Supervised Domain Adaptation for Automatic Sub-cortical Brain Structure Segmentation with Minimal User Interaction
Supervised Domain Adaptation for Automatic Sub-cortical Brain Structure Segmentation with Minimal User Interaction
复制标题
DOI：
10.1038/s41598-019-43299-z
复制
发表时间：
2019-05-01
影响因子：
4.6
通讯作者：
Llado, Xavier
中科院分区：
文献类型：
--
作者：
Kushibar, Kaisar;Valverde, Sergi;Llado, Xavier
近年来，一些卷积神经网络（CNN）已经被提出来分割来自磁共振图像（MRI）的皮层下脑结构。尽管这些方法提供了准确的分割，但是存在关于从不同图像域分割MRI体积的再现性问题，例如，协议、扫描仪和强度曲线的差异。因此，网络必须从头开始重新训练，以在不同的成像领域中类似地执行，限制了这种方法在临床环境中的适用性。在本文中，我们采用迁移学习策略来解决域转移问题。我们通过利用预训练网络获得的知识来减少训练图像的数量，并通过减少CNN的可训练参数的数量来提高训练速度。我们在两个公开的数据集上测试了我们的方法- MICCAI 2012和IBSR -并将它们与常用的方法进行了比较：FIRST。我们的方法显示出与完全训练的CNN获得的结果相似的结果，并且我们的方法使用了来自目标域的图像数量明显较少。此外，仅用来自MICCAI 2012的一张图像和来自IBSR数据集的三张图像训练网络就足以显著优于FIRST，分别为（p < 0.001）和（p < 0.05）。
In recent years, some convolutional neural networks (CNNs) have been proposed to segment subcortical brain structures from magnetic resonance images (MRIs). Although these methods provide accurate segmentation, there is a reproducibility issue regarding segmenting MRI volumes from different image domains-e.g., differences in protocol, scanner, and intensity profile. Thus, the network must be retrained from scratch to perform similarly in different imaging domains, limiting the applicability of such methods in clinical settings. In this paper, we employ the transfer learning strategy to solve the domain shift problem. We reduced the number of training images by leveraging the knowledge obtained by a pretrained network, and improved the training speed by reducing the number of trainable parameters of the CNN. We tested our method on two publicly available datasets - MICCAI 2012 and IBSR - and compared them with a commonly used approach: FIRST. Our method showed similar results to those obtained by a fully trained CNN, and our method used a remarkably smaller number of images from the target domain. Moreover, training the network with only one image from MICCAI 2012 and three images from IBSR datasets was sufficient to significantly outperform FIRST with (p < 0.001) and (p < 0.05), respectively.