Image informatics for clinical and preclinical biomedical analysis

Kenneth W. Tobin, Edward Chaum, Jens Gregor, Thomas P. Karnowski, Jeffery R. Price, Jonathan Wall

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Biomedical informatics is the study of the application of computational and statistical algorithms, data structures, and methods to improve communication, understanding, and management of biomedical information. Our objective in this chapter is to describe and demonstrate our research in the use of biomedical image databases, in both preclinical and clinical settings, to classify, predict, research, diagnose, and otherwise learn from the informational content encapsulated in historical image repositories. We detail our approach of describing image content in a Bayesian probabilistic framework to achieve learning from retrieved populations of similar images. We use specific examples from two biomedical applications to describe anatomic segmentation, statistical feature generation and indexing, efficient retrieval architectures, and predictive results.

Original languageEnglish (US)
Title of host publicationComputational Intelligence in Medical Imaging
Subtitle of host publicationTechniques and Applications
PublisherCRC Press
Pages239-290
Number of pages52
ISBN (Electronic)9781420060614
ISBN (Print)9781420060591
DOIs
StatePublished - Jan 1 2009
Externally publishedYes

Fingerprint

Medical Informatics
Information Management
Informatics
Research
Data structures
Communication
Learning
Databases
data structures
learning
Population
retrieval
communication

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Medicine(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Physics and Astronomy(all)

Cite this

Tobin, K. W., Chaum, E., Gregor, J., Karnowski, T. P., Price, J. R., & Wall, J. (2009). Image informatics for clinical and preclinical biomedical analysis. In Computational Intelligence in Medical Imaging: Techniques and Applications (pp. 239-290). CRC Press. https://doi.org/10.1201/9781420060614

Image informatics for clinical and preclinical biomedical analysis. / Tobin, Kenneth W.; Chaum, Edward; Gregor, Jens; Karnowski, Thomas P.; Price, Jeffery R.; Wall, Jonathan.

Computational Intelligence in Medical Imaging: Techniques and Applications. CRC Press, 2009. p. 239-290.

Research output: Chapter in Book/Report/Conference proceedingChapter

Tobin, KW, Chaum, E, Gregor, J, Karnowski, TP, Price, JR & Wall, J 2009, Image informatics for clinical and preclinical biomedical analysis. in Computational Intelligence in Medical Imaging: Techniques and Applications. CRC Press, pp. 239-290. https://doi.org/10.1201/9781420060614
Tobin KW, Chaum E, Gregor J, Karnowski TP, Price JR, Wall J. Image informatics for clinical and preclinical biomedical analysis. In Computational Intelligence in Medical Imaging: Techniques and Applications. CRC Press. 2009. p. 239-290 https://doi.org/10.1201/9781420060614
Tobin, Kenneth W. ; Chaum, Edward ; Gregor, Jens ; Karnowski, Thomas P. ; Price, Jeffery R. ; Wall, Jonathan. / Image informatics for clinical and preclinical biomedical analysis. Computational Intelligence in Medical Imaging: Techniques and Applications. CRC Press, 2009. pp. 239-290
@inbook{fc342c94ee2549f18741e0138cd18084,
title = "Image informatics for clinical and preclinical biomedical analysis",
abstract = "Biomedical informatics is the study of the application of computational and statistical algorithms, data structures, and methods to improve communication, understanding, and management of biomedical information. Our objective in this chapter is to describe and demonstrate our research in the use of biomedical image databases, in both preclinical and clinical settings, to classify, predict, research, diagnose, and otherwise learn from the informational content encapsulated in historical image repositories. We detail our approach of describing image content in a Bayesian probabilistic framework to achieve learning from retrieved populations of similar images. We use specific examples from two biomedical applications to describe anatomic segmentation, statistical feature generation and indexing, efficient retrieval architectures, and predictive results.",
author = "Tobin, {Kenneth W.} and Edward Chaum and Jens Gregor and Karnowski, {Thomas P.} and Price, {Jeffery R.} and Jonathan Wall",
year = "2009",
month = "1",
day = "1",
doi = "10.1201/9781420060614",
language = "English (US)",
isbn = "9781420060591",
pages = "239--290",
booktitle = "Computational Intelligence in Medical Imaging",
publisher = "CRC Press",

}

TY - CHAP

T1 - Image informatics for clinical and preclinical biomedical analysis

AU - Tobin, Kenneth W.

AU - Chaum, Edward

AU - Gregor, Jens

AU - Karnowski, Thomas P.

AU - Price, Jeffery R.

AU - Wall, Jonathan

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Biomedical informatics is the study of the application of computational and statistical algorithms, data structures, and methods to improve communication, understanding, and management of biomedical information. Our objective in this chapter is to describe and demonstrate our research in the use of biomedical image databases, in both preclinical and clinical settings, to classify, predict, research, diagnose, and otherwise learn from the informational content encapsulated in historical image repositories. We detail our approach of describing image content in a Bayesian probabilistic framework to achieve learning from retrieved populations of similar images. We use specific examples from two biomedical applications to describe anatomic segmentation, statistical feature generation and indexing, efficient retrieval architectures, and predictive results.

AB - Biomedical informatics is the study of the application of computational and statistical algorithms, data structures, and methods to improve communication, understanding, and management of biomedical information. Our objective in this chapter is to describe and demonstrate our research in the use of biomedical image databases, in both preclinical and clinical settings, to classify, predict, research, diagnose, and otherwise learn from the informational content encapsulated in historical image repositories. We detail our approach of describing image content in a Bayesian probabilistic framework to achieve learning from retrieved populations of similar images. We use specific examples from two biomedical applications to describe anatomic segmentation, statistical feature generation and indexing, efficient retrieval architectures, and predictive results.

UR - http://www.scopus.com/inward/record.url?scp=85056394912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056394912&partnerID=8YFLogxK

U2 - 10.1201/9781420060614

DO - 10.1201/9781420060614

M3 - Chapter

SN - 9781420060591

SP - 239

EP - 290

BT - Computational Intelligence in Medical Imaging

PB - CRC Press

ER -