Model-based tendon segmentation from ultrasound images

Bo I. Chuang, Yung-Nien Sun, Tai-Hua Yang, Fong-chin Su, Li-Chieh Kuo, I. Ming Jou

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

3 Citations (Scopus)

Abstract

In orthopedics, trigger finger is one of the popular occupational hazards in recent years. Ultrasound images are usually used for diagnosing the severity of trigger finger clinically. Finger ultrasound image has two important characteristics: the shape of tendon is close to an ellipse, and the tendon boundaries vary significantly in image appearance. The traditional segmentation methods usually cannot segment the tendon well. In this study, we develop an ultrasound image detection and estimation system that can assist clinician to locate and evaluate the area of tendon and synovial sheath automatically. An adaptive texture-based active shape model (ATASM) method is proposed to overcome the complex segmentation problems with the proposed shape model by minimizing the objective function based on gradient and texture information. Considering the segmentation may have many local solutions due to various image qualities, the genetic algorithm (GA) is adopted to search for the best shape parameters. In the experiments, the results of tendon segmentation are found with small segmentation errors and similar to the contour drawn by trained users.

Original languageEnglish
Title of host publicationProceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479937288
DOIs
Publication statusPublished - 2014 Dec 2
Event2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014 - Boston, United States
Duration: 2014 Apr 252014 Apr 27

Publication series

NameProceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC
Volume2014-December
ISSN (Print)1071-121X
ISSN (Electronic)2160-7001

Other

Other2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014
CountryUnited States
CityBoston
Period14-04-2514-04-27

Fingerprint

Tendons
Ultrasonics
Textures
Orthopedics
Image quality
Hazards
Genetic algorithms
Experiments

All Science Journal Classification (ASJC) codes

  • Bioengineering

Cite this

Chuang, B. I., Sun, Y-N., Yang, T-H., Su, F., Kuo, L-C., & Jou, I. M. (2014). Model-based tendon segmentation from ultrasound images. In Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014 [6972757] (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC; Vol. 2014-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEBEC.2014.6972757
Chuang, Bo I. ; Sun, Yung-Nien ; Yang, Tai-Hua ; Su, Fong-chin ; Kuo, Li-Chieh ; Jou, I. Ming. / Model-based tendon segmentation from ultrasound images. Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC).
@inproceedings{e23416b1a8814122956930ebb13dc140,
title = "Model-based tendon segmentation from ultrasound images",
abstract = "In orthopedics, trigger finger is one of the popular occupational hazards in recent years. Ultrasound images are usually used for diagnosing the severity of trigger finger clinically. Finger ultrasound image has two important characteristics: the shape of tendon is close to an ellipse, and the tendon boundaries vary significantly in image appearance. The traditional segmentation methods usually cannot segment the tendon well. In this study, we develop an ultrasound image detection and estimation system that can assist clinician to locate and evaluate the area of tendon and synovial sheath automatically. An adaptive texture-based active shape model (ATASM) method is proposed to overcome the complex segmentation problems with the proposed shape model by minimizing the objective function based on gradient and texture information. Considering the segmentation may have many local solutions due to various image qualities, the genetic algorithm (GA) is adopted to search for the best shape parameters. In the experiments, the results of tendon segmentation are found with small segmentation errors and similar to the contour drawn by trained users.",
author = "Chuang, {Bo I.} and Yung-Nien Sun and Tai-Hua Yang and Fong-chin Su and Li-Chieh Kuo and Jou, {I. Ming}",
year = "2014",
month = "12",
day = "2",
doi = "10.1109/NEBEC.2014.6972757",
language = "English",
series = "Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014",
address = "United States",

}

Chuang, BI, Sun, Y-N, Yang, T-H, Su, F, Kuo, L-C & Jou, IM 2014, Model-based tendon segmentation from ultrasound images. in Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014., 6972757, Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC, vol. 2014-December, Institute of Electrical and Electronics Engineers Inc., 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014, Boston, United States, 14-04-25. https://doi.org/10.1109/NEBEC.2014.6972757

Model-based tendon segmentation from ultrasound images. / Chuang, Bo I.; Sun, Yung-Nien; Yang, Tai-Hua; Su, Fong-chin; Kuo, Li-Chieh; Jou, I. Ming.

Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 6972757 (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC; Vol. 2014-December).

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

TY - GEN

T1 - Model-based tendon segmentation from ultrasound images

AU - Chuang, Bo I.

AU - Sun, Yung-Nien

AU - Yang, Tai-Hua

AU - Su, Fong-chin

AU - Kuo, Li-Chieh

AU - Jou, I. Ming

PY - 2014/12/2

Y1 - 2014/12/2

N2 - In orthopedics, trigger finger is one of the popular occupational hazards in recent years. Ultrasound images are usually used for diagnosing the severity of trigger finger clinically. Finger ultrasound image has two important characteristics: the shape of tendon is close to an ellipse, and the tendon boundaries vary significantly in image appearance. The traditional segmentation methods usually cannot segment the tendon well. In this study, we develop an ultrasound image detection and estimation system that can assist clinician to locate and evaluate the area of tendon and synovial sheath automatically. An adaptive texture-based active shape model (ATASM) method is proposed to overcome the complex segmentation problems with the proposed shape model by minimizing the objective function based on gradient and texture information. Considering the segmentation may have many local solutions due to various image qualities, the genetic algorithm (GA) is adopted to search for the best shape parameters. In the experiments, the results of tendon segmentation are found with small segmentation errors and similar to the contour drawn by trained users.

AB - In orthopedics, trigger finger is one of the popular occupational hazards in recent years. Ultrasound images are usually used for diagnosing the severity of trigger finger clinically. Finger ultrasound image has two important characteristics: the shape of tendon is close to an ellipse, and the tendon boundaries vary significantly in image appearance. The traditional segmentation methods usually cannot segment the tendon well. In this study, we develop an ultrasound image detection and estimation system that can assist clinician to locate and evaluate the area of tendon and synovial sheath automatically. An adaptive texture-based active shape model (ATASM) method is proposed to overcome the complex segmentation problems with the proposed shape model by minimizing the objective function based on gradient and texture information. Considering the segmentation may have many local solutions due to various image qualities, the genetic algorithm (GA) is adopted to search for the best shape parameters. In the experiments, the results of tendon segmentation are found with small segmentation errors and similar to the contour drawn by trained users.

UR - http://www.scopus.com/inward/record.url?scp=84940675900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940675900&partnerID=8YFLogxK

U2 - 10.1109/NEBEC.2014.6972757

DO - 10.1109/NEBEC.2014.6972757

M3 - Conference contribution

T3 - Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC

BT - Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chuang BI, Sun Y-N, Yang T-H, Su F, Kuo L-C, Jou IM. Model-based tendon segmentation from ultrasound images. In Proceedings - 2014 40th Annual Northeast Bioengineering Conference, NEBEC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 6972757. (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC). https://doi.org/10.1109/NEBEC.2014.6972757