欧亚国际

摘要 

背景：植物根系的非侵入性3D成像和连续3D分割在基础植物研究和选择性育种中引起了人们的兴趣。目前，现有技术包括计算机断层扫描系统（CT）扫描和重建，然后是适当的3D分割过程。挑战：由于不均匀的土壤成分以及根系结构本身的高尺度变化，生成根系的精确3D分割变得很有挑战性。方法：（1）我们通过将深度卷积神经网络（DCNN）与弱监督学习范式相结合来应对这一挑战。此外，（2）我们应用了空间金字塔池（SPP）层来处理根的尺度方差。（3） 我们使用专门的子标记技术生成了一个经过微调的训练数据集。（4） 最后，为了产生快速和高质量的分割，我们提出了一种专门的迭代推理算法，该算法对网络的视场（FoV）进行局部调整。实验：我们将我们的分割结果与用于对木薯植物的一组根进行根分割的分析参考算法（RootForce）进行比较，并定性地表明，可以分割更多的根体素和根分支。结果：我们的研究结果表明，与经典的分析参考方法相比，所提出的DCNN方法与动态推理相结合，可以检测到更多的根结构，尤其是精细的根结构。结论：我们表明，所提出的DCNN方法的应用带来了更好、更鲁棒的根分割，尤其是对于非常小和细的根。

3D segmentation of plant root systems using spatial pyramid pooling and locally adaptive field-of-view inference

April 2023

Frontiers in Plant Science 14:1120189

DOI:10.3389/fpls.2023.1120189

Abstract 

Background: The non-invasive 3D-imaging and successive 3D-segmentation of plant root systems has gained interest within fundamental plant research and selectively breeding resilient crops. Currently the state of the art consists of computed tomography (CT) scans and reconstruction followed by an adequate 3D-segmentation process. Challenge: Generating an exact 3D-segmentation of the roots becomes challenging due to inhomogeneous soil composition, as well as high scale variance in the root structures themselves. Approach: (1) We address the challenge by combining deep convolutional neural networks (DCNNs) with a weakly supervised learning paradigm. Furthermore, (2) we apply a spatial pyramid pooling (SPP) layer to cope with the scale variance of roots. (3) We generate a fine-tuned training data set with a specialized sub-labeling technique. (4) Finally, to yield fast and high-quality segmentations, we propose a specialized iterative inference algorithm, which locally adapts the field of view (FoV) for the network. Experiments: We compare our segmentation results against an analytical reference algorithm for root segmentation (RootForce) on a set of roots from Cassava plants and show qualitatively that an increased amount of root voxels and root branches can be segmented. Results: Our findings show that with the proposed DCNN approach combined with the dynamic inference, much more, and especially fine, root structures can be detected than with a classical analytical reference method. Conclusion: We show that the application of the proposed DCNN approach leads to better and more robust root segmentation, especially for very small and thin roots.