Registration-based segmentation with articulated model from multipostural magnetic resonance images for hand bone motion animation

Hsin Chen Chen, I. Ming Jou, Chien-Kuo Wang, Fong-chin Su, Yung-Nien Sun

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Purpose: The quantitative measurements of hand bones, including volume, surface, orientation, and position are essential in investigating hand kinematics. Moreover, within the measurement stage, bone segmentation is the most important step due to its certain influences on measuring accuracy. Since hand bones are small and tubular in shape, magnetic resonance (MR) imaging is prone to artifacts such as nonuniform intensity and fuzzy boundaries. Thus, greater detail is required for improving segmentation accuracy. The authors then propose using a novel registration-based method on an articulated hand model to segment hand bones from multipostural MR images. Methods: The proposed method consists of the model construction and registration-based segmentation stages. Given a reference postural image, the first stage requires construction of a drivable reference model characterized by hand bone shapes, intensity patterns, and articulated joint mechanism. By applying the reference model to the second stage, the authors initially design a model-based registration pursuant to intensity distribution similarity, MR bone intensity properties, and constraints of model geometry to align the reference model to target bone regions of the given postural image. The authors then refine the resulting surface to improve the superimposition between the registered reference model and target bone boundaries. Results: For each subject, given a reference postural image, the proposed method can automatically segment all hand bones from all other postural images. Compared to the ground truth from two experts, the resulting surface image had an average margin of error within 1 mm (mm) only. In addition, the proposed method showed good agreement on the overlap of bone segmentations by dice similarity coefficient and also demonstrated better segmentation results than conventional methods. Conclusions: The proposed registration-based segmentation method can successfully overcome drawbacks caused by inherent artifacts in MR images and obtain more accurate segmentation results automatically. Moreover, realistic hand motion animations can be generated based on the bone segmentation results. The proposed method is found helpful for understanding hand bone geometries in dynamic postures that can be used in simulating 3D hand motion through multipostural MR images.

Original languageEnglish
Pages (from-to)2670-2682
Number of pages13
JournalMedical Physics
Volume37
Issue number6
DOIs
Publication statusPublished - 2010 Jan 1

Fingerprint

Hand Bones
Magnetic Resonance Spectroscopy
Bone and Bones
Hand
Artifacts
Posture
Biomechanical Phenomena
Joints
Magnetic Resonance Imaging

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

@article{7d29782148b04b05b6d146771900d8e2,
title = "Registration-based segmentation with articulated model from multipostural magnetic resonance images for hand bone motion animation",
abstract = "Purpose: The quantitative measurements of hand bones, including volume, surface, orientation, and position are essential in investigating hand kinematics. Moreover, within the measurement stage, bone segmentation is the most important step due to its certain influences on measuring accuracy. Since hand bones are small and tubular in shape, magnetic resonance (MR) imaging is prone to artifacts such as nonuniform intensity and fuzzy boundaries. Thus, greater detail is required for improving segmentation accuracy. The authors then propose using a novel registration-based method on an articulated hand model to segment hand bones from multipostural MR images. Methods: The proposed method consists of the model construction and registration-based segmentation stages. Given a reference postural image, the first stage requires construction of a drivable reference model characterized by hand bone shapes, intensity patterns, and articulated joint mechanism. By applying the reference model to the second stage, the authors initially design a model-based registration pursuant to intensity distribution similarity, MR bone intensity properties, and constraints of model geometry to align the reference model to target bone regions of the given postural image. The authors then refine the resulting surface to improve the superimposition between the registered reference model and target bone boundaries. Results: For each subject, given a reference postural image, the proposed method can automatically segment all hand bones from all other postural images. Compared to the ground truth from two experts, the resulting surface image had an average margin of error within 1 mm (mm) only. In addition, the proposed method showed good agreement on the overlap of bone segmentations by dice similarity coefficient and also demonstrated better segmentation results than conventional methods. Conclusions: The proposed registration-based segmentation method can successfully overcome drawbacks caused by inherent artifacts in MR images and obtain more accurate segmentation results automatically. Moreover, realistic hand motion animations can be generated based on the bone segmentation results. The proposed method is found helpful for understanding hand bone geometries in dynamic postures that can be used in simulating 3D hand motion through multipostural MR images.",
author = "Chen, {Hsin Chen} and Jou, {I. Ming} and Chien-Kuo Wang and Fong-chin Su and Yung-Nien Sun",
year = "2010",
month = "1",
day = "1",
doi = "10.1118/1.3395580",
language = "English",
volume = "37",
pages = "2670--2682",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

Registration-based segmentation with articulated model from multipostural magnetic resonance images for hand bone motion animation. / Chen, Hsin Chen; Jou, I. Ming; Wang, Chien-Kuo; Su, Fong-chin; Sun, Yung-Nien.

In: Medical Physics, Vol. 37, No. 6, 01.01.2010, p. 2670-2682.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Registration-based segmentation with articulated model from multipostural magnetic resonance images for hand bone motion animation

AU - Chen, Hsin Chen

AU - Jou, I. Ming

AU - Wang, Chien-Kuo

AU - Su, Fong-chin

AU - Sun, Yung-Nien

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Purpose: The quantitative measurements of hand bones, including volume, surface, orientation, and position are essential in investigating hand kinematics. Moreover, within the measurement stage, bone segmentation is the most important step due to its certain influences on measuring accuracy. Since hand bones are small and tubular in shape, magnetic resonance (MR) imaging is prone to artifacts such as nonuniform intensity and fuzzy boundaries. Thus, greater detail is required for improving segmentation accuracy. The authors then propose using a novel registration-based method on an articulated hand model to segment hand bones from multipostural MR images. Methods: The proposed method consists of the model construction and registration-based segmentation stages. Given a reference postural image, the first stage requires construction of a drivable reference model characterized by hand bone shapes, intensity patterns, and articulated joint mechanism. By applying the reference model to the second stage, the authors initially design a model-based registration pursuant to intensity distribution similarity, MR bone intensity properties, and constraints of model geometry to align the reference model to target bone regions of the given postural image. The authors then refine the resulting surface to improve the superimposition between the registered reference model and target bone boundaries. Results: For each subject, given a reference postural image, the proposed method can automatically segment all hand bones from all other postural images. Compared to the ground truth from two experts, the resulting surface image had an average margin of error within 1 mm (mm) only. In addition, the proposed method showed good agreement on the overlap of bone segmentations by dice similarity coefficient and also demonstrated better segmentation results than conventional methods. Conclusions: The proposed registration-based segmentation method can successfully overcome drawbacks caused by inherent artifacts in MR images and obtain more accurate segmentation results automatically. Moreover, realistic hand motion animations can be generated based on the bone segmentation results. The proposed method is found helpful for understanding hand bone geometries in dynamic postures that can be used in simulating 3D hand motion through multipostural MR images.

AB - Purpose: The quantitative measurements of hand bones, including volume, surface, orientation, and position are essential in investigating hand kinematics. Moreover, within the measurement stage, bone segmentation is the most important step due to its certain influences on measuring accuracy. Since hand bones are small and tubular in shape, magnetic resonance (MR) imaging is prone to artifacts such as nonuniform intensity and fuzzy boundaries. Thus, greater detail is required for improving segmentation accuracy. The authors then propose using a novel registration-based method on an articulated hand model to segment hand bones from multipostural MR images. Methods: The proposed method consists of the model construction and registration-based segmentation stages. Given a reference postural image, the first stage requires construction of a drivable reference model characterized by hand bone shapes, intensity patterns, and articulated joint mechanism. By applying the reference model to the second stage, the authors initially design a model-based registration pursuant to intensity distribution similarity, MR bone intensity properties, and constraints of model geometry to align the reference model to target bone regions of the given postural image. The authors then refine the resulting surface to improve the superimposition between the registered reference model and target bone boundaries. Results: For each subject, given a reference postural image, the proposed method can automatically segment all hand bones from all other postural images. Compared to the ground truth from two experts, the resulting surface image had an average margin of error within 1 mm (mm) only. In addition, the proposed method showed good agreement on the overlap of bone segmentations by dice similarity coefficient and also demonstrated better segmentation results than conventional methods. Conclusions: The proposed registration-based segmentation method can successfully overcome drawbacks caused by inherent artifacts in MR images and obtain more accurate segmentation results automatically. Moreover, realistic hand motion animations can be generated based on the bone segmentation results. The proposed method is found helpful for understanding hand bone geometries in dynamic postures that can be used in simulating 3D hand motion through multipostural MR images.

UR - http://www.scopus.com/inward/record.url?scp=77953490969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953490969&partnerID=8YFLogxK

U2 - 10.1118/1.3395580

DO - 10.1118/1.3395580

M3 - Article

VL - 37

SP - 2670

EP - 2682

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -