Automatic generation of statistical pose and shape models for articulated joints

Statistical analysis of motion patterns of body joints is potentially useful for detecting and quantifying pathologies. However, building a statistical motion model across different subjects remains a challenging task, especially for a complex joint like the wrist. We present a novel framework for s...

Full description

Bibliographic Details
Main Authors: Chen, Xin, Graham, Jim, Hutchinson, Charles, Muir, Lindsay
Format: Article
Published: Institute of Electrical and Electronics Engineers 2013
Subjects:
Online Access:https://eprints.nottingham.ac.uk/42106/
_version_ 1848796420508745728
author Chen, Xin
Graham, Jim
Hutchinson, Charles
Muir, Lindsay
author_facet Chen, Xin
Graham, Jim
Hutchinson, Charles
Muir, Lindsay
author_sort Chen, Xin
building Nottingham Research Data Repository
collection Online Access
description Statistical analysis of motion patterns of body joints is potentially useful for detecting and quantifying pathologies. However, building a statistical motion model across different subjects remains a challenging task, especially for a complex joint like the wrist. We present a novel framework for simultaneous registration and segmentation of multiple 3-D (CT or MR) volumes of different subjects at various articulated positions. The framework starts with a pose model generated from 3-D volumes captured at different articulated positions of a single subject (template). This initial pose model is used to register the template volume to image volumes from new subjects. During this process, the Grow-Cut algorithm is used in an iterative refinement of the segmentation of the bone along with the pose parameters. As each new subject is registered and segmented, the pose model is updated, improving the accuracy of successive registrations. We applied the algorithm to CT images of the wrist from 25 subjects, each at five different wrist positions and demonstrated that it performed robustly and accurately. More importantly, the resulting segmentations allowed a statistical pose model of the carpal bones to be generated automatically without interaction. The evaluation results show that our proposed framework achieved accurate registration with an average mean target registration error of mm. The automatic segmentation results also show high consistency with the ground truth obtained semi-automatically. Furthermore, we demonstrated the capability of the resulting statistical pose and shape models by using them to generate a measurement tool for scaphoid-lunate dissociation diagnosis, which achieved 90% sensitivity and specificity.
first_indexed 2025-11-14T19:47:42Z
format Article
id nottingham-42106
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:47:42Z
publishDate 2013
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling nottingham-421062020-05-04T16:39:24Z https://eprints.nottingham.ac.uk/42106/ Automatic generation of statistical pose and shape models for articulated joints Chen, Xin Graham, Jim Hutchinson, Charles Muir, Lindsay Statistical analysis of motion patterns of body joints is potentially useful for detecting and quantifying pathologies. However, building a statistical motion model across different subjects remains a challenging task, especially for a complex joint like the wrist. We present a novel framework for simultaneous registration and segmentation of multiple 3-D (CT or MR) volumes of different subjects at various articulated positions. The framework starts with a pose model generated from 3-D volumes captured at different articulated positions of a single subject (template). This initial pose model is used to register the template volume to image volumes from new subjects. During this process, the Grow-Cut algorithm is used in an iterative refinement of the segmentation of the bone along with the pose parameters. As each new subject is registered and segmented, the pose model is updated, improving the accuracy of successive registrations. We applied the algorithm to CT images of the wrist from 25 subjects, each at five different wrist positions and demonstrated that it performed robustly and accurately. More importantly, the resulting segmentations allowed a statistical pose model of the carpal bones to be generated automatically without interaction. The evaluation results show that our proposed framework achieved accurate registration with an average mean target registration error of mm. The automatic segmentation results also show high consistency with the ground truth obtained semi-automatically. Furthermore, we demonstrated the capability of the resulting statistical pose and shape models by using them to generate a measurement tool for scaphoid-lunate dissociation diagnosis, which achieved 90% sensitivity and specificity. Institute of Electrical and Electronics Engineers 2013-10-11 Article PeerReviewed Chen, Xin, Graham, Jim, Hutchinson, Charles and Muir, Lindsay (2013) Automatic generation of statistical pose and shape models for articulated joints. IEEE Transactions on Medical Imaging, 33 (2). pp. 372-383. ISSN 1558-254X Wrist Carpal bones 3D image registration Segmentation Statistical pose model Statistical shape model Articulated joint http://ieeexplore.ieee.org/document/6630071/ doi:10.1109/TMI.2013.2285503 doi:10.1109/TMI.2013.2285503
spellingShingle Wrist
Carpal bones
3D image registration
Segmentation
Statistical pose model
Statistical shape model
Articulated joint
Chen, Xin
Graham, Jim
Hutchinson, Charles
Muir, Lindsay
Automatic generation of statistical pose and shape models for articulated joints
title Automatic generation of statistical pose and shape models for articulated joints
title_full Automatic generation of statistical pose and shape models for articulated joints
title_fullStr Automatic generation of statistical pose and shape models for articulated joints
title_full_unstemmed Automatic generation of statistical pose and shape models for articulated joints
title_short Automatic generation of statistical pose and shape models for articulated joints
title_sort automatic generation of statistical pose and shape models for articulated joints
topic Wrist
Carpal bones
3D image registration
Segmentation
Statistical pose model
Statistical shape model
Articulated joint
url https://eprints.nottingham.ac.uk/42106/
https://eprints.nottingham.ac.uk/42106/
https://eprints.nottingham.ac.uk/42106/