Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France.
Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France.
Comput Methods Programs Biomed. 2022 Feb;214:106563. doi: 10.1016/j.cmpb.2021.106563. Epub 2021 Nov 29.
In order to study neural plasticity in immature brain following early brain lesion, large animal model are needed. Because of its morphological similarities with the human developmental brain, piglet is a suitable but little used one. Its study from Magnetic Resonance Imaging (MRI) requires the development of automatic algorithms for the segmentation of the different structures and tissues. A crucial preliminary step consists in automatically segmenting the brain.
We propose a fully automatic brain segmentation method applied to piglets by combining a 3D patch-based U-Net and a post-processing pipeline for spatial regularization and elimination of false positives. Our approach also integrates a transfer-learning strategy for managing an automated longitudinal monitoring evaluated for four developmental stages (2, 6, 10 and 18 weeks), facing the issue of MRI changes resulting from the rapid brain development. It is compared to a 2D approach and the Brain Extraction Tool (BET) as well as techniques adapted to other animals (rodents, macaques). The influence of training patches size and distribution is studied as well as the benefits of spatial regularization.
Results show that our approach is efficient in terms of average Dice score (0.952) and Hausdorff distance (8.51), outperforming the use of a 2D U-Net (Dice: 0.919, Hausdorff distance: 11.06) and BET (Dice: 0.764, Hausdorff distance: 25.91). The transfer-learning strategy achieves a good performance on older piglets (Dice of 0.934 at 6 weeks, 0.956 at 10 weeks and 0.958 at 18 weeks) compared to a standard training strategy with few data (Dice of 0.636 at 6 weeks, 0.907 at 10 weeks, not calculable at 18 weeks because of too few training piglets).
In conclusion, we provide a method for longitudinal MRI piglet brain segmentation based on 3D U-Net and transfer learning which can be used for future morphometric studies and applied to other animals.
为了研究早期脑损伤后未成熟大脑的神经可塑性，需要使用大动物模型。由于其在形态上与人类发育中的大脑相似，小猪是一种合适但使用较少的模型。从小猪的磁共振成像（MRI）研究中，需要开发用于分割不同结构和组织的自动算法。一个关键的初步步骤是自动分割大脑。
我们提出了一种完全自动的脑分割方法，通过结合基于 3D 补丁的 U-Net 和用于空间正则化和消除假阳性的后处理管道，应用于小猪。我们的方法还集成了一种迁移学习策略，用于管理自动纵向监测，该监测针对四个发育阶段（2、6、10 和 18 周）进行评估，以应对由于大脑快速发育导致的 MRI 变化的问题。它与 2D 方法和脑提取工具（BET）以及适用于其他动物（啮齿动物、猕猴）的技术进行了比较。还研究了训练补丁大小和分布的影响以及空间正则化的好处。
结果表明，我们的方法在平均 Dice 评分（0.952）和 Hausdorff 距离（8.51）方面都很有效，优于使用 2D U-Net（Dice：0.919，Hausdorff 距离：11.06）和 BET（Dice：0.764，Hausdorff 距离：25.91）。与使用少量数据的标准训练策略相比，迁移学习策略在较老的小猪（6 周时的 Dice 为 0.934，10 周时为 0.956，18 周时为 0.958）上表现出色，18 周时因为训练小猪太少而无法计算）。
总之，我们提供了一种基于 3D U-Net 和迁移学习的纵向 MRI 小猪脑分割方法，可用于未来的形态学研究，并可应用于其他动物。
