Segmentation of flexor tendons within carpal tunnel from magnetic resonance image

Hsin Chen Chen, Yung-Nien Sun, Yi Ying Wang, Cheng Hsien Lin, Chien-Kuo Wang, I. Ming Jou

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

1 Citation (Scopus)

Abstract

Carpal tunnel syndrome (CTS) is one of the most common peripheral neuropathies. For evaluation of the CTS, segmentation of carpal tunnel and its contents from magnetic resonance (MR) images is rather important. In this paper we propose a new segmentation framework for the flexor tendons within the carpal tunnel on MR images. The proposed method consists of two stages including construction of reference tendon contour (RTC) and registration-based segmentation. Initially, we segment the flexor tendons from the most proximally cross-sectional image using watershed algorithm. The resulting segmented tendons then serve as the RTCs and are applied to the registration-based segmentation stage. Each of the RTCs in this stage is registered to its distally adjacent image by a rigid transformation and then its shape is refined by snake deformation. The registration-based segmentation is sequentially performed on each pair of adjacent cross-sectional images along the proximal to distal direction until the most distal image is segmented. Consequently, the flexor tendons in the entire MR volume can be automatically segmented. In the experiments three MR volumes were used to validate the accuracy of the proposed method. Compared to the manual results, our proposed method showed good agreement on the tendon segmentations with dice similarity coefficient above 0.8.

Original languageEnglish
Title of host publicationICS 2010 - International Computer Symposium
Pages932-935
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan
Duration: 2010 Dec 162010 Dec 18

Publication series

NameICS 2010 - International Computer Symposium

Other

Other2010 International Computer Symposium, ICS 2010
CountryTaiwan
CityTainan
Period10-12-1610-12-18

Fingerprint

Tendons
Magnetic resonance
Tunnels
Watersheds
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Chen, H. C., Sun, Y-N., Wang, Y. Y., Lin, C. H., Wang, C-K., & Jou, I. M. (2010). Segmentation of flexor tendons within carpal tunnel from magnetic resonance image. In ICS 2010 - International Computer Symposium (pp. 932-935). [5685376] (ICS 2010 - International Computer Symposium). https://doi.org/10.1109/COMPSYM.2010.5685376
Chen, Hsin Chen ; Sun, Yung-Nien ; Wang, Yi Ying ; Lin, Cheng Hsien ; Wang, Chien-Kuo ; Jou, I. Ming. / Segmentation of flexor tendons within carpal tunnel from magnetic resonance image. ICS 2010 - International Computer Symposium. 2010. pp. 932-935 (ICS 2010 - International Computer Symposium).
@inproceedings{a374b06c05d94df1aa643d13572adfb5,
title = "Segmentation of flexor tendons within carpal tunnel from magnetic resonance image",
abstract = "Carpal tunnel syndrome (CTS) is one of the most common peripheral neuropathies. For evaluation of the CTS, segmentation of carpal tunnel and its contents from magnetic resonance (MR) images is rather important. In this paper we propose a new segmentation framework for the flexor tendons within the carpal tunnel on MR images. The proposed method consists of two stages including construction of reference tendon contour (RTC) and registration-based segmentation. Initially, we segment the flexor tendons from the most proximally cross-sectional image using watershed algorithm. The resulting segmented tendons then serve as the RTCs and are applied to the registration-based segmentation stage. Each of the RTCs in this stage is registered to its distally adjacent image by a rigid transformation and then its shape is refined by snake deformation. The registration-based segmentation is sequentially performed on each pair of adjacent cross-sectional images along the proximal to distal direction until the most distal image is segmented. Consequently, the flexor tendons in the entire MR volume can be automatically segmented. In the experiments three MR volumes were used to validate the accuracy of the proposed method. Compared to the manual results, our proposed method showed good agreement on the tendon segmentations with dice similarity coefficient above 0.8.",
author = "Chen, {Hsin Chen} and Yung-Nien Sun and Wang, {Yi Ying} and Lin, {Cheng Hsien} and Chien-Kuo Wang and Jou, {I. Ming}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/COMPSYM.2010.5685376",
language = "English",
isbn = "9781424476404",
series = "ICS 2010 - International Computer Symposium",
pages = "932--935",
booktitle = "ICS 2010 - International Computer Symposium",

}

Chen, HC, Sun, Y-N, Wang, YY, Lin, CH, Wang, C-K & Jou, IM 2010, Segmentation of flexor tendons within carpal tunnel from magnetic resonance image. in ICS 2010 - International Computer Symposium., 5685376, ICS 2010 - International Computer Symposium, pp. 932-935, 2010 International Computer Symposium, ICS 2010, Tainan, Taiwan, 10-12-16. https://doi.org/10.1109/COMPSYM.2010.5685376

Segmentation of flexor tendons within carpal tunnel from magnetic resonance image. / Chen, Hsin Chen; Sun, Yung-Nien; Wang, Yi Ying; Lin, Cheng Hsien; Wang, Chien-Kuo; Jou, I. Ming.

ICS 2010 - International Computer Symposium. 2010. p. 932-935 5685376 (ICS 2010 - International Computer Symposium).

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

TY - GEN

T1 - Segmentation of flexor tendons within carpal tunnel from magnetic resonance image

AU - Chen, Hsin Chen

AU - Sun, Yung-Nien

AU - Wang, Yi Ying

AU - Lin, Cheng Hsien

AU - Wang, Chien-Kuo

AU - Jou, I. Ming

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Carpal tunnel syndrome (CTS) is one of the most common peripheral neuropathies. For evaluation of the CTS, segmentation of carpal tunnel and its contents from magnetic resonance (MR) images is rather important. In this paper we propose a new segmentation framework for the flexor tendons within the carpal tunnel on MR images. The proposed method consists of two stages including construction of reference tendon contour (RTC) and registration-based segmentation. Initially, we segment the flexor tendons from the most proximally cross-sectional image using watershed algorithm. The resulting segmented tendons then serve as the RTCs and are applied to the registration-based segmentation stage. Each of the RTCs in this stage is registered to its distally adjacent image by a rigid transformation and then its shape is refined by snake deformation. The registration-based segmentation is sequentially performed on each pair of adjacent cross-sectional images along the proximal to distal direction until the most distal image is segmented. Consequently, the flexor tendons in the entire MR volume can be automatically segmented. In the experiments three MR volumes were used to validate the accuracy of the proposed method. Compared to the manual results, our proposed method showed good agreement on the tendon segmentations with dice similarity coefficient above 0.8.

AB - Carpal tunnel syndrome (CTS) is one of the most common peripheral neuropathies. For evaluation of the CTS, segmentation of carpal tunnel and its contents from magnetic resonance (MR) images is rather important. In this paper we propose a new segmentation framework for the flexor tendons within the carpal tunnel on MR images. The proposed method consists of two stages including construction of reference tendon contour (RTC) and registration-based segmentation. Initially, we segment the flexor tendons from the most proximally cross-sectional image using watershed algorithm. The resulting segmented tendons then serve as the RTCs and are applied to the registration-based segmentation stage. Each of the RTCs in this stage is registered to its distally adjacent image by a rigid transformation and then its shape is refined by snake deformation. The registration-based segmentation is sequentially performed on each pair of adjacent cross-sectional images along the proximal to distal direction until the most distal image is segmented. Consequently, the flexor tendons in the entire MR volume can be automatically segmented. In the experiments three MR volumes were used to validate the accuracy of the proposed method. Compared to the manual results, our proposed method showed good agreement on the tendon segmentations with dice similarity coefficient above 0.8.

UR - http://www.scopus.com/inward/record.url?scp=79851473032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851473032&partnerID=8YFLogxK

U2 - 10.1109/COMPSYM.2010.5685376

DO - 10.1109/COMPSYM.2010.5685376

M3 - Conference contribution

SN - 9781424476404

T3 - ICS 2010 - International Computer Symposium

SP - 932

EP - 935

BT - ICS 2010 - International Computer Symposium

ER -

Chen HC, Sun Y-N, Wang YY, Lin CH, Wang C-K, Jou IM. Segmentation of flexor tendons within carpal tunnel from magnetic resonance image. In ICS 2010 - International Computer Symposium. 2010. p. 932-935. 5685376. (ICS 2010 - International Computer Symposium). https://doi.org/10.1109/COMPSYM.2010.5685376