Ultrasound bone segmentation using dynamic programming

Pezhman Foroughi, Emad Boctor, Michael J. Swartz, Russell H Taylor, Gabor Fichtinger

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

Abstract

Segmentation of bone surface in ultrasound images has numerous applications in computer aided orthopedic surgery. A robust bone surface extraction technique for ultrasound images can be used to non-invasively probe the bone surface. In this work, we present early results with an intuitive and computationally inexpensive bone segmentation approach. The prior knowledge about the appearance of bone in ultrasound images is exploited toward achieving robust and fast bone segmentation. Continuity and smoothness of the bone surface are incorporated in a cost function, which is globally minimized using dynamic programming. The performance of this method is evaluated on ultrasound images collected from two male cadavers. The images are segmented in about half a second making the algorithm suitable for real-time applications. Comparison between manual and automatic segmentation shows an average accuracy of less than 3 pixels (0.3 mm).

Original languageEnglish (US)
Title of host publicationProceedings - IEEE Ultrasonics Symposium
Pages2523-2526
Number of pages4
DOIs
StatePublished - 2007
Event2007 IEEE Ultrasonics Symposium, IUS - New York, NY, United States
Duration: Oct 28 2007Oct 31 2007

Other

Other2007 IEEE Ultrasonics Symposium, IUS
CountryUnited States
CityNew York, NY
Period10/28/0710/31/07

Fingerprint

Dynamic programming
Bone
Ultrasonics
Orthopedics
Cost functions
Surgery
Pixels

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Foroughi, P., Boctor, E., Swartz, M. J., Taylor, R. H., & Fichtinger, G. (2007). Ultrasound bone segmentation using dynamic programming. In Proceedings - IEEE Ultrasonics Symposium (pp. 2523-2526). [4410208] https://doi.org/10.1109/ULTSYM.2007.635

Ultrasound bone segmentation using dynamic programming. / Foroughi, Pezhman; Boctor, Emad; Swartz, Michael J.; Taylor, Russell H; Fichtinger, Gabor.

Proceedings - IEEE Ultrasonics Symposium. 2007. p. 2523-2526 4410208.

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

Foroughi, P, Boctor, E, Swartz, MJ, Taylor, RH & Fichtinger, G 2007, Ultrasound bone segmentation using dynamic programming. in Proceedings - IEEE Ultrasonics Symposium., 4410208, pp. 2523-2526, 2007 IEEE Ultrasonics Symposium, IUS, New York, NY, United States, 10/28/07. https://doi.org/10.1109/ULTSYM.2007.635
Foroughi P, Boctor E, Swartz MJ, Taylor RH, Fichtinger G. Ultrasound bone segmentation using dynamic programming. In Proceedings - IEEE Ultrasonics Symposium. 2007. p. 2523-2526. 4410208 https://doi.org/10.1109/ULTSYM.2007.635
Foroughi, Pezhman ; Boctor, Emad ; Swartz, Michael J. ; Taylor, Russell H ; Fichtinger, Gabor. / Ultrasound bone segmentation using dynamic programming. Proceedings - IEEE Ultrasonics Symposium. 2007. pp. 2523-2526
@inproceedings{5cd545a4031a4c65891dfcb05daba0a5,
title = "Ultrasound bone segmentation using dynamic programming",
abstract = "Segmentation of bone surface in ultrasound images has numerous applications in computer aided orthopedic surgery. A robust bone surface extraction technique for ultrasound images can be used to non-invasively probe the bone surface. In this work, we present early results with an intuitive and computationally inexpensive bone segmentation approach. The prior knowledge about the appearance of bone in ultrasound images is exploited toward achieving robust and fast bone segmentation. Continuity and smoothness of the bone surface are incorporated in a cost function, which is globally minimized using dynamic programming. The performance of this method is evaluated on ultrasound images collected from two male cadavers. The images are segmented in about half a second making the algorithm suitable for real-time applications. Comparison between manual and automatic segmentation shows an average accuracy of less than 3 pixels (0.3 mm).",
author = "Pezhman Foroughi and Emad Boctor and Swartz, {Michael J.} and Taylor, {Russell H} and Gabor Fichtinger",
year = "2007",
doi = "10.1109/ULTSYM.2007.635",
language = "English (US)",
isbn = "1424413834",
pages = "2523--2526",
booktitle = "Proceedings - IEEE Ultrasonics Symposium",

}

TY - GEN

T1 - Ultrasound bone segmentation using dynamic programming

AU - Foroughi, Pezhman

AU - Boctor, Emad

AU - Swartz, Michael J.

AU - Taylor, Russell H

AU - Fichtinger, Gabor

PY - 2007

Y1 - 2007

N2 - Segmentation of bone surface in ultrasound images has numerous applications in computer aided orthopedic surgery. A robust bone surface extraction technique for ultrasound images can be used to non-invasively probe the bone surface. In this work, we present early results with an intuitive and computationally inexpensive bone segmentation approach. The prior knowledge about the appearance of bone in ultrasound images is exploited toward achieving robust and fast bone segmentation. Continuity and smoothness of the bone surface are incorporated in a cost function, which is globally minimized using dynamic programming. The performance of this method is evaluated on ultrasound images collected from two male cadavers. The images are segmented in about half a second making the algorithm suitable for real-time applications. Comparison between manual and automatic segmentation shows an average accuracy of less than 3 pixels (0.3 mm).

AB - Segmentation of bone surface in ultrasound images has numerous applications in computer aided orthopedic surgery. A robust bone surface extraction technique for ultrasound images can be used to non-invasively probe the bone surface. In this work, we present early results with an intuitive and computationally inexpensive bone segmentation approach. The prior knowledge about the appearance of bone in ultrasound images is exploited toward achieving robust and fast bone segmentation. Continuity and smoothness of the bone surface are incorporated in a cost function, which is globally minimized using dynamic programming. The performance of this method is evaluated on ultrasound images collected from two male cadavers. The images are segmented in about half a second making the algorithm suitable for real-time applications. Comparison between manual and automatic segmentation shows an average accuracy of less than 3 pixels (0.3 mm).

UR - http://www.scopus.com/inward/record.url?scp=44949229714&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949229714&partnerID=8YFLogxK

U2 - 10.1109/ULTSYM.2007.635

DO - 10.1109/ULTSYM.2007.635

M3 - Conference contribution

AN - SCOPUS:44949229714

SN - 1424413834

SN - 9781424413836

SP - 2523

EP - 2526

BT - Proceedings - IEEE Ultrasonics Symposium

ER -