WRIST: A WRist Image Segmentation Toolkit for carpal bone delineation from MRI

Brent Foster, Anand A. Joshi, Marissa Borgese, Yasser Abdelhafez, Robert D Boutin, Abhijit Chaudhari

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Segmentation of the carpal bones from 3D imaging modalities, such as magnetic resonance imaging (MRI), is commonly performed for in vivo analysis of wrist morphology, kinematics, and biomechanics. This crucial task is typically carried out manually and is labor intensive, time consuming, subject to high inter- and intra-observer variability, and may result in topologically incorrect surfaces. We present a method, WRist Image Segmentation Toolkit (WRIST), for 3D semi-automated, rapid segmentation of the carpal bones of the wrist from MRI. In our method, the boundary of the bones were iteratively found using prior known anatomical constraints and a shape-detection level set. The parameters of the method were optimized using a training dataset of 48 manually segmented carpal bones and evaluated on 112 carpal bones which included both healthy participants without known wrist conditions and participants with thumb basilar osteoarthritis (OA). Manual segmentation by two expert human observers was considered as a reference. On the healthy subject dataset we obtained a Dice overlap of 93.0 ± 3.8, Jaccard Index of 87.3 ± 6.2, and a Hausdorff distance of 2.7 ± 3.4 mm, while on the OA dataset we obtained a Dice overlap of 90.7 ± 8.6, Jaccard Index of 83.0 ± 10.6, and a Hausdorff distance of 4.0 ± 4.4 mm. The short computational time of 20.8 s per bone (or 5.1 s per bone in the parallelized version) and the high agreement with the expert observers gives WRIST the potential to be utilized in musculoskeletal research.

Original languageEnglish (US)
JournalComputerized Medical Imaging and Graphics
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Carpal Bones
Magnetic resonance
Wrist
Image segmentation
Bone
Magnetic Resonance Imaging
Imaging techniques
Biomechanical Phenomena
Bone and Bones
Osteoarthritis
Healthy Volunteers
Observer Variation
Thumb
Biomechanics
Research
Kinematics
Datasets
Personnel

Keywords

  • Bone segmentation
  • Carpal bones
  • MRI segmentation

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

WRIST : A WRist Image Segmentation Toolkit for carpal bone delineation from MRI. / Foster, Brent; Joshi, Anand A.; Borgese, Marissa; Abdelhafez, Yasser; Boutin, Robert D; Chaudhari, Abhijit.

In: Computerized Medical Imaging and Graphics, 01.01.2018.

Research output: Contribution to journalArticle

@article{426aefcdcd2847b29048dfbc008f0b3e,
title = "WRIST: A WRist Image Segmentation Toolkit for carpal bone delineation from MRI",
abstract = "Segmentation of the carpal bones from 3D imaging modalities, such as magnetic resonance imaging (MRI), is commonly performed for in vivo analysis of wrist morphology, kinematics, and biomechanics. This crucial task is typically carried out manually and is labor intensive, time consuming, subject to high inter- and intra-observer variability, and may result in topologically incorrect surfaces. We present a method, WRist Image Segmentation Toolkit (WRIST), for 3D semi-automated, rapid segmentation of the carpal bones of the wrist from MRI. In our method, the boundary of the bones were iteratively found using prior known anatomical constraints and a shape-detection level set. The parameters of the method were optimized using a training dataset of 48 manually segmented carpal bones and evaluated on 112 carpal bones which included both healthy participants without known wrist conditions and participants with thumb basilar osteoarthritis (OA). Manual segmentation by two expert human observers was considered as a reference. On the healthy subject dataset we obtained a Dice overlap of 93.0 ± 3.8, Jaccard Index of 87.3 ± 6.2, and a Hausdorff distance of 2.7 ± 3.4 mm, while on the OA dataset we obtained a Dice overlap of 90.7 ± 8.6, Jaccard Index of 83.0 ± 10.6, and a Hausdorff distance of 4.0 ± 4.4 mm. The short computational time of 20.8 s per bone (or 5.1 s per bone in the parallelized version) and the high agreement with the expert observers gives WRIST the potential to be utilized in musculoskeletal research.",
keywords = "Bone segmentation, Carpal bones, MRI segmentation",
author = "Brent Foster and Joshi, {Anand A.} and Marissa Borgese and Yasser Abdelhafez and Boutin, {Robert D} and Abhijit Chaudhari",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.compmedimag.2017.12.003",
language = "English (US)",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - WRIST

T2 - A WRist Image Segmentation Toolkit for carpal bone delineation from MRI

AU - Foster, Brent

AU - Joshi, Anand A.

AU - Borgese, Marissa

AU - Abdelhafez, Yasser

AU - Boutin, Robert D

AU - Chaudhari, Abhijit

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Segmentation of the carpal bones from 3D imaging modalities, such as magnetic resonance imaging (MRI), is commonly performed for in vivo analysis of wrist morphology, kinematics, and biomechanics. This crucial task is typically carried out manually and is labor intensive, time consuming, subject to high inter- and intra-observer variability, and may result in topologically incorrect surfaces. We present a method, WRist Image Segmentation Toolkit (WRIST), for 3D semi-automated, rapid segmentation of the carpal bones of the wrist from MRI. In our method, the boundary of the bones were iteratively found using prior known anatomical constraints and a shape-detection level set. The parameters of the method were optimized using a training dataset of 48 manually segmented carpal bones and evaluated on 112 carpal bones which included both healthy participants without known wrist conditions and participants with thumb basilar osteoarthritis (OA). Manual segmentation by two expert human observers was considered as a reference. On the healthy subject dataset we obtained a Dice overlap of 93.0 ± 3.8, Jaccard Index of 87.3 ± 6.2, and a Hausdorff distance of 2.7 ± 3.4 mm, while on the OA dataset we obtained a Dice overlap of 90.7 ± 8.6, Jaccard Index of 83.0 ± 10.6, and a Hausdorff distance of 4.0 ± 4.4 mm. The short computational time of 20.8 s per bone (or 5.1 s per bone in the parallelized version) and the high agreement with the expert observers gives WRIST the potential to be utilized in musculoskeletal research.

AB - Segmentation of the carpal bones from 3D imaging modalities, such as magnetic resonance imaging (MRI), is commonly performed for in vivo analysis of wrist morphology, kinematics, and biomechanics. This crucial task is typically carried out manually and is labor intensive, time consuming, subject to high inter- and intra-observer variability, and may result in topologically incorrect surfaces. We present a method, WRist Image Segmentation Toolkit (WRIST), for 3D semi-automated, rapid segmentation of the carpal bones of the wrist from MRI. In our method, the boundary of the bones were iteratively found using prior known anatomical constraints and a shape-detection level set. The parameters of the method were optimized using a training dataset of 48 manually segmented carpal bones and evaluated on 112 carpal bones which included both healthy participants without known wrist conditions and participants with thumb basilar osteoarthritis (OA). Manual segmentation by two expert human observers was considered as a reference. On the healthy subject dataset we obtained a Dice overlap of 93.0 ± 3.8, Jaccard Index of 87.3 ± 6.2, and a Hausdorff distance of 2.7 ± 3.4 mm, while on the OA dataset we obtained a Dice overlap of 90.7 ± 8.6, Jaccard Index of 83.0 ± 10.6, and a Hausdorff distance of 4.0 ± 4.4 mm. The short computational time of 20.8 s per bone (or 5.1 s per bone in the parallelized version) and the high agreement with the expert observers gives WRIST the potential to be utilized in musculoskeletal research.

KW - Bone segmentation

KW - Carpal bones

KW - MRI segmentation

UR - http://www.scopus.com/inward/record.url?scp=85040330448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040330448&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2017.12.003

DO - 10.1016/j.compmedimag.2017.12.003

M3 - Article

C2 - 29331208

AN - SCOPUS:85040330448

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

ER -