Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

How Many Templates Does It Take for a Good Segmentation? Error Analysis in Multiatlas Segmentation as a Function of Database Size

Institution:
Scientific Computing and Imaging (SCI) Institute, University of Utah, Salt Lake City, UT, USA.
Publisher:
Int Conf Med Image Comput Comput Assist Interv. MICCAI 2012
Publication Date:
Oct-2012
Journal:
Med Image Comput Comput Assist Interv
Volume Number:
15
Issue Number:
Pt 2
Pages:
103-14
Citation:
Int Conf Med Image Comput Comput Assist Interv. 2012 Oct;15(Pt 2):103-14.
PubMed ID:
24501720
PMCID:
PMC3910563
Appears in Collections:
NA-MIC
Sponsors:
U54 EB005149/EB/NIBIB NIH HHS/United States
P41 RR012553/RR/NCRR NIH HHS/United States
Generated Citation:
Awate S.P., Zhu P., Whitaker R.T. How Many Templates Does It Take for a Good Segmentation? Error Analysis in Multiatlas Segmentation as a Function of Database Size. Int Conf Med Image Comput Comput Assist Interv. 2012 Oct;15(Pt 2):103-14. PMID: 24501720. PMCID: PMC3910563.
Downloaded: 1199 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

This paper proposes a novel formulation to model and analyze the statistical characteristics of some types of segmentation problems that are based on combining label maps / templates / atlases. Such segmentation-by-example approaches are quite powerful on their own for several clinical applications and they provide prior information, through spatial context, when combined with intensity-based segmentation methods. The proposed formulation models a class of multiatlas segmentation problems as nonparametric regression problems in the high-dimensional space of images. The paper presents a systematic analysis of the nonparametric estimation’s convergence behavior (i.e. characterizing segmentation error as a function of the size of the multiatlas database) and shows that it has a specific analytic form involving several parameters that are fundamental to the specific segmentation problem (i.e. chosen anatomical structure, imaging modality, registration method, label-fusion algorithm, etc.). We describe how to estimate these parameters and show that several brain anatomical structures exhibit the trends determined analytically. The proposed framework also provides per-voxel confidence measures for the segmentation. We show that the segmentation error for large database sizes can be predicted using small-sized databases. Thus, small databases can be exploited to predict the database sizes required (“how many templates”) to achieve “good” segmentations having errors lower than a specified tolerance. Such cost-benefit analysis is crucial for designing and deploying multiatlas segmentation systems.

Additional Material
1 File (68.53kB)
Awate-MICCAI2012-fig2.jpg (68.53kB)