GISentinel

A software platform for automatic ulcer detection on capsule endoscopy videos

Steven Yi, Heng Jiao, Fan Meng, Jonathan A Leighton, Shabana F Pasha, Lauri Rentz

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

Abstract

In this paper, we present a novel and clinically valuable software platform for automatic ulcer detection on gastrointestinal (GI) tract from Capsule Endoscopy (CE) videos. Typical CE videos take about 8 hours. They have to be reviewed manually by physicians to detect and locate diseases such as ulcers and bleedings. The process is time consuming. Moreover, because of the long-time manual review, it is easy to lead to miss-finding. Working with our collaborators, we were focusing on developing a software platform called GISentinel, which can fully automated GI tract ulcer detection and classification. This software includes 3 parts: the frequency based Log-Gabor filter regions of interest (ROI) extraction, the unique feature selection and validation method (e.g. illumination invariant feature, color independent features, and symmetrical texture features), and the cascade SVM classification for handling "ulcer vs. non-ulcer" cases. After the experiments, this SW gave descent results. In frame-wise, the ulcer detection rate is 69.65% (319/458). In instance-wise, the ulcer detection rate is 82.35%(28/34).The false alarm rate is 16.43% (34/207). This work is a part of our innovative 2D/3D based GI tract disease detection software platform. The final goal of this SW is to find and classification of major GI tract diseases intelligently, such as bleeding, ulcer, and polyp from the CE videos. This paper will mainly describe the automatic ulcer detection functional module.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
PublisherSPIE
Volume9035
ISBN (Print)9780819498281
DOIs
StatePublished - 2014
EventMedical Imaging 2014: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 18 2014Feb 20 2014

Other

OtherMedical Imaging 2014: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/18/142/20/14

Fingerprint

ulcers
Capsule Endoscopy
Endoscopy
capsules
Ulcer
Capsules
Software
platforms
computer programs
Gastrointestinal Tract
Gabor filters
bleeding
Feature extraction
Gastrointestinal Diseases
Textures
Lighting
Color
Hemorrhage
physicians
false alarms

Keywords

  • And false alarm
  • Automatic ulcer detection
  • Capsule endoscopy
  • CE imaging
  • Disease detection
  • Miss-detection
  • Ulcer classification

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Yi, S., Jiao, H., Meng, F., Leighton, J. A., Pasha, S. F., & Rentz, L. (2014). GISentinel: A software platform for automatic ulcer detection on capsule endoscopy videos. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9035). [90352Y] SPIE. https://doi.org/10.1117/12.2042369

GISentinel : A software platform for automatic ulcer detection on capsule endoscopy videos. / Yi, Steven; Jiao, Heng; Meng, Fan; Leighton, Jonathan A; Pasha, Shabana F; Rentz, Lauri.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035 SPIE, 2014. 90352Y.

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

Yi, S, Jiao, H, Meng, F, Leighton, JA, Pasha, SF & Rentz, L 2014, GISentinel: A software platform for automatic ulcer detection on capsule endoscopy videos. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9035, 90352Y, SPIE, Medical Imaging 2014: Computer-Aided Diagnosis, San Diego, CA, United States, 2/18/14. https://doi.org/10.1117/12.2042369
Yi S, Jiao H, Meng F, Leighton JA, Pasha SF, Rentz L. GISentinel: A software platform for automatic ulcer detection on capsule endoscopy videos. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035. SPIE. 2014. 90352Y https://doi.org/10.1117/12.2042369
Yi, Steven ; Jiao, Heng ; Meng, Fan ; Leighton, Jonathan A ; Pasha, Shabana F ; Rentz, Lauri. / GISentinel : A software platform for automatic ulcer detection on capsule endoscopy videos. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035 SPIE, 2014.
@inproceedings{a24259ffd3614a90be9f1af1ffe877d9,
title = "GISentinel: A software platform for automatic ulcer detection on capsule endoscopy videos",
abstract = "In this paper, we present a novel and clinically valuable software platform for automatic ulcer detection on gastrointestinal (GI) tract from Capsule Endoscopy (CE) videos. Typical CE videos take about 8 hours. They have to be reviewed manually by physicians to detect and locate diseases such as ulcers and bleedings. The process is time consuming. Moreover, because of the long-time manual review, it is easy to lead to miss-finding. Working with our collaborators, we were focusing on developing a software platform called GISentinel, which can fully automated GI tract ulcer detection and classification. This software includes 3 parts: the frequency based Log-Gabor filter regions of interest (ROI) extraction, the unique feature selection and validation method (e.g. illumination invariant feature, color independent features, and symmetrical texture features), and the cascade SVM classification for handling {"}ulcer vs. non-ulcer{"} cases. After the experiments, this SW gave descent results. In frame-wise, the ulcer detection rate is 69.65{\%} (319/458). In instance-wise, the ulcer detection rate is 82.35{\%}(28/34).The false alarm rate is 16.43{\%} (34/207). This work is a part of our innovative 2D/3D based GI tract disease detection software platform. The final goal of this SW is to find and classification of major GI tract diseases intelligently, such as bleeding, ulcer, and polyp from the CE videos. This paper will mainly describe the automatic ulcer detection functional module.",
keywords = "And false alarm, Automatic ulcer detection, Capsule endoscopy, CE imaging, Disease detection, Miss-detection, Ulcer classification",
author = "Steven Yi and Heng Jiao and Fan Meng and Leighton, {Jonathan A} and Pasha, {Shabana F} and Lauri Rentz",
year = "2014",
doi = "10.1117/12.2042369",
language = "English (US)",
isbn = "9780819498281",
volume = "9035",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",

}

TY - GEN

T1 - GISentinel

T2 - A software platform for automatic ulcer detection on capsule endoscopy videos

AU - Yi, Steven

AU - Jiao, Heng

AU - Meng, Fan

AU - Leighton, Jonathan A

AU - Pasha, Shabana F

AU - Rentz, Lauri

PY - 2014

Y1 - 2014

N2 - In this paper, we present a novel and clinically valuable software platform for automatic ulcer detection on gastrointestinal (GI) tract from Capsule Endoscopy (CE) videos. Typical CE videos take about 8 hours. They have to be reviewed manually by physicians to detect and locate diseases such as ulcers and bleedings. The process is time consuming. Moreover, because of the long-time manual review, it is easy to lead to miss-finding. Working with our collaborators, we were focusing on developing a software platform called GISentinel, which can fully automated GI tract ulcer detection and classification. This software includes 3 parts: the frequency based Log-Gabor filter regions of interest (ROI) extraction, the unique feature selection and validation method (e.g. illumination invariant feature, color independent features, and symmetrical texture features), and the cascade SVM classification for handling "ulcer vs. non-ulcer" cases. After the experiments, this SW gave descent results. In frame-wise, the ulcer detection rate is 69.65% (319/458). In instance-wise, the ulcer detection rate is 82.35%(28/34).The false alarm rate is 16.43% (34/207). This work is a part of our innovative 2D/3D based GI tract disease detection software platform. The final goal of this SW is to find and classification of major GI tract diseases intelligently, such as bleeding, ulcer, and polyp from the CE videos. This paper will mainly describe the automatic ulcer detection functional module.

AB - In this paper, we present a novel and clinically valuable software platform for automatic ulcer detection on gastrointestinal (GI) tract from Capsule Endoscopy (CE) videos. Typical CE videos take about 8 hours. They have to be reviewed manually by physicians to detect and locate diseases such as ulcers and bleedings. The process is time consuming. Moreover, because of the long-time manual review, it is easy to lead to miss-finding. Working with our collaborators, we were focusing on developing a software platform called GISentinel, which can fully automated GI tract ulcer detection and classification. This software includes 3 parts: the frequency based Log-Gabor filter regions of interest (ROI) extraction, the unique feature selection and validation method (e.g. illumination invariant feature, color independent features, and symmetrical texture features), and the cascade SVM classification for handling "ulcer vs. non-ulcer" cases. After the experiments, this SW gave descent results. In frame-wise, the ulcer detection rate is 69.65% (319/458). In instance-wise, the ulcer detection rate is 82.35%(28/34).The false alarm rate is 16.43% (34/207). This work is a part of our innovative 2D/3D based GI tract disease detection software platform. The final goal of this SW is to find and classification of major GI tract diseases intelligently, such as bleeding, ulcer, and polyp from the CE videos. This paper will mainly describe the automatic ulcer detection functional module.

KW - And false alarm

KW - Automatic ulcer detection

KW - Capsule endoscopy

KW - CE imaging

KW - Disease detection

KW - Miss-detection

KW - Ulcer classification

UR - http://www.scopus.com/inward/record.url?scp=84902089696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902089696&partnerID=8YFLogxK

U2 - 10.1117/12.2042369

DO - 10.1117/12.2042369

M3 - Conference contribution

SN - 9780819498281

VL - 9035

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

PB - SPIE

ER -