Supraspinatus Segmentation from Shoulder Ultrasound Images Using a Multilayer Self-shrinking Snake

You Wei Wang, Chung Chien Lee, Chung Ming Lo

Research output: Contribution to journalArticle

Abstract

Objective: Over people’s lifetimes, the prevalence of shoulder pain exceeds 70%. In particular, 70% of shoulder pain is caused by rotator cuff lesions which are located in the supraspinatus area. The automatic and quantitative segmentation of the supraspinatus area can provide a more-objective and accurate assessment of rotator cuff lesions. Methods: In this study, 108 shoulder ultrasound images comprised the image database to evaluate the proposed segmentation method, and a multilayer selfshrinking snake (S3), based on a multilayer segmentation framework, was used to achieve optimal segmentation. Using a rough initial contour that enclosed the supraspinatus area, the modified snake was shrunken with an iteration procedure according to boundary conditions that included the elasticity, curvature, gradient, and distance. Results: In the performance evaluation, the S3 achieved an F-measure of 0.85. Conclusions: The success of the S3 could provide more-objective location information to physicians diagnosing rotator cuff lesions.

Original languageEnglish
JournalIEEE Access
DOIs
Publication statusAccepted/In press - Jan 1 2018

Fingerprint

Multilayers
Ultrasonics
Elasticity
Boundary conditions

Keywords

  • Elasticity
  • Image segmentation
  • Lesions
  • Nonhomogeneous media
  • Pain
  • rotator cuff
  • segmentation
  • Shoulder
  • shoulder pain
  • snake
  • Ultrasonic imaging
  • ultrasound

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Supraspinatus Segmentation from Shoulder Ultrasound Images Using a Multilayer Self-shrinking Snake. / Wang, You Wei; Lee, Chung Chien; Lo, Chung Ming.

In: IEEE Access, 01.01.2018.

Research output: Contribution to journalArticle

@article{1423ff90d217496d8899d3c91bda5da9,
title = "Supraspinatus Segmentation from Shoulder Ultrasound Images Using a Multilayer Self-shrinking Snake",
abstract = "Objective: Over people’s lifetimes, the prevalence of shoulder pain exceeds 70{\%}. In particular, 70{\%} of shoulder pain is caused by rotator cuff lesions which are located in the supraspinatus area. The automatic and quantitative segmentation of the supraspinatus area can provide a more-objective and accurate assessment of rotator cuff lesions. Methods: In this study, 108 shoulder ultrasound images comprised the image database to evaluate the proposed segmentation method, and a multilayer selfshrinking snake (S3), based on a multilayer segmentation framework, was used to achieve optimal segmentation. Using a rough initial contour that enclosed the supraspinatus area, the modified snake was shrunken with an iteration procedure according to boundary conditions that included the elasticity, curvature, gradient, and distance. Results: In the performance evaluation, the S3 achieved an F-measure of 0.85. Conclusions: The success of the S3 could provide more-objective location information to physicians diagnosing rotator cuff lesions.",
keywords = "Elasticity, Image segmentation, Lesions, Nonhomogeneous media, Pain, rotator cuff, segmentation, Shoulder, shoulder pain, snake, Ultrasonic imaging, ultrasound",
author = "Wang, {You Wei} and Lee, {Chung Chien} and Lo, {Chung Ming}",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2885709",
language = "English",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Supraspinatus Segmentation from Shoulder Ultrasound Images Using a Multilayer Self-shrinking Snake

AU - Wang, You Wei

AU - Lee, Chung Chien

AU - Lo, Chung Ming

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Objective: Over people’s lifetimes, the prevalence of shoulder pain exceeds 70%. In particular, 70% of shoulder pain is caused by rotator cuff lesions which are located in the supraspinatus area. The automatic and quantitative segmentation of the supraspinatus area can provide a more-objective and accurate assessment of rotator cuff lesions. Methods: In this study, 108 shoulder ultrasound images comprised the image database to evaluate the proposed segmentation method, and a multilayer selfshrinking snake (S3), based on a multilayer segmentation framework, was used to achieve optimal segmentation. Using a rough initial contour that enclosed the supraspinatus area, the modified snake was shrunken with an iteration procedure according to boundary conditions that included the elasticity, curvature, gradient, and distance. Results: In the performance evaluation, the S3 achieved an F-measure of 0.85. Conclusions: The success of the S3 could provide more-objective location information to physicians diagnosing rotator cuff lesions.

AB - Objective: Over people’s lifetimes, the prevalence of shoulder pain exceeds 70%. In particular, 70% of shoulder pain is caused by rotator cuff lesions which are located in the supraspinatus area. The automatic and quantitative segmentation of the supraspinatus area can provide a more-objective and accurate assessment of rotator cuff lesions. Methods: In this study, 108 shoulder ultrasound images comprised the image database to evaluate the proposed segmentation method, and a multilayer selfshrinking snake (S3), based on a multilayer segmentation framework, was used to achieve optimal segmentation. Using a rough initial contour that enclosed the supraspinatus area, the modified snake was shrunken with an iteration procedure according to boundary conditions that included the elasticity, curvature, gradient, and distance. Results: In the performance evaluation, the S3 achieved an F-measure of 0.85. Conclusions: The success of the S3 could provide more-objective location information to physicians diagnosing rotator cuff lesions.

KW - Elasticity

KW - Image segmentation

KW - Lesions

KW - Nonhomogeneous media

KW - Pain

KW - rotator cuff

KW - segmentation

KW - Shoulder

KW - shoulder pain

KW - snake

KW - Ultrasonic imaging

KW - ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85058636651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058636651&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2885709

DO - 10.1109/ACCESS.2018.2885709

M3 - Article

AN - SCOPUS:85058636651

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -