IEEE Trans Med Imaging. 2017 Jul;36(7):1533-1541. doi: 10.1109/TMI.2017.2679713. Epub 2017 Mar 8.
Digital reconstruction, or tracing, of 3-D neuron structure from microscopy images is a critical step toward reversing engineering the wiring and anatomy of a brain. Despite a number of prior attempts, this task remains very challenging, especially when images are contaminated by noises or have discontinued segments of neurite patterns. An approach for addressing such problems is to identify the locations of neuronal voxels using image segmentation methods, prior to applying tracing or reconstruction techniques. This preprocessing step is expected to remove noises in the data, thereby leading to improved reconstruction results. In this paper, we proposed to use 3-D convolutional neural networks (CNNs) for segmenting the neuronal microscopy images. Specifically, we designed a novel CNN architecture, that takes volumetric images as the inputs and their voxel-wise segmentation maps as the outputs. The developed architecture allows us to train and predict using large microscopy images in an end-to-end manner. We evaluated the performance of our model on a variety of challenging 3-D microscopy images from different organisms. Results showed that the proposed methods improved the tracing performance significantly when combined with different reconstruction algorithms.
从显微镜图像中对 3D 神经元结构进行数字重建或追踪，是对大脑进行逆向工程、重建其连接和解剖结构的关键步骤。尽管已经进行了多次尝试，但这项任务仍然极具挑战性，尤其是当图像受到噪声干扰或神经突模式出现不连续部分时。解决此类问题的一种方法是，在应用追踪或重建技术之前，使用图像分割方法来确定神经元体素的位置。这一预处理步骤有望去除数据中的噪声，从而提高重建结果。在本文中，我们提出使用 3D 卷积神经网络 (CNN) 对神经元显微镜图像进行分割。具体来说，我们设计了一种新颖的 CNN 架构，该架构将体积图像作为输入，并将其体素级分割图作为输出。所开发的架构允许我们以端到端的方式使用大型显微镜图像进行训练和预测。我们在来自不同生物体的各种具有挑战性的 3D 显微镜图像上评估了我们模型的性能。结果表明，当与不同的重建算法结合使用时，所提出的方法显著提高了追踪性能。
