We address the complex problem of reliably segmenting root structure from soil in X-ray Computed Tomography (CT) images. We utilise a deep learning approach, and propose a state-of-the-art multi-resolution architecture based on encoder-decoders. While previous work in encoder-decoders implies the use of multiple resolutions simply by downsampling and upsampling images, we make this process explicit, with branches of the network tasked separately with obtaining local high-resolution segmentation, and wider low-resolution contextual information. The complete network is a memory efficient implementation that is still able to resolve small root detail in large volumetric images. We compare against a number of different encoder-decoder based architectures from the literature, as well as a popular existing image analysis tool designed for root CT segmentation. We show qualitatively and quantitatively that a multi-resolution approach offers substantial accuracy improvements over a both a small receptive field size in a deep network, or a larger receptive field in a shallower network. We then further improve performance using an incremental learning approach, in which failures in the original network are used to generate harder negative training examples. Our proposed method requires no user interaction, is fully automatic, and identifies large and fine root material throughout the whole volume.

中文翻译：

---

使用多分辨率编码器-解码器网络的三维根 CT 分割。


我们解决了在 X 射线计算机断层扫描 (CT) 图像中可靠地从土壤中分割根结构的复杂问题。我们利用深度学习方法，提出了一种基于编码器-解码器的最先进的多分辨率架构。虽然编码器-解码器之前的工作意味着仅通过对图像进行下采样和上采样来使用多种分辨率，但我们使这个过程变得明确，网络的分支分别负责获取局部高分辨率分割和更广泛的低分辨率上下文信息。完整的网络是一种内存高效的实现，仍然能够解析大体积图像中的小根细节。我们与文献中许多不同的基于编码器-解码器的架构以及为根 CT 分割设计的流行的现有图像分析工具进行了比较。我们定性和定量地表明，与深层网络中较小的感受野大小或较浅网络中较大的感受野相比，多分辨率方法可显着提高准确性。然后，我们使用增量学习方法进一步提高性能，其中原始网络中的失败用于生成更难的负面训练示例。我们提出的方法不需要用户交互，是全自动的，并且可以识别整个体积中的大根和细根材料。