Effects of Registration Regularization and Atlas Sharpness on Segmentation Accuracy

@article{Yeo2007EffectsOR,
  title={Effects of Registration Regularization and Atlas Sharpness on Segmentation Accuracy},
  author={B. T. Thomas Yeo and Mert R. Sabuncu and Rahul S Desikan and Bruce Fischl and Polina Golland},
  journal={Medical image analysis},
  year={2007},
  volume={12 5},
  pages={603-15}
}
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… CONTINUE READING