Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images

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

4 Citations (Scopus)

Abstract

Segmentation is one of the most important steps in automated medical diagnosis applications, which remains to be a difficult task. In this paper, we propose a semi-automated segmentation method for extracting lung lesions from thoracic Computed Tomography (CT) images by combining low level processing and active contour techniques. To evaluate its accuracy, the Jaccard Index (JI) was used as a measure of the image of the segmented lesion compared to alternative segmentations from the QIN lung CT segmentation challenge. The results show that our proposed technique has acceptable accuracy in lung lesion segmentation with JI values between 0.837 to 0.956, especially when considering the variability of the alternative segmentations.

Original languageEnglish
Title of host publicationISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages26-30
Number of pages5
ISBN (Print)9781467378154
DOIs
Publication statusPublished - 17 Mar 2016
EventIEEE Student Symposium in Biomedical Engineering and Sciences, ISSBES 2015 - UiTM, Shah Alam, Malaysia
Duration: 4 Nov 2015 → …

Other

OtherIEEE Student Symposium in Biomedical Engineering and Sciences, ISSBES 2015
CountryMalaysia
CityUiTM, Shah Alam
Period4/11/15 → …

Fingerprint

Tomography
Thorax
Lung
Processing

Keywords

  • active contour
  • low level processing
  • lung lesion
  • semi-automated
  • thoracic CT
  • volumetric segmentation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications
  • Signal Processing

Cite this

Rossi, F., & Abd Rahni, A. A. (2016). Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images. In ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student (pp. 26-30). [7435887] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISSBES.2015.7435887

Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images. / Rossi, Farli; Abd Rahni, Ashrani Aizzuddin.

ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student. Institute of Electrical and Electronics Engineers Inc., 2016. p. 26-30 7435887.

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

Rossi, F & Abd Rahni, AA 2016, Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images. in ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student., 7435887, Institute of Electrical and Electronics Engineers Inc., pp. 26-30, IEEE Student Symposium in Biomedical Engineering and Sciences, ISSBES 2015, UiTM, Shah Alam, Malaysia, 4/11/15. https://doi.org/10.1109/ISSBES.2015.7435887
Rossi F, Abd Rahni AA. Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images. In ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student. Institute of Electrical and Electronics Engineers Inc. 2016. p. 26-30. 7435887 https://doi.org/10.1109/ISSBES.2015.7435887
Rossi, Farli ; Abd Rahni, Ashrani Aizzuddin. / Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images. ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 26-30
@inproceedings{94df325e5c2941be8c5dbf685050e45f,
title = "Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images",
abstract = "Segmentation is one of the most important steps in automated medical diagnosis applications, which remains to be a difficult task. In this paper, we propose a semi-automated segmentation method for extracting lung lesions from thoracic Computed Tomography (CT) images by combining low level processing and active contour techniques. To evaluate its accuracy, the Jaccard Index (JI) was used as a measure of the image of the segmented lesion compared to alternative segmentations from the QIN lung CT segmentation challenge. The results show that our proposed technique has acceptable accuracy in lung lesion segmentation with JI values between 0.837 to 0.956, especially when considering the variability of the alternative segmentations.",
keywords = "active contour, low level processing, lung lesion, semi-automated, thoracic CT, volumetric segmentation",
author = "Farli Rossi and {Abd Rahni}, {Ashrani Aizzuddin}",
year = "2016",
month = "3",
day = "17",
doi = "10.1109/ISSBES.2015.7435887",
language = "English",
isbn = "9781467378154",
pages = "26--30",
booktitle = "ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Combination of low level processing and active contour techniques for semi-automated volumetric lung lesion segmentation from thoracic CT images

AU - Rossi, Farli

AU - Abd Rahni, Ashrani Aizzuddin

PY - 2016/3/17

Y1 - 2016/3/17

N2 - Segmentation is one of the most important steps in automated medical diagnosis applications, which remains to be a difficult task. In this paper, we propose a semi-automated segmentation method for extracting lung lesions from thoracic Computed Tomography (CT) images by combining low level processing and active contour techniques. To evaluate its accuracy, the Jaccard Index (JI) was used as a measure of the image of the segmented lesion compared to alternative segmentations from the QIN lung CT segmentation challenge. The results show that our proposed technique has acceptable accuracy in lung lesion segmentation with JI values between 0.837 to 0.956, especially when considering the variability of the alternative segmentations.

AB - Segmentation is one of the most important steps in automated medical diagnosis applications, which remains to be a difficult task. In this paper, we propose a semi-automated segmentation method for extracting lung lesions from thoracic Computed Tomography (CT) images by combining low level processing and active contour techniques. To evaluate its accuracy, the Jaccard Index (JI) was used as a measure of the image of the segmented lesion compared to alternative segmentations from the QIN lung CT segmentation challenge. The results show that our proposed technique has acceptable accuracy in lung lesion segmentation with JI values between 0.837 to 0.956, especially when considering the variability of the alternative segmentations.

KW - active contour

KW - low level processing

KW - lung lesion

KW - semi-automated

KW - thoracic CT

KW - volumetric segmentation

UR - http://www.scopus.com/inward/record.url?scp=84965118135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965118135&partnerID=8YFLogxK

U2 - 10.1109/ISSBES.2015.7435887

DO - 10.1109/ISSBES.2015.7435887

M3 - Conference contribution

AN - SCOPUS:84965118135

SN - 9781467378154

SP - 26

EP - 30

BT - ISSBES 2015 - IEEE Student Symposium in Biomedical Engineering and Sciences: By the Student for the Student

PB - Institute of Electrical and Electronics Engineers Inc.

ER -