Search

Composite materials have many applications and are used in buildings, bridges, and vehicles. We wish to understand how damage propagates in these materials. Fiber breaks form within composite materials when tensile loads are applied to them. Segmentations of these fiber breaks are often needed to study the damage propagation within the material, but such segmentations can be hard to obtain in some materials. In this study, we utilize interactive machine learning to create a pipeline for fiber break segmentation in synchrotron radiation computed tomography images. This method does not provide a single model for fiber break segmentation, but a framework that can be used to obtain new models in new scenarios. We use the open-source IML software RootPainter3D [Smith et al., 2021] and adapt it for composite materials. We propose to diminish the cold start problem by including preliminary segmentations and present an algorithm to obtain preliminary segmentations of fiber breaks. Our method was successful and allowed us to obtain fiber break segmentations with a Dice score of up to 0.95 during the interactive annotation procedure. We perform user tests of the pipeline and get a usability SUS score of 0.85. Current models fail to predict fiber break development accurately. We study the hypothesis that the microstructure of the material influences the development, by using the SRCT in-situ images and the labels obtained with IML to predict fiber breakage at later time steps. We did not find conclusive evidence that microstructure influences fiber break formation.

Composite materials have many applications and are used in buildings, bridges, and vehicles. We wish to understand how damage propagates in these materials. Fiber breaks form within composite materials when tensile loads are applied to them. Segmentations of these fiber breaks are often needed to study the damage propagation within the material, but such segmentations can be hard to obtain in some materials. In this study, we utilize interactive machine learning to create a pipeline for fiber break segmentation in synchrotron radiation computed tomography images. This method does not provide a single model for fiber break segmentation, but a framework that can be used to obtain new models in new scenarios. We use the open-source IML software RootPainter3D [Smith et al., 2021] and adapt it for composite materials. We propose to diminish the cold start problem by including preliminary segmentations and present an algorithm to obtain preliminary segmentations of fiber breaks. Our method was successful and allowed us to obtain fiber break segmentations with a Dice score of up to 0.95 during the interactive annotation procedure. We perform user tests of the pipeline and get a usability SUS score of 0.85. Current models fail to predict fiber break development accurately. We study the hypothesis that the microstructure of the material influences the development, by using the SRCT in-situ images and the labels obtained with IML to predict fiber breakage at later time steps. We did not find conclusive evidence that microstructure influences fiber break formation.

Crop root segmentation models developed through deep learning have increased the throughput of in situ crop phenotyping studies. However, models trained to identify roots in one image dataset may not accurately identify roots in another dataset, especially when the new dataset contains known differences, called domain shifts. The objective of this study was to quantify how model performance changes when models are used to segment image datasets that contain domain shifts and evaluate approaches to reduce error associated with domain shifts. We collected maize root images at two growth stages (V7 and R2) in a field experiment and manually segmented images to measure total root length (TRL). We developed five segmentation models and evaluated each model's ability to handle a temporal (growth-stage) domain shift. For the V7 growth stage, a growth-stage-specific model trained only on images captured at the V7 growth stage was best suited for measuring TRL. At the R2 growth stage, combining images from both growth stages into a single dataset to train a model resulted in the most accurate TRL measurements. We applied two of the field models to images from a greenhouse experiment to evaluate how model performance changed when exposed to a cross-site domain shift. Field models were less accurate than models trained only on the greenhouse images even when crop growth stage was identical. Although models may perform well for one experiment, model error increases when applied to images from different experiments even when crop species, growth stage, and soil type are similar.

Crop root segmentation models developed through deep learning have increased the throughput of in situ crop phenotyping studies. However, models trained to identify roots in one image dataset may not accurately identify roots in another dataset, especially when the new dataset contains known differences, called domain shifts. The objective of this study was to quantify how model performance changes when models are used to segment image datasets that contain domain shifts and evaluate approaches to reduce error associated with domain shifts. We collected maize root images at two growth stages (V7 and R2) in a field experiment and manually segmented images to measure total root length (TRL). We developed five segmentation models and evaluated each model's ability to handle a temporal (growth-stage) domain shift. For the V7 growth stage, a growth-stage-specific model trained only on images captured at the V7 growth stage was best suited for measuring TRL. At the R2 growth stage, combining images from both growth stages into a single dataset to train a model resulted in the most accurate TRL measurements. We applied two of the field models to images from a greenhouse experiment to evaluate how model performance changed when exposed to a cross-site domain shift. Field models were less accurate than models trained only on the greenhouse images even when crop growth stage was identical. Although models may perform well for one experiment, model error increases when applied to images from different experiments even when crop species, growth stage, and soil type are similar.

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.

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., info:eu-repo/semantics/openAccess

Background and purpose: Daily plan adaptations could take the dose delivered in previous fractions into account. Due to high dose delivered per fraction, low number of fractions, steep dose gradients, and large interfractional organ deformations, this might be particularly important for liver SBRT. This study investigates inter-algorithm variation of interfractional dose accumulation for MR-guided liver SBRT. Materials and methods: We assessed 27 consecutive MR-guided liver SBRT treatments of 67.5 Gy in three (n = 15) or 50 Gy in five fractions (n = 12), both prescribed to the GTV. We calculated fraction doses on daily patient anatomy, warped these doses to the simulation MRI using seven different algorithms, and accumulated the warped doses. Thus, we obtained differences in planned doses and warped or accumulated doses for each algorithm. This enabled us to calculate the inter-algorithm variations in warped doses per fraction and in accumulated doses per treatment course. Results: The four intensity-based algorithms were more consistent with planned PTV dose than affine or contour-based algorithms. The mean (range) variation of the dose difference for PTV D95% due to dose warping by these intensity-based algorithms was 10.4 percentage points (0.3 to 43.7) between fractions and 8.6 (0.3 to 24.9) between accumulated treatment doses. As seen by these ranges, the variation was very dependent on the patient and the fraction being analyzed. Nevertheless, no correlations between patient or plan characteristics on the one hand and inter-algorithm dose warping variation on the other hand was found. Conclusion: Inter-algorithm dose accumulation variation is highly patient- and fraction-dependent for MR-guided liver SBRT. We advise against trusting a single algorithm for dose accumulation in liver SBRT.

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.

Background and purpose: Daily plan adaptations could take the dose delivered in previous fractions into account. Due to high dose delivered per fraction, low number of fractions, steep dose gradients, and large interfractional organ deformations, this might be particularly important for liver SBRT. This study investigates inter-algorithm variation of interfractional dose accumulation for MR-guided liver SBRT. Materials and methods: We assessed 27 consecutive MR-guided liver SBRT treatments of 67.5 Gy in three (n = 15) or 50 Gy in five fractions (n = 12), both prescribed to the GTV. We calculated fraction doses on daily patient anatomy, warped these doses to the simulation MRI using seven different algorithms, and accumulated the warped doses. Thus, we obtained differences in planned doses and warped or accumulated doses for each algorithm. This enabled us to calculate the inter-algorithm variations in warped doses per fraction and in accumulated doses per treatment course. Results: The four intensity-based algorithms were more consistent with planned PTV dose than affine or contour-based algorithms. The mean (range) variation of the dose difference for PTV D95% due to dose warping by these intensity-based algorithms was 10.4 percentage points (0.3 to 43.7) between fractions and 8.6 (0.3 to 24.9) between accumulated treatment doses. As seen by these ranges, the variation was very dependent on the patient and the fraction being analyzed. Nevertheless, no correlations between patient or plan characteristics on the one hand and inter-algorithm dose warping variation on the other hand was found. Conclusion: Inter-algorithm dose accumulation variation is highly patient- and fraction-dependent for MR-guided liver SBRT. We advise against trusting a single algorithm for dose accumulation in liver SBRT.

Increased organ at risk segmentation accuracy is required to reduce cost and complications for patients receiving radiotherapy treatment. Some deep learning methods for the segmentation of organs at risk use a two stage process where a localisation network first crops an image to the relevant region and then a locally specialised network segments the cropped organ of interest. We investigate the accuracy improvements brought about by such a localisation stage by comparing to a single-stage baseline network trained on full resolution images. We find that localisation approaches can improve both training time and stability and a two stage process involving both a localisation and organ segmentation network provides a significant increase in segmentation accuracy for the spleen, pancreas and heart from the Medical Segmentation Decathlon dataset. We also observe increased benefits of localisation for smaller organs. Source code that recreates the main results is available at \href{https://github.com/Abe404/localise_to_segment}{this https URL}.

Deep learning segmentation has been found to be effective and accurate for a variety of tasks including auto-contouring for radiotherapy and root phenotyping for agricultural and plant physiological research. Prior work has shown that existing models may not generalise well to new datasets, resulting in an unmet need for a method allowing clinical personnel and biological research labs to conveniently train their own models for new segmentation tasks. We aimed to investigate the effectiveness of Interactive Machine Learning (IML) for the rapid training of models for use in both plant science and radiotherapy. IML puts the human-in-the-loop in the model training process, allowing them to directly observe and influence the characteristics of the model whilst annotating, yet there is little research investigating the potential of IML for deep learning segmentation model training. We implemented and investigated various corrective-annotation approaches for multiple segmentation tasks and found that IML via corrective-annotation provides a way to rapidly train fully-automatic models for diverse datasets in plant image segmentation in under two hours of interactive training. In the field of radiotherapy, we found the IML process can be directly utilised for task completion, with the model and humans collaborating whilst the model learns from human feedback. The auto-contouring model was found to continuously provide improvements in contouring time for a heart contouring task, eventually out-performing the existing clinical delineation software. We also quantified agreement of the generated heart contours in terms of radiation dose, finding that for the vast majority of automatic contours there is little deviation between the model predicted and human corrected contours, yet in some rare cases there can be large differences with potentially catastrophic consequences, highlighting the need for continuous monitoring and guidance from a human observer, an intrinsic pr

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.

Locoregional recurrences (LRR) are still a frequent site of treatment failure for head and neck squamous cell carcinoma (HNSCC) patients. Identification of high risk subvolumes based on pretreatment imaging is key to biologically targeted radiation therapy. We investigated the extent to which a Convolutional neural network (CNN) is able to predict LRR volumes based on pre-treatment 18F-fluorodeoxyglucose positron emission tomography (FDG-PET)/computed tomography (CT) scans in HNSCC patients and thus the potential to identify biological high risk volumes using CNNs. For 37 patients who had undergone primary radiotherapy for oropharyngeal squamous cell carcinoma, five oncologists contoured the relapse volumes on recurrence CT scans. Datasets of pre-treatment FDG-PET/CT, gross tumour volume (GTV) and contoured relapse for each of the patients were randomly divided into training (n=23), validation (n=7) and test (n=7) datasets. We compared a CNN trained from scratch, a pre-trained CNN, a SUVmax threshold approach, and using the GTV directly. The SUVmax threshold method included 5 out of the 7 relapse origin points within a volume of median 4.6 cubic centimetres (cc). Both the GTV contour and best CNN segmentations included the relapse origin 6 out of 7 times with median volumes of 28 and 18 cc respectively. The CNN included the same or greater number of relapse volume POs, with significantly smaller relapse volumes. Our novel findings indicate that CNNs may predict LRR, yet further work on dataset development is required to attain clinically useful prediction accuracy.

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 RootPainter by training models for root length extraction from chicory (Cichorium intybus L.) 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 RootPainter with 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.

Purpose: Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. Methods: We implement an open-source interactive-machine-learning software application that facilitates corrective-annotation for deep-learning generated contours on X-ray CT images. A trained-physician contoured 933 hearts using our software by delineating the first image, starting model training, and then correcting the model predictions for all subsequent images. These corrections were added into the training data, which was used for continuously training the assisting model. From the 933 hearts, the same physician also contoured the first 10 and last 10 in Eclipse (Varian) to enable comparison in terms of accuracy and duration. Results: We find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods. After 923 images had been delineated, hearts took 2 min and 2 s to delineate on average, which includes time to evaluate the initial model prediction and assign the needed corrections, compared to 7 min and 1 s when delineating manually. Conclusions: Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows.

Aims: Perennial crops with more extensive and deep root systems could access deep stored water and build resilience to water shortage. In the context of human nutrition, perennial grain crops are very interesting. However, it is still questionable whether they are effective in using subsoil water. We compared intermediate wheatgrass (Kernza®) Thinopyrum intermedium, a perennial grain crop, to alfalfa Medicago sativa, a forage crop, for subsoil root growth and water uptake. Alfalfa was chosen because of its deep root system and agronomical interest as a companion crop. Methods: Using TDR sensors, deuterium tracer labelling, minirhizotrons and the Hydrus-1D model we characterised the root distribution and water uptake patterns of these two perennial crops during two cropping seasons under field conditions down to 2.5 m soil depth. Results: Both crops grew roots down to 2.0 m depth that were active in water uptake but alfalfa was deeper rooted than intermediate wheatgrass. All experimental methods concluded that alfalfa used more water from below 1.0 m depth than intermediate wheatgrass. However, simulations predicted that intermediate wheatgrass used more than 20 mm of water after anthesis from below 1 m soil depth. Simulations confirmed the advantage of deep roots in accessing deep soil water under drought. Conclusions: In regions with high groundwater recharge, growing deep-rooted perennial crops have great potential to exploit deep soil water that is often left unused. However, the road to a profitable perennial grain crop is still long and breeding intermediate wheatgrass (Kernza®) cultivars for increased root growth at depth seems to be a worthy investment for the development of more drought tolerant cultivars.

Background and purpose: MR-guided radiotherapy (MRgRT) allows real-time beam-gating to compensate for intra-fractional target position variations. This study investigates the dosimetric impact of beam-gating and the impact of PTV margin on prostate coverage for prostate cancer patients treated with online-adaptive MRgRT. Materials and methods: 20 consecutive prostate cancer patients were treated with online-adaptive MRgRT SBRT with 36.25 Gy in 5 fractions (PTV D95% ≥ 95% (N=5) and PTV D95% ≥ 100% (N=15)). Sagittal 2D cine MRIs were used for gating on the prostate with a 3 mm expansion as the gating window. We computed motion-compensated dose distributions for (i) all prostate positions during treatment (simulating non-gated treatments) and (ii) for prostate positions within the gating window (gated treatments). To evaluate the impact of PTV margin on prostate coverage, we simulated coverage with smaller margins than clinically applied both for gated and non-gated treatments. Motion-compensated fraction doses were accumulated and dose metrics were compared. Results: We found a negligible dosimetric impact of beam-gating on prostate coverage (median of 0.00 Gy for both D95% and Dmean). For 18/20 patients, prostate coverage (D95%≥100%) would have been ensured with a prostate-to-PTV margin of 3 mm, even without gating. The same was true for all but one fraction. Conclusion: Beam-gating has negligible dosimetric impact in online-adaptive MRgRT of prostate cancer. Accounting for motion, the clinically used prostate-to-PTV margin could potentially be reduced from 5 mm to 3 mm for 18/20 patients.

The growing demand for food and feed crops in the world because of growing population and more extreme weather events requires high-yielding and resilient crops. Many agriculturally important traits are polygenic, controlled by multiple regulatory layers, and with a strong interaction with the environment. In this study, 120 F2 families of perennial ryegrass (Lolium perenne L.) were grown across a water gradient in a semifield facility with subsoil irrigation. Genomic (single-nucleotide polymorphism [SNP]), transcriptomic (gene expression [GE]), and DNA methylomic (MET) data were integrated with feed quality trait data collected from control and drought sections in the semifield facility, providing a treatment effect. Deep root length (DRL) below 110 cm was assessed with convolutional neural network image analysis. Bayesian prediction models were used to partition phenotypic variance into its components and evaluated the proportion of phenotypic variance in all traits captured by different regulatory layers (SNP, GE, and MET). The spatial effects and effects of SNP, GE, MET, the interaction between GE and MET (GE × MET) and GE × treatment (GEControl and GEDrought) interaction were investigated. Gene expression explained a substantial part of the genetic and spatial variance for all the investigated phenotypes, whereas MET explained residual variance not accounted for by SNPs or GE. For DRL, MET also contributed to explaining spatial variance. The study provides a statistically elegant analytical paradigm that integrates genomic, transcriptomic, and MET information to understand the regulatory mechanisms of polygenic effects for complex traits.

Soil biopore genesis is a dynamic and context-dependent process. Yet integrative investigations of biopore genesis under varying soil type, tillage and vegetation history are rare. Recent advances in Machine Learning (ML) made faster and more accurate image analysis possible. We validated a model trained on Convolutional Neural Network (CNN) using a multisite dataset from varying soil types (Luvisol, Cambisol and Kandosol), tillage (deep ploughing and without deep ploughing) and vegetation history (taprooted and fibrous-rooted crops) to automatically predict biopore formation. The model trained on the multisite dataset outperformed individually trained single-site models, especially when the dataset contained images with noise and/or fewer biopores. Our model successfully replicated previously established treatment effects but provided new insights at more detailed scales and for different pore-size classes. These insights demonstrated that effects of deep ploughing on soil biopores can persist for more than 50 years and are more pronounced on the Luvisol rather than the Cambisol soil type. The effects of perennial fodder crops with high biopore generating capacity were also shown to persist for at least a decade. re-growing the same fodder crops or a mixture with grass had no further impact on biopore density but generated a shift in pore-size classes from large to smaller biopores. We suspect this is likely to have resulted from three possible scenarios; (1) newly created fine pores (1–4 mm); (2) blockage of large-sized pores by earthworm faeces; (3) decrease in pore diameter. In summary, by using a single robust model trained on the multisite dataset, we were able to generate new insights on pore-size distribution as affected by site, vegetation, and deep ploughing. We have demonstrated that Deep Learning-based image analysis can provide easier biopore quantification and can generate models that provide novel insights across different research settings consist

The deformation and damage development of nano-engineered composites have not yet been investigated in 3D, although it can provide a deeper insight into their damage behavior. To fill this gap, we perform a tensile test on a nano-engineered composite with in-situ X-ray micro-Computed Tomography (micro-CT). The composite is made from woven alumina fibers with grafted carbon nanotubes (CNTs) and epoxy. More diffuse damage seems to exist for the materials with CNTs compared to the baseline material. However, at such resolution where individual fibers are vaguely visible, grayscale thresholding does not accurately characterize the matrix cracks due to their small opening and low contrast with the material itself. Thus, we employ a deep-learning tool, called RootPainter, for segmentation of cracks with small opening in relation to the voxel size, in the 3D images. The results show that RootPainter can reliably identify these small cracks. In addition to the investigation of the mechanical performance of the nano-engineered composite, this study provides a novel and reliable method for the characterization of micro-cracks in in-situ tomograms of these composites.

Soil biopore genesis is a dynamic and context-dependent process. Yet integrative investigations of biopore genesis under varying soil type, tillage and vegetation history are rare. Recent advances in Machine Learning (ML) made faster and more accurate image analysis possible. We validated a model trained on Convolutional Neural Network (CNN) using a multisite dataset from varying soil types (Luvisol, Cambisol and Kandosol), tillage (deep ploughing and without deep ploughing) and vegetation history (taprooted and fibrous-rooted crops) to automatically predict biopore formation. The model trained on the multisite dataset outperformed individually trained single-site models, especially when the dataset contained images with noise and/or fewer biopores. Our model successfully replicated previously established treatment effects but provided new insights at more detailed scales and for different pore-size classes. These insights demonstrated that effects of deep ploughing on soil biopores can persist for more than 50 years and are more pronounced on the Luvisol rather than the Cambisol soil type. The effects of perennial fodder crops with high biopore generating capacity were also shown to persist for at least a decade. re-growing the same fodder crops or a mixture with grass had no further impact on biopore density but generated a shift in pore-size classes from large to smaller biopores. We suspect this is likely to have resulted from three possible scenarios; (1) newly created fine pores (1–4 mm); (2) blockage of large-sized pores by earthworm faeces; (3) decrease in pore diameter. In summary, by using a single robust model trained on the multisite dataset, we were able to generate new insights on pore-size distribution as affected by site, vegetation, and deep ploughing. We have demonstrated that Deep Learning-based image analysis can provide easier biopore quantification and can generate models that provide novel insights across different research settings consist

Purpose: Measuring continuous root growth with less time- and resource-intensive methods is challenging for plant ecologists. We propose an approach where photos of fine root growth were taken with smartphones and analyzed by the deep learning method-based program RootPainter. Methods: Picea abies saplings were grown in transparent boxes in growth chambers at either moderate (mRH) or elevated air humidity (eRH) and in nitrate (NO3−) or ammonium (NH4+) dominated soil. To evaluate the partitioning of roots, we analyzed both fine root projection area (PA) of total and young white roots. We aimed to measure the ability of RootPainter to pick up on variation in fine root growth caused by changes in air humidity and soil nitrogen source. Results: Trees growing at mRH-NH4+ had the highest total PA, 9.4 ± 1.9 cm2, while the lowest was in trees growing at eRH-NO3−, 3.9 ± 0.6 cm2. The young root PA was highest at the beginning of the experiment and was affected by the initial soil nitrogen source. The older (brown) root PA increased over time. At mRH, the relative growth peak of root browning followed the peak of white roots, while at eRH, the peaks coincided. We found strong agreement between the automatic segmentation and manual annotation (F-measure = 0.88); the error measures showed no treatment-specific bias. Conclusions: We conclude that the increased air humidity reduced the fine root growth and diminished sequential developmental peaks. The combination of smartphone images and RootPainter gives reliable results and is easy to use in future plant growth manipulation experiments.

Deep rooting winter wheat genotypes can reduce nitrate leaching losses and increase N uptake. We aimed to investigate which deep root traits are correlated to deep N uptake and to estimate genetic variation in root traits and deep 15N tracer uptake. In 2 years, winter wheat genotypes were grown in RadiMax, a semifield root-screening facility. Minirhizotron root imaging was performed three times during the main growing season. At anthesis, 15N was injected via subsurface drip irrigation at 1.8 m depth. Mature ears from above the injection area were analysed for 15N content. From minirhizotron image-based root length data, 82 traits were constructed, describing root depth, density, distribution and growth aspects. Their ability to predict 15N uptake was analysed with the least absolute shrinkage and selection operator (LASSO) regression. Root traits predicted 24% and 14% of tracer uptake variation in 2 years. Both root traits and genotype showed significant effects on tracer uptake. In 2018, genotype and the three LASSO-selected root traits predicted 41% of the variation in tracer uptake, in 2019 genotype and one root trait predicted 48%. In both years, one root trait significantly mediated the genotype effect on tracer uptake. Deep root traits from minirhizotron images can predict deep N uptake, indicating the potential to breed deep-N-uptake-genotypes.

Background and purpose: MR-guided radiotherapy (MRgRT) allows real-time beam-gating to compensate for intra-fractional target position variations. This study investigates the dosimetric impact of beam-gating and the impact of PTV margin on prostate coverage for prostate cancer patients treated with online-adaptive MRgRT. Materials and methods: 20 consecutive prostate cancer patients were treated with online-adaptive MRgRT SBRT with 36.25 Gy in 5 fractions (PTV D95% ≥ 95% (N = 5) and PTV D95% ≥ 100% (N = 15)). Sagittal 2D cine MRIs were used for gating on the prostate with a 3 mm expansion as the gating window. We computed motion-compensated dose distributions for (i) all prostate positions during treatment (simulating non-gated treatments) and (ii) for prostate positions within the gating window (gated treatments). To evaluate the impact of PTV margin on prostate coverage, we simulated coverage with smaller margins than clinically applied both for gated and non-gated treatments. Motion-compensated fraction doses were accumulated and dose metrics were compared. Results: We found a negligible dosimetric impact of beam-gating on prostate coverage (median of 0.00 Gy for both D95% and Dmean). For 18/20 patients, prostate coverage (D95% ≥ 100%) would have been ensured with a prostate-to-PTV margin of 3 mm, even without gating. The same was true for all but one fraction. Conclusion: Beam-gating has negligible dosimetric impact in online-adaptive MRgRT of prostate cancer. Accounting for motion, the clinically used prostate-to-PTV margin could potentially be reduced from 5 mm to 3 mm for 18/20 patients.

Background and purpose: MR-guided radiotherapy (MRgRT) allows real-time beam-gating to compensate for intra-fractional target position variations. This study investigates the dosimetric impact of beam-gating and the impact of PTV margin on prostate coverage for prostate cancer patients treated with online-adaptive MRgRT. Materials and methods: 20 consecutive prostate cancer patients were treated with online-adaptive MRgRT SBRT with 36.25 Gy in 5 fractions (PTV D95% ≥ 95% (N = 5) and PTV D95% ≥ 100% (N = 15)). Sagittal 2D cine MRIs were used for gating on the prostate with a 3 mm expansion as the gating window. We computed motion-compensated dose distributions for (i) all prostate positions during treatment (simulating non-gated treatments) and (ii) for prostate positions within the gating window (gated treatments). To evaluate the impact of PTV margin on prostate coverage, we simulated coverage with smaller margins than clinically applied both for gated and non-gated treatments. Motion-compensated fraction doses were accumulated and dose metrics were compared. Results: We found a negligible dosimetric impact of beam-gating on prostate coverage (median of 0.00 Gy for both D95% and Dmean). For 18/20 patients, prostate coverage (D95% ≥ 100%) would have been ensured with a prostate-to-PTV margin of 3 mm, even without gating. The same was true for all but one fraction. Conclusion: Beam-gating has negligible dosimetric impact in online-adaptive MRgRT of prostate cancer. Accounting for motion, the clinically used prostate-to-PTV margin could potentially be reduced from 5 mm to 3 mm for 18/20 patients.

Purpose: Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. Methods: We implement an open-source interactive-machine-learning software application that facilitates corrective-annotation for deep-learning generated contours on X-ray CT images. A trained-physician contoured 933 hearts using our software by delineating the first image, starting model training, and then correcting the model predictions for all subsequent images. These corrections were added into the training data, which was used for continuously training the assisting model. From the 933 hearts, the same physician also contoured the first 10 and last 10 in Eclipse (Varian) to enable comparison in terms of accuracy and duration. Results: We find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods. After 923 images had been delineated, hearts took 2 min and 2 s to delineate on average, which includes time to evaluate the initial model prediction and assign the needed corrections, compared to 7 min and 1 s when delineating manually. Conclusions: Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows.

Aims: Perennial crops with more extensive and deep root systems could access deep stored water and build resilience to water shortage. In the context of human nutrition, perennial grain crops are very interesting. However, it is still questionable whether they are effective in using subsoil water. We compared intermediate wheatgrass (Kernza®) Thinopyrum intermedium, a perennial grain crop, to alfalfa Medicago sativa, a forage crop, for subsoil root growth and water uptake. Alfalfa was chosen because of its deep root system and agronomical interest as a companion crop. Methods: Using TDR sensors, deuterium tracer labelling, minirhizotrons and the Hydrus-1D model we characterised the root distribution and water uptake patterns of these two perennial crops during two cropping seasons under field conditions down to 2.5 m soil depth. Results: Both crops grew roots down to 2.0 m depth that were active in water uptake but alfalfa was deeper rooted than intermediate wheatgrass. All experimental methods concluded that alfalfa used more water from below 1.0 m depth than intermediate wheatgrass. However, simulations predicted that intermediate wheatgrass used more than 20 mm of water after anthesis from below 1 m soil depth. Simulations confirmed the advantage of deep roots in accessing deep soil water under drought. Conclusions: In regions with high groundwater recharge, growing deep-rooted perennial crops have great potential to exploit deep soil water that is often left unused. However, the road to a profitable perennial grain crop is still long and breeding intermediate wheatgrass (Kernza®) cultivars for increased root growth at depth seems to be a worthy investment for the development of more drought tolerant cultivars.

Background and purpose: MR-guided radiotherapy (MRgRT) allows real-time beam-gating to compensate for intra-fractional target position variations. This study investigates the dosimetric impact of beam-gating and the impact of PTV margin on prostate coverage for prostate cancer patients treated with online-adaptive MRgRT. Materials and methods: 20 consecutive prostate cancer patients were treated with online-adaptive MRgRT SBRT with 36.25 Gy in 5 fractions (PTV D95% ≥ 95% (N = 5) and PTV D95% ≥ 100% (N = 15)). Sagittal 2D cine MRIs were used for gating on the prostate with a 3 mm expansion as the gating window. We computed motion-compensated dose distributions for (i) all prostate positions during treatment (simulating non-gated treatments) and (ii) for prostate positions within the gating window (gated treatments). To evaluate the impact of PTV margin on prostate coverage, we simulated coverage with smaller margins than clinically applied both for gated and non-gated treatments. Motion-compensated fraction doses were accumulated and dose metrics were compared. Results: We found a negligible dosimetric impact of beam-gating on prostate coverage (median of 0.00 Gy for both D95% and Dmean). For 18/20 patients, prostate coverage (D95% ≥ 100%) would have been ensured with a prostate-to-PTV margin of 3 mm, even without gating. The same was true for all but one fraction. Conclusion: Beam-gating has negligible dosimetric impact in online-adaptive MRgRT of prostate cancer. Accounting for motion, the clinically used prostate-to-PTV margin could potentially be reduced from 5 mm to 3 mm for 18/20 patients. Keywords: Adaptive radiotherapy; Beam-gating; Deformable image registration; Dose accumulation; MR-guided radiotherapy; Margin assessment; Motion-mitigation; Prostate cancer; Prostate motion; Radiotherapy.

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 (CNN) 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 minutes 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: cm cm-3) between crops with contrasting root systems were captured using automatic segmentation at soil profiles with high RLD (1 to 5 cm cm-3) as well as at low RLD (0.1 to 0.3 cm cm-3). Our results demonstrate that the proposed approach using CNN can lead to substantial reductions in root

Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. We compare the method to the Eclipse contouring software and find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods, with hearts that take 2 minutes and 2 seconds to delineate on average, after 923 images have been delineated, compared to 7 minutes and 1 seconds when delineating manually. Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows. Source code is available at \href{https://github.com/Abe404/RootPainter3D}{this HTTPS URL}.

Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

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.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

Demonstration of the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

Demonstration of the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

Demonstration of the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

Demonstration of the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semiautomatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.

Demonstration of the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method.