3D Intervertebral Disc Localization and Segmentation from MR Images by Data-Driven Regression and Classification

Chu, Chengwen; Belavy, D.; Zheng, Guoyan (2014). 3D Intervertebral Disc Localization and Segmentation from MR Images by Data-Driven Regression and Classification. In: Wu, Guorong; Zhang, Daoqiang; Zhou, Luping (eds.) MLMI 2014, LNCS 8679. Lecture Notes in Computer Science: Vol. 8679 (pp. 50-58). Cham: Springer 10.1007/978-3-319-10581-9_7

[img] Text
chp%3A10.1007%2F978-3-319-10581-9_7.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB)

In this paper we propose a new fully-automatic method for
localizing and segmenting 3D intervertebral discs from MR images, where
the two problems are solved in a unified data-driven regression and classification
framework. We estimate the output (image displacements for
localization, or fg/bg labels for segmentation) of image points by exploiting
both training data and geometric constraints simultaneously.
The problem is formulated in a unified objective function which is then
solved globally and efficiently. We validate our method on MR images
of 25 patients. Taking manually labeled data as the ground truth, our
method achieves a mean localization error of 1.3 mm, a mean Dice metric
of 87%, and a mean surface distance of 1.3 mm. Our method can be
applied to other localization and segmentation tasks.

Item Type:

Book Section (Book Chapter)

Division/Institute:

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

UniBE Contributor:

Chu, Chengwen, Zheng, Guoyan

Subjects:

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

ISSN:

0302-9743

ISBN:

978-3-319-10580-2

Series:

Lecture Notes in Computer Science

Publisher:

Springer

Language:

German

Submitter:

Guoyan Zheng

Date Deposited:

01 May 2015 15:39

Last Modified:

05 Dec 2022 14:46

Publisher DOI:

10.1007/978-3-319-10581-9_7

BORIS DOI:

10.7892/boris.67983

URI:

https://boris.unibe.ch/id/eprint/67983

Actions (login required)

Edit item Edit item
Provide Feedback