Learning disease severity for capsule endoscopy images

R. Kumar, P. Rajan, S. Bejakovic, S. Seshamani, Gerard Mullin, T. Dassopoulos, Gregory Hager

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

Abstract

Wireless capsule endoscopy (CE) is increasing being used to assess several gastrointestinal(GI) diseases and disorders. Current clinical methods are based on subjective evaluation of images. In this paper, we develop a method for ranking lesions appearing in CE images. This ranking is based on pairwise comparisons among representative images supplied by an expert. With such sparse pairwise rank information for a small number of images, we investigate methods for creating and evaluating global ranking functions. In experiments with CE images, we train statistical classifiers using color and edge feature descriptors extracted frommanually annotated regions of interest. Experiments on a data set using Crohn's disease lesions for lesion severity are presented with the developed ranking functions achieve high accuracy rates.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
Pages1314-1317
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 - Boston, MA, United States
Duration: Jun 28 2009Jul 1 2009

Other

Other2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
CountryUnited States
CityBoston, MA
Period6/28/097/1/09

Fingerprint

Capsule Endoscopy
Endoscopy
Learning
Gastrointestinal Diseases
Crohn Disease
Classifiers
Color
Experiments

Keywords

  • Capsule endoscopy
  • Disease severity
  • Ordinal regression
  • Statistical classification

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Kumar, R., Rajan, P., Bejakovic, S., Seshamani, S., Mullin, G., Dassopoulos, T., & Hager, G. (2009). Learning disease severity for capsule endoscopy images. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 (pp. 1314-1317). [5193306] https://doi.org/10.1109/ISBI.2009.5193306

Learning disease severity for capsule endoscopy images. / Kumar, R.; Rajan, P.; Bejakovic, S.; Seshamani, S.; Mullin, Gerard; Dassopoulos, T.; Hager, Gregory.

Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 1314-1317 5193306.

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

Kumar, R, Rajan, P, Bejakovic, S, Seshamani, S, Mullin, G, Dassopoulos, T & Hager, G 2009, Learning disease severity for capsule endoscopy images. in Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009., 5193306, pp. 1314-1317, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009, Boston, MA, United States, 6/28/09. https://doi.org/10.1109/ISBI.2009.5193306
Kumar R, Rajan P, Bejakovic S, Seshamani S, Mullin G, Dassopoulos T et al. Learning disease severity for capsule endoscopy images. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 1314-1317. 5193306 https://doi.org/10.1109/ISBI.2009.5193306
Kumar, R. ; Rajan, P. ; Bejakovic, S. ; Seshamani, S. ; Mullin, Gerard ; Dassopoulos, T. ; Hager, Gregory. / Learning disease severity for capsule endoscopy images. Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. pp. 1314-1317
@inproceedings{fbe2e0f360904f5b960521b7a419de06,
title = "Learning disease severity for capsule endoscopy images",
abstract = "Wireless capsule endoscopy (CE) is increasing being used to assess several gastrointestinal(GI) diseases and disorders. Current clinical methods are based on subjective evaluation of images. In this paper, we develop a method for ranking lesions appearing in CE images. This ranking is based on pairwise comparisons among representative images supplied by an expert. With such sparse pairwise rank information for a small number of images, we investigate methods for creating and evaluating global ranking functions. In experiments with CE images, we train statistical classifiers using color and edge feature descriptors extracted frommanually annotated regions of interest. Experiments on a data set using Crohn's disease lesions for lesion severity are presented with the developed ranking functions achieve high accuracy rates.",
keywords = "Capsule endoscopy, Disease severity, Ordinal regression, Statistical classification",
author = "R. Kumar and P. Rajan and S. Bejakovic and S. Seshamani and Gerard Mullin and T. Dassopoulos and Gregory Hager",
year = "2009",
doi = "10.1109/ISBI.2009.5193306",
language = "English (US)",
isbn = "9781424439324",
pages = "1314--1317",
booktitle = "Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009",

}

TY - GEN

T1 - Learning disease severity for capsule endoscopy images

AU - Kumar, R.

AU - Rajan, P.

AU - Bejakovic, S.

AU - Seshamani, S.

AU - Mullin, Gerard

AU - Dassopoulos, T.

AU - Hager, Gregory

PY - 2009

Y1 - 2009

N2 - Wireless capsule endoscopy (CE) is increasing being used to assess several gastrointestinal(GI) diseases and disorders. Current clinical methods are based on subjective evaluation of images. In this paper, we develop a method for ranking lesions appearing in CE images. This ranking is based on pairwise comparisons among representative images supplied by an expert. With such sparse pairwise rank information for a small number of images, we investigate methods for creating and evaluating global ranking functions. In experiments with CE images, we train statistical classifiers using color and edge feature descriptors extracted frommanually annotated regions of interest. Experiments on a data set using Crohn's disease lesions for lesion severity are presented with the developed ranking functions achieve high accuracy rates.

AB - Wireless capsule endoscopy (CE) is increasing being used to assess several gastrointestinal(GI) diseases and disorders. Current clinical methods are based on subjective evaluation of images. In this paper, we develop a method for ranking lesions appearing in CE images. This ranking is based on pairwise comparisons among representative images supplied by an expert. With such sparse pairwise rank information for a small number of images, we investigate methods for creating and evaluating global ranking functions. In experiments with CE images, we train statistical classifiers using color and edge feature descriptors extracted frommanually annotated regions of interest. Experiments on a data set using Crohn's disease lesions for lesion severity are presented with the developed ranking functions achieve high accuracy rates.

KW - Capsule endoscopy

KW - Disease severity

KW - Ordinal regression

KW - Statistical classification

UR - http://www.scopus.com/inward/record.url?scp=70449449418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449449418&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2009.5193306

DO - 10.1109/ISBI.2009.5193306

M3 - Conference contribution

AN - SCOPUS:70449449418

SN - 9781424439324

SP - 1314

EP - 1317

BT - Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009

ER -