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

Autor:	Alle J; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Development Center X-Ray Technology, Fürth, Germany., Gruber R; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Development Center X-Ray Technology, Fürth, Germany.; Friedrich-Alexander-Universität Erlangen-Nürnberg, Chair for Visual Computing, Erlangen, Germany., Wörlein N; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Development Center X-Ray Technology, Fürth, Germany., Uhlmann N; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Development Center X-Ray Technology, Fürth, Germany., Claußen J; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Development Center X-Ray Technology, Fürth, Germany., Wittenberg T; Friedrich-Alexander-Universität Erlangen-Nürnberg, Chair for Visual Computing, Erlangen, Germany.; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Smart Sensors and Electronics, Erlangen, Germany., Gerth S; Fraunhofer Institut für Integrierte Schaltungen (IIS), Fraunhofer Institute for Integrated Circuits Institut für Integrierte Schaltungen (IIS), Division Development Center X-Ray Technology, Fürth, Germany.
Jazyk:	angličtina
Zdroj:	Frontiers in plant science [Front Plant Sci] 2023 Apr 04; Vol. 14, pp. 1120189. Date of Electronic Publication: 2023 Apr 04 (Print Publication: 2023).
DOI:	10.3389/fpls.2023.1120189
Abstrakt:	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. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2023 Alle, Gruber, Wörlein, Uhlmann, Claußen, Wittenberg and Gerth.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu