10 August 2022 in New Phytologist
NONiels Alvin Faircloth Olsen
Niels Alvin Faircloth Olsen
+2
Summary: Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine‐learning background. We present RootPainter, an open‐source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate RootPainterby training models for root length extraction from chicory (Cichorium intybusL.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using RootPainterwith corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep‐learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.
8 February 2020 in Plant Methods
Background: Plant root research can provide a way to attain stress-tolerant crops that produce greater yield in a diverse array of conditions. Phenotyping roots in soil is often challenging due to the roots being difficult to access and the use of time consuming manual methods. Rhizotrons allow visual inspection of root growth through transparent surfaces. Agronomists currently manually label photographs of roots obtained from rhizotrons using a line-intersect method to obtain root length density and rooting depth measurements which are essential for their experiments. We investigate the effectiveness of an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture to enable such measurements. We design a data-set of 50 annotated chicory (Cichorium intybus L.) root images which we use to train, validate and test the system and compare against a baseline built using the Frangi vesselness filter. We obtain metrics using manual annotations and line-intersect counts. Results: Our results on the held out data show our proposed automated segmentation system to be a viable solution for detecting and quantifying roots. We evaluate our system using 867 images for which we have obtained line-intersect counts, attaining a Spearman rank correlation of 0.9748 and an $$r^2$$ of 0.9217. We also achieve an $$F_1$$ of 0.7 when comparing the automated segmentation to the manual annotations, with our automated segmentation system producing segmentations with higher quality than the manual annotations for large portions of the image. Conclusion: We have demonstrated the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method. The success of our approach is also a demonstration of the feasibility of deep learning in practice for small research groups needing to create their own custom labelled dataset from scratch.
21 April 2021 in Journal of Experimental Botany
The scale of root quantification in research is often limited by the time required for sampling, measurement, and processing samples. Recent developments in convolutional neural networks (CNNs) have made faster and more accurate plant image analysis possible, which may significantly reduce the time required for root measurement, but challenges remain in making these methods accessible to researchers without an in-depth knowledge of machine learning. We analyzed root images acquired from three destructive root samplings using the RootPainter CNN software that features an interface for corrective annotation for easier use. Root scans with and without non-root debris were used to test if training a model (i.e. learning from labeled examples) can effectively exclude the debris by comparing the end results with measurements from clean images. Root images acquired from soil profile walls and the cross-section of soil cores were also used for training, and the derived measurements were compared with manual measurements. After 200 min of training on each dataset, significant relationships between manual measurements and RootPainter-derived data were noted for monolith (R2=0.99), profile wall (R2=0.76), and core-break (R2=0.57). The rooting density derived from images with debris was not significantly different from that derived from clean images after processing with RootPainter. Rooting density was also successfully calculated from both profile wall and soil core images, and in each case the gradient of root density with depth was not significantly different from manual counts. Differences in root-length density (RLD) between crops with contrasting root systems were captured using automatic segmentation at soil profiles with high RLD (1–5 cm cm–3) as well with low RLD (0.1–0.3 cm cm–3). Our results demonstrate that the proposed approach using CNN can lead to substantial reductions in root sample processing workloads, increasing the potential scale of future root investigations.
6 November 2023 in Plant Methods
Background: Manual analysis of (mini-)rhizotron (MR) images is tedious. Several methods have been proposed for semantic root segmentation based on homogeneous, single-source MR datasets. Recent advances in deep learning (DL) have enabled automated feature extraction, but comparisons of segmentation accuracy, false positives and transferability are virtually lacking. Here we compare six state-of-the-art methods and propose two improved DL models for semantic root segmentation using a large MR dataset with and without augmented data. We determine the performance of the methods on a homogeneous maize dataset, and a mixed dataset of > 8 species (mixtures), 6 soil types and 4 imaging systems. The generalisation potential of the derived DL models is determined on a distinct, unseen dataset. Results: The best performance was achieved by the U-Net models; the more complex the encoder the better the accuracy and generalisation of the model. The heterogeneous mixed MR dataset was a particularly challenging for the non-U-Net techniques. Data augmentation enhanced model performance. We demonstrated the improved performance of deep meta-architectures and feature extractors, and a reduction in the number of false positives. Conclusions: Although correction factors are still required to match human labelled root lengths, neural network architectures greatly reduce the time required to compute the root length. The more complex architectures illustrate how future improvements in root segmentation within MR images can be achieved, particularly reaching higher segmentation accuracies and model generalisation when analysing real-world datasets with artefacts—limiting the need for model retraining.
15 November 2021 in Medical Physics
CTCynthia Terrones‐Campos
+2