Knee-cartilage segmentation and thickness measurement from 2D ultrasound

Prajna Desai, Ilker Hacihaliloglu

Research output: Contribution to journalArticle

Abstract

Ultrasound (US) could become a standard of care imaging modality for the quantitative assessment of femoral cartilage thickness for the early diagnosis of knee osteoarthritis. However, low contrast, high levels of speckle noise, and various imaging artefacts hinder the analysis of collected data. Accurate, robust, and fully automatic US image-enhancement and cartilage-segmentation methods are needed in order to improve the widespread deployment of this imaging modality for knee-osteoarthritis diagnosis and monitoring. In this work, we propose a method based on local-phase-based image processing for automatic knee-cartilage image enhancement, segmentation, and thickness measurement. A local-phase feature-guided dynamic-programming approach is used for the fully automatic localization of knee-bone surfaces. The localized bone surfaces are used as seed points for automating the seed-guided segmentation of the cartilage. We evaluated the Random Walker (RW), watershed, and graph-cut-based segmentation methods from 200 scans obtained from ten healthy volunteers. Validation against manual expert segmentation achieved a mean dice similarity coefficient of 0.90, 0.86, and 0.84 for the RW, watershed, and graph-cut segmentation methods, respectively. Automatically segmented cartilage regions achieved 0.18 mm localization accuracy compared to manual expert thickness measurement.

Original languageEnglish (US)
Article number43
JournalJournal of Imaging
Volume5
Issue number4
DOIs
StatePublished - Apr 1 2019

Fingerprint

Thickness measurement
Cartilage
Knee
Ultrasonics
Image Enhancement
Image enhancement
Knee Osteoarthritis
Watersheds
Imaging techniques
Seed
Seeds
Bone
Bone and Bones
Standard of Care
Speckle
Thigh
Dynamic programming
Artifacts
Early Diagnosis
Healthy Volunteers

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

Keywords

  • Cartilage thickness
  • Knee
  • Local phase
  • Osteoarthritis
  • Segmentation
  • Wltrasound

Cite this

@article{62ca88679aa8417b84703aa1d0b13e9e,
title = "Knee-cartilage segmentation and thickness measurement from 2D ultrasound",
abstract = "Ultrasound (US) could become a standard of care imaging modality for the quantitative assessment of femoral cartilage thickness for the early diagnosis of knee osteoarthritis. However, low contrast, high levels of speckle noise, and various imaging artefacts hinder the analysis of collected data. Accurate, robust, and fully automatic US image-enhancement and cartilage-segmentation methods are needed in order to improve the widespread deployment of this imaging modality for knee-osteoarthritis diagnosis and monitoring. In this work, we propose a method based on local-phase-based image processing for automatic knee-cartilage image enhancement, segmentation, and thickness measurement. A local-phase feature-guided dynamic-programming approach is used for the fully automatic localization of knee-bone surfaces. The localized bone surfaces are used as seed points for automating the seed-guided segmentation of the cartilage. We evaluated the Random Walker (RW), watershed, and graph-cut-based segmentation methods from 200 scans obtained from ten healthy volunteers. Validation against manual expert segmentation achieved a mean dice similarity coefficient of 0.90, 0.86, and 0.84 for the RW, watershed, and graph-cut segmentation methods, respectively. Automatically segmented cartilage regions achieved 0.18 mm localization accuracy compared to manual expert thickness measurement.",
keywords = "Cartilage thickness, Knee, Local phase, Osteoarthritis, Segmentation, Wltrasound",
author = "Prajna Desai and Ilker Hacihaliloglu",
year = "2019",
month = "4",
day = "1",
doi = "10.3390/jimaging5040043",
language = "English (US)",
volume = "5",
journal = "Journal of Imaging",
issn = "2313-433X",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "4",

}

Knee-cartilage segmentation and thickness measurement from 2D ultrasound. / Desai, Prajna; Hacihaliloglu, Ilker.

In: Journal of Imaging, Vol. 5, No. 4, 43, 01.04.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Knee-cartilage segmentation and thickness measurement from 2D ultrasound

AU - Desai, Prajna

AU - Hacihaliloglu, Ilker

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Ultrasound (US) could become a standard of care imaging modality for the quantitative assessment of femoral cartilage thickness for the early diagnosis of knee osteoarthritis. However, low contrast, high levels of speckle noise, and various imaging artefacts hinder the analysis of collected data. Accurate, robust, and fully automatic US image-enhancement and cartilage-segmentation methods are needed in order to improve the widespread deployment of this imaging modality for knee-osteoarthritis diagnosis and monitoring. In this work, we propose a method based on local-phase-based image processing for automatic knee-cartilage image enhancement, segmentation, and thickness measurement. A local-phase feature-guided dynamic-programming approach is used for the fully automatic localization of knee-bone surfaces. The localized bone surfaces are used as seed points for automating the seed-guided segmentation of the cartilage. We evaluated the Random Walker (RW), watershed, and graph-cut-based segmentation methods from 200 scans obtained from ten healthy volunteers. Validation against manual expert segmentation achieved a mean dice similarity coefficient of 0.90, 0.86, and 0.84 for the RW, watershed, and graph-cut segmentation methods, respectively. Automatically segmented cartilage regions achieved 0.18 mm localization accuracy compared to manual expert thickness measurement.

AB - Ultrasound (US) could become a standard of care imaging modality for the quantitative assessment of femoral cartilage thickness for the early diagnosis of knee osteoarthritis. However, low contrast, high levels of speckle noise, and various imaging artefacts hinder the analysis of collected data. Accurate, robust, and fully automatic US image-enhancement and cartilage-segmentation methods are needed in order to improve the widespread deployment of this imaging modality for knee-osteoarthritis diagnosis and monitoring. In this work, we propose a method based on local-phase-based image processing for automatic knee-cartilage image enhancement, segmentation, and thickness measurement. A local-phase feature-guided dynamic-programming approach is used for the fully automatic localization of knee-bone surfaces. The localized bone surfaces are used as seed points for automating the seed-guided segmentation of the cartilage. We evaluated the Random Walker (RW), watershed, and graph-cut-based segmentation methods from 200 scans obtained from ten healthy volunteers. Validation against manual expert segmentation achieved a mean dice similarity coefficient of 0.90, 0.86, and 0.84 for the RW, watershed, and graph-cut segmentation methods, respectively. Automatically segmented cartilage regions achieved 0.18 mm localization accuracy compared to manual expert thickness measurement.

KW - Cartilage thickness

KW - Knee

KW - Local phase

KW - Osteoarthritis

KW - Segmentation

KW - Wltrasound

UR - http://www.scopus.com/inward/record.url?scp=85067697784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067697784&partnerID=8YFLogxK

U2 - 10.3390/jimaging5040043

DO - 10.3390/jimaging5040043

M3 - Article

AN - SCOPUS:85067697784

VL - 5

JO - Journal of Imaging

JF - Journal of Imaging

SN - 2313-433X

IS - 4

M1 - 43

ER -