Information-theoretic feature detection in ultrasound images

Greg Slabaugh; Gozde Unal; Ti Chiun Chang

doi:10.1109/IEMBS.2006.260254

Information-theoretic feature detection in ultrasound images

Greg Slabaugh^*, Gozde Unal, Ti Chiun Chang

^*Corresponding author for this work

Siemens

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

The detection of image features is an essential component of medical image processing, and has wide-ranging applications including adaptive filtering, segmentation, and registration. In this paper, we present an information-theoretic approach to feature detection in ultrasound images. Ultrasound images are corrupted by speckle noise, which is a disruptive random pattern that obscures the features of interest. Using theoretical probability density functions of the speckle intensity distributions, we derive analytic expressions that measure the distance between distributions taken from different regions in an ultrasound image and use these distances to detect features. We compare the technique to classic gradient-based feature detection methods.

Original language	English
Title of host publication	28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
Pages	2638-2642
Number of pages	5
DOIs	https://doi.org/10.1109/IEMBS.2006.260254
Publication status	Published - 2006
Externally published	Yes
Event	28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 - New York, NY, United States Duration: 30 Aug 2006 → 3 Sept 2006

Publication series

Name	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
ISSN (Print)	0589-1019

Conference

Conference	28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
Country/Territory	United States
City	New York, NY
Period	30/08/06 → 3/09/06

Access to Document

10.1109/IEMBS.2006.260254

Cite this

Slabaugh, G., Unal, G., & Chang, T. C. (2006). Information-theoretic feature detection in ultrasound images. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 (pp. 2638-2642). Article 4029590 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings). https://doi.org/10.1109/IEMBS.2006.260254

@inproceedings{f31e2888112e4531ae27fef8f8867708,

title = "Information-theoretic feature detection in ultrasound images",

abstract = "The detection of image features is an essential component of medical image processing, and has wide-ranging applications including adaptive filtering, segmentation, and registration. In this paper, we present an information-theoretic approach to feature detection in ultrasound images. Ultrasound images are corrupted by speckle noise, which is a disruptive random pattern that obscures the features of interest. Using theoretical probability density functions of the speckle intensity distributions, we derive analytic expressions that measure the distance between distributions taken from different regions in an ultrasound image and use these distances to detect features. We compare the technique to classic gradient-based feature detection methods.",

author = "Greg Slabaugh and Gozde Unal and Chang, {Ti Chiun}",

year = "2006",

doi = "10.1109/IEMBS.2006.260254",

language = "English",

isbn = "1424400325",

series = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

pages = "2638--2642",

booktitle = "28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06",

note = "28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 ; Conference date: 30-08-2006 Through 03-09-2006",

}

Slabaugh, G, Unal, G & Chang, TC 2006, Information-theoretic feature detection in ultrasound images. in 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06., 4029590, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 2638-2642, 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06, New York, NY, United States, 30/08/06. https://doi.org/10.1109/IEMBS.2006.260254

Information-theoretic feature detection in ultrasound images. / Slabaugh, Greg; Unal, Gozde; Chang, Ti Chiun.
28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 2638-2642 4029590 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Information-theoretic feature detection in ultrasound images

AU - Slabaugh, Greg

AU - Unal, Gozde

AU - Chang, Ti Chiun

PY - 2006

Y1 - 2006

N2 - The detection of image features is an essential component of medical image processing, and has wide-ranging applications including adaptive filtering, segmentation, and registration. In this paper, we present an information-theoretic approach to feature detection in ultrasound images. Ultrasound images are corrupted by speckle noise, which is a disruptive random pattern that obscures the features of interest. Using theoretical probability density functions of the speckle intensity distributions, we derive analytic expressions that measure the distance between distributions taken from different regions in an ultrasound image and use these distances to detect features. We compare the technique to classic gradient-based feature detection methods.

AB - The detection of image features is an essential component of medical image processing, and has wide-ranging applications including adaptive filtering, segmentation, and registration. In this paper, we present an information-theoretic approach to feature detection in ultrasound images. Ultrasound images are corrupted by speckle noise, which is a disruptive random pattern that obscures the features of interest. Using theoretical probability density functions of the speckle intensity distributions, we derive analytic expressions that measure the distance between distributions taken from different regions in an ultrasound image and use these distances to detect features. We compare the technique to classic gradient-based feature detection methods.

UR - http://www.scopus.com/inward/record.url?scp=34047152984&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2006.260254

DO - 10.1109/IEMBS.2006.260254

M3 - Conference contribution

C2 - 17946127

AN - SCOPUS:34047152984

SN - 1424400325

SN - 9781424400324

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SP - 2638

EP - 2642

BT - 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06

T2 - 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06

Y2 - 30 August 2006 through 3 September 2006

ER -

Information-theoretic feature detection in ultrasound images

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this