Liu Yilin, Nacewicz Brendon M, Zhao Gengyan, Adluru Nagesh, Kirk Gregory R, Ferrazzano Peter A, Styner Martin A, Alexander Andrew L
Waisman Brain Imaging Laboratory, University of Wisconsin-Madison, Madison, WI, United States.
Department of Psychiatry, University of Wisconsin-Madison, Madison, WI, United States.
Front Neurosci. 2020 May 21;14:260. doi: 10.3389/fnins.2020.00260. eCollection 2020.
Recent advances in deep learning have improved the segmentation accuracy of subcortical brain structures, which would be useful in neuroimaging studies of many neurological disorders. However, most existing deep learning based approaches in neuroimaging do not investigate the specific difficulties that exist in segmenting extremely small but important brain regions such as the subnuclei of the amygdala. To tackle this challenging task, we developed a dual-branch dilated residual 3D fully convolutional network with parallel convolutions to extract more global context and alleviate the class imbalance issue by maintaining a small receptive field that is just the size of the regions of interest (ROIs). We also conduct multi-scale feature fusion in both parallel and series to compensate the potential information loss during convolutions, which has been shown to be important for small objects. The serial feature fusion enabled by residual connections is further enhanced by a proposed top-down attention-guided refinement unit, where the high-resolution low-level spatial details are selectively integrated to complement the high-level but coarse semantic information, enriching the final feature representations. As a result, the segmentations resulting from our method are more accurate both volumetrically and morphologically, compared with other deep learning based approaches. To the best of our knowledge, this work is the first deep learning-based approach that targets the subregions of the amygdala. We also demonstrated the feasibility of using a cycle-consistent generative adversarial network (CycleGAN) to harmonize multi-site MRI data, and show that our method generalizes well to challenging traumatic brain injury (TBI) datasets collected from multiple centers. This appears to be a promising strategy for image segmentation for multiple site studies and increased morphological variability from significant brain pathology.
深度学习的最新进展提高了大脑皮层下结构的分割精度，这在许多神经系统疾病的神经影像学研究中很有用。然而，神经影像学中大多数现有的基于深度学习的方法并未研究在分割极小但重要的脑区（如杏仁核亚核）时存在的具体困难。为了解决这一具有挑战性的任务，我们开发了一种具有并行卷积的双分支扩张残差3D全卷积网络，以提取更多全局上下文，并通过保持仅与感兴趣区域（ROI）大小相同的小感受野来缓解类别不平衡问题。我们还在并行和串行中进行多尺度特征融合，以补偿卷积过程中潜在的信息损失，这已被证明对小物体很重要。由残差连接实现的串行特征融合通过提出的自上而下注意力引导细化单元进一步增强，其中高分辨率的低级空间细节被选择性地整合以补充高级但粗糙的语义信息，丰富最终的特征表示。结果，与其他基于深度学习的方法相比，我们的方法所得到的分割在体积和形态上都更准确。据我们所知，这项工作是第一种针对杏仁核子区域的基于深度学习的方法。我们还展示了使用循环一致生成对抗网络（CycleGAN）来协调多站点MRI数据的可行性，并表明我们的方法能很好地推广到从多个中心收集的具有挑战性的创伤性脑损伤（TBI）数据集。这似乎是一种用于多站点研究的图像分割以及因严重脑病理导致的形态变异性增加的有前景的策略。
