Xue Hui, Srinivasan Latha, Jiang Shuzhou, Rutherford Mary, Edwards A David, Rueckert Daniel, Hajnal Jo V
Imaging Sciences Department, Imperial College, London, Du cane Road, UK.
Inf Process Med Imaging. 2007;20:257-69. doi: 10.1007/978-3-540-73273-0_22.
The segmentation of neonatal cortex from magnetic resonance (MR) images is much more challenging than the segmentation of cortex in adults. The main reason is the inverted contrast between grey matter (GM) and white matter (WM) that occurs when myelination is incomplete. This causes mislabeled partial volume voxels, especially at the interface between GM and cerebrospinal fluid (CSF). We propose a fully automatic cortical segmentation algorithm, detecting these mislabeled voxels using a knowledge-based approach and correcting errors by adjusting local priors to favor the correct classification. Our results show that the proposed algorithm corrects errors in the segmentation of both GM and WM compared to the classic EM scheme. The segmentation algorithm has been tested on 25 neonates with the gestational ages ranging from approximately 27 to 45 weeks. Quantitative comparison to the manual segmentation demonstrates good performance of the method (mean Dice similarity: 0.758 +/- 0.037 for GM and 0.794 +/- 0.078 for WM).
从磁共振（MR）图像中分割新生儿大脑皮层比分割成人大脑皮层更具挑战性。主要原因是在髓鞘形成不完全时，灰质（GM）和白质（WM）之间会出现对比度反转。这会导致部分体素标记错误，尤其是在GM与脑脊液（CSF）的界面处。我们提出了一种全自动皮层分割算法，使用基于知识的方法检测这些标记错误的体素，并通过调整局部先验以支持正确分类来纠正错误。我们的结果表明，与经典的期望最大化（EM）方案相比，所提出的算法纠正了GM和WM分割中的错误。该分割算法已在25名胎龄约为27至45周的新生儿上进行了测试。与手动分割的定量比较表明该方法具有良好的性能（GM的平均骰子相似系数：0.758±0.037，WM的平均骰子相似系数：0.794±0.078）。
