Biomedical Applications in Molecular, Structural, and Functional Imaging

Abdomen and spinal cord segmentation with augmented active shape models

[+] Author Affiliations
Zhoubing Xu

Vanderbilt University, Electrical Engineering, 2301 Vanderbilt Place, P.O. Box 351679 Station B, Nashville, Tennessee 37235, United States

Benjamin N. Conrad, Seth A. Smith

Vanderbilt University, Institute of Imaging Science, 1161 21st Avenue South, AA-1105, Nashville, Tennessee 37232, United States

Vanderbilt University, Radiology and Radiological Science, 1161 21st Avenue South, Nashville, Tennessee 37203, United States

Rebeccah B. Baucom, Benjamin K. Poulose

Vanderbilt University Medical Center, General Surgery, 1161 21st Avenue South, D5203, Nashville, Tennessee 37232, United States

Bennett A. Landman

Vanderbilt University, Electrical Engineering, 2301 Vanderbilt Place, P.O. Box 351679 Station B, Nashville, Tennessee 37235, United States

Vanderbilt University, Institute of Imaging Science, 1161 21st Avenue South, AA-1105, Nashville, Tennessee 37232, United States

Vanderbilt University, Radiology and Radiological Science, 1161 21st Avenue South, Nashville, Tennessee 37203, United States

J. Med. Imag. 3(3), 036002 (Aug 26, 2016). doi:10.1117/1.JMI.3.3.036002
History: Received January 27, 2016; Accepted August 5, 2016
Text Size: A A A

Abstract.  Active shape models (ASMs) have been widely used for extracting human anatomies in medical images given their capability for shape regularization of topology preservation. However, sensitivity to model initialization and local correspondence search often undermines their performances, especially around highly variable contexts in computed-tomography (CT) and magnetic resonance (MR) images. In this study, we propose an augmented ASM (AASM) by integrating the multiatlas label fusion (MALF) and level set (LS) techniques into the traditional ASM framework. Using AASM, landmark updates are optimized globally via a region-based LS evolution applied on the probability map generated from MALF. This augmentation effectively extends the searching range of correspondent landmarks while reducing sensitivity to the image contexts and improves the segmentation robustness. We propose the AASM framework as a two-dimensional segmentation technique targeting structures with one axis of regularity. We apply AASM approach to abdomen CT and spinal cord (SC) MR segmentation challenges. On 20 CT scans, the AASM segmentation of the whole abdominal wall enables the subcutaneous/visceral fat measurement, with high correlation to the measurement derived from manual segmentation. On 28 3T MR scans, AASM yields better performances than other state-of-the-art approaches in segmenting white/gray matter in SC.

Figures in this Article
© 2016 Society of Photo-Optical Instrumentation Engineers

Citation

Zhoubing Xu ; Benjamin N. Conrad ; Rebeccah B. Baucom ; Seth A. Smith ; Benjamin K. Poulose, et al.
"Abdomen and spinal cord segmentation with augmented active shape models", J. Med. Imag. 3(3), 036002 (Aug 26, 2016). ; http://dx.doi.org/10.1117/1.JMI.3.3.036002


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.