Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method

Mahdi Alizadeh, Hoda Eskandari, Kaveh Sharzehi

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

1 Citation (Scopus)

Abstract

Finding borders of interests in both normal and abnormal images might be helpful for physician to make decision of an image being normal or abnormal. Also, in some points instead of entire images these detected borders can be considered for processing. In this paper, the author proposed the Fisher Transform Method (FTM) as edge detection method. FTM increases gradient of endoscopy images and then, it will represent better performance rather than traditional methods. The proposed FTM was applied on 21 endoscopic images consist of normal and abnormal images included Lymphangiectasia captured by Wireless Capsule Endoscopy (WCE). The results show that, this method presents a better performance rather than color Canny edge detector. The detection results were validated with ground truth image was drawn by an independent board certified gastroenterologists. The proposed method was detected 96% of borders of Lymphangiectasia and 75% of borders in normal images. In comparison, it was detected 75% and 51% of Lymphangiectasia and normal image borders before using FTM respectively.

Original languageEnglish (US)
Title of host publication2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479983605
DOIs
StatePublished - Jan 1 2015
Externally publishedYes
Event2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015 - Troy, United States
Duration: Apr 17 2015Apr 19 2015

Publication series

Name2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015

Conference

Conference2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015
CountryUnited States
CityTroy
Period4/17/154/19/15

Fingerprint

Lymphangiectasis
Capsule Endoscopy
Endoscopy
Mathematical transformations
Gradient methods
Edge detection
Color
Detectors
Processing
Physicians

Keywords

  • color Canny edge detector
  • Fisher Transform Method
  • Lymphangiectasia
  • Wireless Capsule Endoscopy

ASJC Scopus subject areas

  • Biotechnology
  • Cancer Research
  • Cell Biology
  • Molecular Medicine
  • Biomedical Engineering
  • Control and Systems Engineering

Cite this

Alizadeh, M., Eskandari, H., & Sharzehi, K. (2015). Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method. In 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015 [7117145] (2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEBEC.2015.7117145

Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method. / Alizadeh, Mahdi; Eskandari, Hoda; Sharzehi, Kaveh.

2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7117145 (2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015).

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

Alizadeh, M, Eskandari, H & Sharzehi, K 2015, Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method. in 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015., 7117145, 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015, Institute of Electrical and Electronics Engineers Inc., 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015, Troy, United States, 4/17/15. https://doi.org/10.1109/NEBEC.2015.7117145
Alizadeh M, Eskandari H, Sharzehi K. Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method. In 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7117145. (2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015). https://doi.org/10.1109/NEBEC.2015.7117145
Alizadeh, Mahdi ; Eskandari, Hoda ; Sharzehi, Kaveh. / Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method. 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. (2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015).
@inproceedings{48a422be60d1425983bbcebdb1c1dd3a,
title = "Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method",
abstract = "Finding borders of interests in both normal and abnormal images might be helpful for physician to make decision of an image being normal or abnormal. Also, in some points instead of entire images these detected borders can be considered for processing. In this paper, the author proposed the Fisher Transform Method (FTM) as edge detection method. FTM increases gradient of endoscopy images and then, it will represent better performance rather than traditional methods. The proposed FTM was applied on 21 endoscopic images consist of normal and abnormal images included Lymphangiectasia captured by Wireless Capsule Endoscopy (WCE). The results show that, this method presents a better performance rather than color Canny edge detector. The detection results were validated with ground truth image was drawn by an independent board certified gastroenterologists. The proposed method was detected 96{\%} of borders of Lymphangiectasia and 75{\%} of borders in normal images. In comparison, it was detected 75{\%} and 51{\%} of Lymphangiectasia and normal image borders before using FTM respectively.",
keywords = "color Canny edge detector, Fisher Transform Method, Lymphangiectasia, Wireless Capsule Endoscopy",
author = "Mahdi Alizadeh and Hoda Eskandari and Kaveh Sharzehi",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/NEBEC.2015.7117145",
language = "English (US)",
series = "2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015",

}

TY - GEN

T1 - Lymphangiectasia detection in Wireless Capsule Endoscopy images using Fisher Transform Method

AU - Alizadeh, Mahdi

AU - Eskandari, Hoda

AU - Sharzehi, Kaveh

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Finding borders of interests in both normal and abnormal images might be helpful for physician to make decision of an image being normal or abnormal. Also, in some points instead of entire images these detected borders can be considered for processing. In this paper, the author proposed the Fisher Transform Method (FTM) as edge detection method. FTM increases gradient of endoscopy images and then, it will represent better performance rather than traditional methods. The proposed FTM was applied on 21 endoscopic images consist of normal and abnormal images included Lymphangiectasia captured by Wireless Capsule Endoscopy (WCE). The results show that, this method presents a better performance rather than color Canny edge detector. The detection results were validated with ground truth image was drawn by an independent board certified gastroenterologists. The proposed method was detected 96% of borders of Lymphangiectasia and 75% of borders in normal images. In comparison, it was detected 75% and 51% of Lymphangiectasia and normal image borders before using FTM respectively.

AB - Finding borders of interests in both normal and abnormal images might be helpful for physician to make decision of an image being normal or abnormal. Also, in some points instead of entire images these detected borders can be considered for processing. In this paper, the author proposed the Fisher Transform Method (FTM) as edge detection method. FTM increases gradient of endoscopy images and then, it will represent better performance rather than traditional methods. The proposed FTM was applied on 21 endoscopic images consist of normal and abnormal images included Lymphangiectasia captured by Wireless Capsule Endoscopy (WCE). The results show that, this method presents a better performance rather than color Canny edge detector. The detection results were validated with ground truth image was drawn by an independent board certified gastroenterologists. The proposed method was detected 96% of borders of Lymphangiectasia and 75% of borders in normal images. In comparison, it was detected 75% and 51% of Lymphangiectasia and normal image borders before using FTM respectively.

KW - color Canny edge detector

KW - Fisher Transform Method

KW - Lymphangiectasia

KW - Wireless Capsule Endoscopy

UR - http://www.scopus.com/inward/record.url?scp=84941100934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941100934&partnerID=8YFLogxK

U2 - 10.1109/NEBEC.2015.7117145

DO - 10.1109/NEBEC.2015.7117145

M3 - Conference contribution

T3 - 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015

BT - 2015 41st Annual Northeast Biomedical Engineering Conference, NEBEC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -