• Register
X
Forgot Password

If you have forgotten your password you can enter your email here and get a temporary password sent to your email.

X

Leaving Community

Are you sure you want to leave this community? Leaving the community will revoke any permissions you have been granted in this community.

No
Yes

Effects of registration regularization and atlas sharpness on segmentation accuracy.

In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically determined empirically. In atlas-based segmentation, this leads to a probabilistic atlas of arbitrary sharpness: weak regularization results in well-aligned training images and a sharp atlas; strong regularization yields a "blurry" atlas. In this paper, we employ a generative model for the joint registration and segmentation of images. The atlas construction process arises naturally as estimation of the model parameters. This framework allows the computation of unbiased atlases from manually labeled data at various degrees of "sharpness", as well as the joint registration and segmentation of a novel brain in a consistent manner. We study the effects of the tradeoff of atlas sharpness and warp smoothness in the context of cortical surface parcellation. This is an important question because of the increasingly availability of atlases in public databases, and the development of registration algorithms separate from the atlas construction process. We find that the optimal segmentation (parcellation) corresponds to a unique balance of atlas sharpness and warp regularization, yielding statistically significant improvements over the FreeSurfer parcellation algorithm. Furthermore, we conclude that one can simply use a single atlas computed at an optimal sharpness for the registration-segmentation of a new subject with a pre-determined, fixed, optimal warp constraint. The optimal atlas sharpness and warp smoothness can be determined by probing the segmentation performance on available training data. Our experiments also suggest that segmentation accuracy is tolerant up to a small mismatch between atlas sharpness and warp smoothness.

Pubmed ID: 18667352

Authors

  • Yeo BT
  • Sabuncu MR
  • Desikan R
  • Fischl B
  • Golland P

Journal

Medical image analysis

Publication Data

October 12, 2008

Associated Grants

  • Agency: NCRR NIH HHS, Id: P41 RR006009
  • Agency: NCRR NIH HHS, Id: P41 RR006009-150400
  • Agency: NCRR NIH HHS, Id: P41 RR013218
  • Agency: NCRR NIH HHS, Id: P41 RR013218-06
  • Agency: NCRR NIH HHS, Id: P41-RR13218
  • Agency: NCRR NIH HHS, Id: P41-RR14075
  • Agency: NIBIB NIH HHS, Id: R01 EB001550
  • Agency: NIBIB NIH HHS, Id: R01 EB006758
  • Agency: NIBIB NIH HHS, Id: R01 EB006758-02
  • Agency: NINDS NIH HHS, Id: R01 NS051826
  • Agency: NINDS NIH HHS, Id: R01 NS051826-03
  • Agency: NINDS NIH HHS, Id: R01 NS052585
  • Agency: NINDS NIH HHS, Id: R01 NS052585-01
  • Agency: NINDS NIH HHS, Id: R01 NS052585-03
  • Agency: NCRR NIH HHS, Id: R01 RR016594
  • Agency: NCRR NIH HHS, Id: R01 RR016594-01A1
  • Agency: NCRR NIH HHS, Id: R01 RR16594-01A1
  • Agency: NINDS NIH HHS, Id: R01-NS051826
  • Agency: NIBIB NIH HHS, Id: R01EB006758
  • Agency: NCRR NIH HHS, Id: U24 RR021382
  • Agency: NCRR NIH HHS, Id: U24 RR021382
  • Agency: NCRR NIH HHS, Id: U24 RR021382-04
  • Agency: NCRR NIH HHS, Id: U24-RR021382
  • Agency: NIBIB NIH HHS, Id: U54 EB005149
  • Agency: NIBIB NIH HHS, Id: U54 EB005149-01
  • Agency: NIBIB NIH HHS, Id: U54-EB005149

Mesh Terms

  • Algorithms
  • Artifacts
  • Artificial Intelligence
  • Brain
  • Humans
  • Image Enhancement
  • Image Interpretation, Computer-Assisted
  • Imaging, Three-Dimensional
  • Magnetic Resonance Imaging
  • Pattern Recognition, Automated
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Subtraction Technique