/11. https://doi.org/10.1109/TENCON.2011.6129127
Wan Zaki WMD, Fauzi MFA, Besar R, Ahmad WSHMW. Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2011. p. 369-373. 6129127 https://doi.org/10.1109/TENCON.2011.6129127
Wan Zaki, Wan Mimi Diyana ; Fauzi, M. Faizal A ; Besar, R. ; Ahmad, W. S H Munirah W. / Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images. IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2011. pp. 369-373
@inproceedings{438d7d66c3ba481488610e018ab31933,
title = "Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images",
abstract = "This paper presents qualitative and quantitative comparisons of our proposed Multi-level Local Segmentation Approach (MLSA) to segment intracranial structures of the CT brain images for haemorrhage detection. The proposed method is able to overcome the main problem in our database images; the inconsistency of grey level values due to different parameter settings during the scanning process that leads to different objects segmented within the same intensity level, as well as helps to automate the segmentation process. One hundred and fifty haemorrhage CT brain images of thirty one patients from Hospital Serdang and Hospital Putrajaya are used in this work. Performance of the segmentation method is quantitatively and qualitatively compared with available automated methods which are watershed and expectation maximization methods. The results show that the MLSA gives the best segmentation of average Percentage of Correct Classification, PCC = 97.1{\%} with 93{\%} of the haemorrhage cases excellently segmented. Besides, qualitatively, it also portrays good segmentation results. The MLSA proves to be accurate and reliable that would provide a strong basis for the application in content-based medical image retrieval.",
keywords = "brain, CBMIR, Computed Tomography, intracranial haemorrhage, multi-level thresholding method",
author = "{Wan Zaki}, {Wan Mimi Diyana} and Fauzi, {M. Faizal A} and R. Besar and Ahmad, {W. S H Munirah W}",
year = "2011",
doi = "10.1109/TENCON.2011.6129127",
language = "English",
isbn = "9781457702556",
pages = "369--373",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - Qualitative and quantitative comparisons of haemorrhage intracranial segmentation in CT brain images

AU - Wan Zaki, Wan Mimi Diyana

AU - Fauzi, M. Faizal A

AU - Besar, R.

AU - Ahmad, W. S H Munirah W

PY - 2011

Y1 - 2011

N2 - This paper presents qualitative and quantitative comparisons of our proposed Multi-level Local Segmentation Approach (MLSA) to segment intracranial structures of the CT brain images for haemorrhage detection. The proposed method is able to overcome the main problem in our database images; the inconsistency of grey level values due to different parameter settings during the scanning process that leads to different objects segmented within the same intensity level, as well as helps to automate the segmentation process. One hundred and fifty haemorrhage CT brain images of thirty one patients from Hospital Serdang and Hospital Putrajaya are used in this work. Performance of the segmentation method is quantitatively and qualitatively compared with available automated methods which are watershed and expectation maximization methods. The results show that the MLSA gives the best segmentation of average Percentage of Correct Classification, PCC = 97.1% with 93% of the haemorrhage cases excellently segmented. Besides, qualitatively, it also portrays good segmentation results. The MLSA proves to be accurate and reliable that would provide a strong basis for the application in content-based medical image retrieval.

AB - This paper presents qualitative and quantitative comparisons of our proposed Multi-level Local Segmentation Approach (MLSA) to segment intracranial structures of the CT brain images for haemorrhage detection. The proposed method is able to overcome the main problem in our database images; the inconsistency of grey level values due to different parameter settings during the scanning process that leads to different objects segmented within the same intensity level, as well as helps to automate the segmentation process. One hundred and fifty haemorrhage CT brain images of thirty one patients from Hospital Serdang and Hospital Putrajaya are used in this work. Performance of the segmentation method is quantitatively and qualitatively compared with available automated methods which are watershed and expectation maximization methods. The results show that the MLSA gives the best segmentation of average Percentage of Correct Classification, PCC = 97.1% with 93% of the haemorrhage cases excellently segmented. Besides, qualitatively, it also portrays good segmentation results. The MLSA proves to be accurate and reliable that would provide a strong basis for the application in content-based medical image retrieval.

KW - brain

KW - CBMIR

KW - Computed Tomography

KW - intracranial haemorrhage

KW - multi-level thresholding method

UR - http://www.scopus.com/inward/record.url?scp=84856918299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856918299&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2011.6129127

DO - 10.1109/TENCON.2011.6129127

M3 - Conference contribution

SN - 9781457702556

SP - 369

EP - 373

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -