Statistical shape modeling of compound musculoskeletal structures around the thigh region

Chu, Chengwen; Takao, Masaki; Ogawa, Takeshi; Yokota, Futoshi; Sato, Yoshinobu; Zheng, Guoyan (2016). Statistical shape modeling of compound musculoskeletal structures around the thigh region. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI 2016) (pp. 885-888). IEEE 10.1109/ISBI.2016.7493407

[img] Text
07493407.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (3MB) | Request a copy

Accurate 3D models of lower extremity are required for model-based simulations in kinematic analysis of musculoskeletal (MS) system. In this paper, we present a modeling framework which combines a hybrid registration scheme with an articulated statistical shape model (aSSM) construction technique. The present modeling framework is used to develop an aSSM of compound MS structures based on a training set of 12 single side CT images with the associated ground-truth segmentation of 7 structures around the thigh region. By incorporating 90% of the training set variations, the model exhibits a generalization ability of 2.77±0.48 mm and specificity of 2.87±0.43 mm. The constructed aSSM has potential applications in model-based 2D-3D construction, 3D medical image segmentation, and kinematic analysis of MS system. To the best of our knowledge, this is the first 3D aSSM of compound MS structures around the thigh region.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

04 Faculty of Medicine > Pre-clinic Human Medicine > Institute for Surgical Technology & Biomechanics ISTB

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Chu, Chengwen and Zheng, Guoyan

Subjects:

500 Science > 570 Life sciences; biology
600 Technology > 610 Medicine & health
600 Technology > 620 Engineering

ISBN:

978-1-4799-2349-6

Publisher:

IEEE

Language:

English

Submitter:

Guoyan Zheng

Date Deposited:

24 May 2017 12:45

Last Modified:

24 May 2017 12:45

Publisher DOI:

10.1109/ISBI.2016.7493407

BORIS DOI:

10.7892/boris.97786

URI:

https://boris.unibe.ch/id/eprint/97786

Actions (login required)

Edit item Edit item
Provide Feedback