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

Multiatlas Segmentation as Nonparametric Regression

School of Computing, University of Utah, Salt Lake City, UT, USA.
IEEE Engineering in Medicine and Biology Society
Publication Date:
IEEE Trans Med Imaging
Volume Number:
Issue Number:
IEEE Trans Med Imaging. 2014 Sep;33(9):1803-17.
PubMed ID:
Appears in Collections:
P41 RR112553/RR/NCRR NIH HHS/United States
R01 EB007688/EB/NIBIB NIH HHS/United States
N01 AR022258/AR/NIAMS NIH HHS/United States
N01 AR022259/AR/NIAMS NIH HHS/United States
N01 AR022260/AR/NIAMS NIH HHS/United States
N01 AR022261/AR/NIAMS NIH HHS/United States
N01 AR022262/AR/NIAMS NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
Generated Citation:
Awate S.P., Whitaker R.T. Multiatlas Segmentation as Nonparametric Regression. IEEE Trans Med Imaging. 2014 Sep;33(9):1803-17. PMID: 24802528. PMCID: PMC4440593.
Downloaded: 1267 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

This paper proposes a novel theoretical framework to model and analyze the statistical characteristics of a wide range of segmentation methods that incorporate a database of label maps or atlases; such methods are termed as label fusion or multiatlas segmentation. We model these multiatlas segmentation problems as nonparametric regression problems in the high-dimensional space of image patches. We analyze the nonparametric estimator's convergence behavior that characterizes expected segmentation error as a function of the size of the multiatlas database. We show that this error has an analytic form involving several parameters that are fundamental to the specific segmentation problem (determined by the chosen anatomical structure, imaging modality, registration algorithm, and label-fusion algorithm). We describe how to estimate these parameters and show that several human anatomical structures exhibit the trends modeled analytically. We use these parameter estimates to optimize the regression estimator. We show that the expected error for large database sizes is well predicted by models learned on small databases. Thus, a few expert segmentations can help predict the database sizes required to keep the expected error below a specified tolerance level. Such cost-benefit analysis is crucial for deploying clinical multiatlas segmentation systems.

Additional Material
1 File (20.812kB)
Awate-TMI2014-fig2.jpg (20.812kB)