Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
Neuroimage. 2018 Apr 15;170:446-455. doi: 10.1016/j.neuroimage.2017.04.041. Epub 2017 Apr 23.
Segmentation of key brain tissues from 3D medical images is of great significance for brain disease diagnosis, progression assessment and monitoring of neurologic conditions. While manual segmentation is time-consuming, laborious, and subjective, automated segmentation is quite challenging due to the complicated anatomical environment of brain and the large variations of brain tissues. We propose a novel voxelwise residual network (VoxResNet) with a set of effective training schemes to cope with this challenging problem. The main merit of residual learning is that it can alleviate the degradation problem when training a deep network so that the performance gains achieved by increasing the network depth can be fully leveraged. With this technique, our VoxResNet is built with 25 layers, and hence can generate more representative features to deal with the large variations of brain tissues than its rivals using hand-crafted features or shallower networks. In order to effectively train such a deep network with limited training data for brain segmentation, we seamlessly integrate multi-modality and multi-level contextual information into our network, so that the complementary information of different modalities can be harnessed and features of different scales can be exploited. Furthermore, an auto-context version of the VoxResNet is proposed by combining the low-level image appearance features, implicit shape information, and high-level context together for further improving the segmentation performance. Extensive experiments on the well-known benchmark (i.e., MRBrainS) of brain segmentation from 3D magnetic resonance (MR) images corroborated the efficacy of the proposed VoxResNet. Our method achieved the first place in the challenge out of 37 competitors including several state-of-the-art brain segmentation methods. Our method is inherently general and can be readily applied as a powerful tool to many brain-related studies, where accurate segmentation of brain structures is critical.
从三维医学图像中分割关键脑组织对于脑疾病诊断、进展评估和神经状况监测具有重要意义。虽然手动分割耗时、费力且主观，但由于大脑解剖环境复杂，脑组织变化较大，自动分割极具挑战性。我们提出了一种新颖的体素残差网络（VoxResNet），并结合了一系列有效的训练方案来应对这一具有挑战性的问题。残差学习的主要优点是它可以缓解训练深度网络时的退化问题，从而充分利用增加网络深度所带来的性能提升。通过这种技术，我们的 VoxResNet 构建了 25 层，因此可以生成更具代表性的特征，从而比使用手工制作特征或较浅网络的竞争对手更好地处理脑组织的大变化。为了有效地训练具有有限训练数据的用于脑分割的这种深度网络，我们将多模态和多层次上下文信息无缝地集成到我们的网络中，从而可以利用不同模态的互补信息并利用不同尺度的特征。此外，通过将低水平的图像外观特征、隐式形状信息和高级上下文结合在一起，提出了 VoxResNet 的自动上下文版本，以进一步提高分割性能。在基于三维磁共振（MR）图像的脑分割的知名基准（即 MRBrainS）上进行的广泛实验验证了所提出的 VoxResNet 的有效性。在包括几种最先进的脑分割方法在内的 37 个竞争对手中，我们的方法在挑战赛中获得了第一名。我们的方法具有内在的通用性，可以很容易地应用于许多与大脑相关的研究中，在这些研究中，准确的脑结构分割至关重要。
