Chitphakdithai Nicha, Vives Kenneth P, Duncan James S
Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
Department of Neurosurgery, Yale School of Medicine, New Haven, CT, USA.
Proc IEEE Int Symp Biomed Imaging. 2011 Mar-Apr;2011:1520-1523. doi: 10.1109/ISBI.2011.5872690. Epub 2011 Jun 9.
Images with missing correspondences are difficult to align using standard registration methods due to the assumption that the same features appear in both images. To address this problem in brain resection images, we have recently proposed an algorithm in which the registration process is aided by an indicator map that is simultaneously estimated to distinguish between missing and valid tissue. We now extend our method to include both intensity and location information for the missing data. We introduce a prior on the indicator map using a Markov random field (MRF) framework to incorporate map smoothness and spatial knowledge of the missing correspondences. The parameters for the indicator map prior are automatically estimated along with the transformation and indicator map. The new method improves both segmentation and registration accuracy as demonstrated using synthetic and real patient data.
由于标准配准方法假定两幅图像中会出现相同的特征，因此对于缺少对应关系的图像，很难使用这些方法进行配准。为了解决脑切除图像中的这一问题，我们最近提出了一种算法，在该算法中，配准过程由一个指示图辅助，该指示图会同时进行估计，以区分缺失组织和有效组织。现在，我们将方法进行扩展，纳入了缺失数据的强度和位置信息。我们使用马尔可夫随机场（MRF）框架在指示图上引入先验，以纳入图的平滑性和缺失对应关系的空间知识。指示图先验的参数会与变换和指示图一起自动估计。如使用合成数据和真实患者数据所证明的那样，新方法提高了分割和配准的准确性。
