Biology subjects

Stavness, I.

Publications and source records attributed to Stavness, I..

9 recordsLinked to original sources

bioRxiv2026

Quantifying Crop Disease Trait Dynamics through Longitudinal Imaging and Temporal Analytics

Reliable and objective phenotyping is essential for plant breeding programs to characterize genetic variation and accelerate crop improvement. Conventional disease assessment relies on expert visual scoring, which is labor-intensive, subjective, and prone to inter- and intra-rater variability. Although image-based phenotyping methods have been proposed, many require manual intervention, specialized imaging setups, or single time-point measurements, limiting their ability to capture disease progression over time. Here, we present a pipeline for longitudinal plant disease phenotyping that quantifies wheat stripe rust and leaf rust progression from time-series images. The pipeline performs semi-automated leaf and automated pustule segmentation from images acquired in situ, enabling objective disease severity estimation with minimal user intervention and without requiring solid backgrounds or manual leaf manipulation or detachment. By extracting temporal traits, including disease severity trajectories and standardized area under the disease progress curve, the method provides a comprehensive characterization of disease development throughout infection. Association between automated and expert assessments was moderate for stripe rust (R2 = 0.58) and strong for leaf rust (R2 = 0.85), while expert inter-rater reliability was moderate for both diseases (ICC = 0.675 and 0.800, respectively). The proposed approach establishes a scalable and reproducible framework for longitudinal disease phenotyping in controlled environments, with broad applications in disease resistance screening and crop breeding.

bioinformatics↗

bioRxiv2025

The Global Wheat Full Semantic Organ Segmentation (GWFSS) dataset

Computer vision is increasingly used in farmers fields and agricultural experiments to quantify important traits. Imaging setups with a sub-millimetre ground sampling distance enable the detection and tracking of plant features, including size, shape, and colour. Although todays AI-driven foundation models segment almost any object in an image, they still fail for complex plant canopies. To improve model performance, the global wheat dataset consortium assembled a diverse set of images from experiments around the globe. After the head detection dataset (GWHD), the new dataset targets a full semantic segmentation (GWFSS) of wheat organs (leaves, stems and spikes) covering all developmental stages. Images were collected by 11 institutions using a wide range of imaging setups. Two datasets are provided: i) a set of 1096 diverse images in which all organs were labelled at the pixel level, and (ii) a dataset of 52,078 images without annotations available for additional training. The labelled set was used to train segmentation models based on DeepLabV3Plus and Segformer. Our Segformer model performed slightly better than DeepLabV3Plus with a mIOU for leaves and spikes of ca. 90%. However, the precision for stems with 54% was rather lower. The major advantages over published models are: i) the exclusion of weeds from the wheat canopy, ii) the detection of all wheat features including necrotic and senescent tissues and its separation from crop residues. This facilitates further development in classifying healthy vs. unhealthy tissue to address the increasing need for accurate quantification of senescence and diseases in wheat canopies.

plant biology↗

bioRxiv2023

GPFN: Prior-Data Fitted Networks for Genomic Prediction

Genomic Prediction (GP) methods predict the breeding value of unphenotyped individuals in order to select parental candidates in breeding populations. Among models for GP, classical linear models have remained consistently popular, while more complex nonlinear methods such as deep neural networks have shown comparable accuracy at best. In this work, we propose the Genomic Prior-Data Fitted Network (GPFN) as a new paradigm for GP. GPFNs perform amortized Bayesian inference by simulating hundreds of thousands or millions of plant or animal populations. This allows GPFNs to be deployed without requiring any training or tuning, providing predictions in a single inference pass. On three populations of plants across two different crop species, GPFNs perform significantly better than the linear baseline on 13 out of 16 traits. On a challenging betweenfamilies structured prediction task on a third crop species, the GPFN matches the performance of the linear baseline while outperforming it in one location. GPFNs represent a completely new direction for the field of genomic prediction, and have the potential to unlock levels of selection accuracy not possible with existing methods, especially in diverse populations.

bioinformatics↗

bioRxiv2023

The effect of bolus properties on muscle activation patterns and TMJ loading during unilateral chewing

Mastication is a vital human function and uses an intricate coordination of muscle activation to break down food. Collection of detailed muscle activation patterns is complex and commonly only masseter and anterior temporalis muscle activation are recorded. Chewing is the orofacial task with the highest muscle forces, potentially leading to high temporomandibular joint (TMJ) loading. Increased TMJ loading is often associated with the onset and progression of temporomandibular disorders (TMD). Hence, studying TMJ mechanical stress during mastication is a central task. Current TMD self-management guidelines suggest eating small and soft pieces of food, but patient safety concerns inhibit in vivo investigations of TMJ biomechanics. For this purpose, we have developed a state-of-the-art in silico model, combining rigid body bones, finite element TMJ discs and line actuator muscles. To solve the problems regarding muscle activation measurement, we used a forward dynamics tracking approach, optimizing muscle activations driven by mandibular motion. We include a total of 256 different combinations of food bolus size, stiffness and position in our study and report kinematics, muscle activation patterns and TMJ disc von Mises stress. Computed mandibular kinematics agree well with previous measurements. The computed muscle activation pattern stayed stable over all simulations, with changes to the magnitude relative to stiffness and size of the bolus. Our results agree with the clinical guidelines regarding bolus modifications as smaller and softer food boluses lead to less TMJ loading. The results help to strengthen the confidence in TMD self-management recommendations, potentially reducing pain levels of patients.

bioengineering↗

bioRxiv2022

Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns

Deep learning has shown potential in domains where large-scale annotated datasets are available. However, manual annotation is expensive, time-consuming, and tedious. Pixel-level annotations are particularly costly for semantic segmentation in images with dense irregular patterns of object instances, such as in plant images. In this work, we propose a method for developing high-performing deep learning models for semantic segmentation of wheat heads utilizing little manual annotation. We simulate a computationally-annotated dataset using a few annotated images, a short unannotated video clip of a wheat field, and several video clips from fields with no wheat. This dataset is then used to train a customized U-Net model for wheat head segmentation. Considering the distribution shift between the simulated and real data, we apply three domain adaptation steps to gradually bridge the domain gap. Only using two annotated images, we achieved a Dice score of 0.89 on the internal test set, i.e., images extracted from the wheat field video. The model trained using only two annotated images was evaluated on a diverse external dataset collected from 18 different domains across five countries and achieved a Dice score of 0.73. To further expose the model to images from different growth stages and environmental conditions, we incorporated two annotated images from each of the 18 domains and further fine-tuned the model. This resulted in improving the Dice score to 0.91. These promising results highlight the utility of the proposed approach in the absence of large-annotated datasets. Although the utility of the proposed method is shown on a wheat head dataset, it can be extended to other segmentation tasks with similar characteristics of irregularly repeating patterns of object instances.

plant biology↗

bioRxiv2022

Quantitative Evaluation of Nonlinear Methods for Population Structure Visualization & Inference

Population structure (also called genetic structure and population stratification) is the presence of a systematic difference in allele frequencies between sub-populations in a population as a result of non-random mating between individuals. It can be informative of genetic ancestry, and in the context of medical genetics it is an important confounding variable in genome wide association studies. Recently, many nonlinear dimensionality reduction techniques have been proposed for the population structure visualization task. However, an objective comparison of these techniques has so far been missing from the literature. In this paper, we discuss the previously proposed nonlinear techniques and some of their potential weaknesses. We then propose a novel quantitative evaluation methodology for comparing these nonlinear techniques, based on populations for which pedigree is either known a-priori through artificial selection or simulation. Based on this evaluation metric, we find graph-based algorithms such as t-SNE and UMAP to be superior to PCA, while neural network based methods fall behind.

bioinformatics↗

bioRxiv2021

Deep Neural Networks for Genomic Prediction Do Not Estimate Marker Effects

Genomic prediction is a promising technology for advancing both plant and animal breeding, with many different prediction models evaluated in the literature. It has been suggested that the ability of powerful nonlinear models such as deep neural networks to capture complex epistatic effects between markers offers advantages for genomic prediction. However, these methods tend not to outperform classical linear methods, leaving it an open question why this capacity to model nonlinear effects does not seem to result in better predictive capability. In this work, we propose the theory that, due to a principle called shortcut learning, deep neural networks tend to base their predictions on overall genetic relatedness, rather than on the effects of particular markers, such as epistatic effects. Using several datasets of crop plants (lentil, wheat, and Brassica carinata), we demonstrate the networks indifference to the values of the markers by showing that the same network, provided with only the locations of matches between markers for two individuals, is able to perform prediction to the same level of accuracy.

bioinformatics↗

bioRxiv2019

Simulated Plant Images Improve Maize Leaf Counting Accuracy

Automatically scoring plant traits using a combination of imaging and deep learning holds promise to accelerate data collection, scientific inquiry, and breeding progress. However, applications of this approach are currently held back by the availability of large and suitably annotated training datasets. Early training datasets targeted arabidopsis or tobacco. The morphology of these plants quite different from that of grass species like maize. Two sets of maize training data, one real-world and one synthetic were generated and annotated for late vegetative stage maize plants using leaf count as a model trait. Convolutional neural networks (CNNs) trained on entirely synthetic data provided predictive power for scoring leaf number in real-world images. This power was less than CNNs trained with equal numbers of real-world images, however, in some cases CNNs trained with larger numbers of synthetic images outperformed CNNs trained with smaller numbers of real-world images. When real-world training images were scarce, augmenting real-world training data with synthetic data provided improved prediction accuracy. Quantifying leaf number over time can provide insight into plant growth rates and stress responses, and can help to parameterize crop growth models. The approaches and annotated training data described here may help future efforts to develop accurate leaf counting algorithms for maize.

plant biology↗

bioRxiv2019

Latent Space Phenotyping: Automatic Image-Based Phenotyping for Treatment Studies

Association mapping studies have enabled researchers to identify candidate loci for many important environmental resistance factors, including agronomically relevant resistance traits in plants. However, traditional genome-by-environment studies such as these require a phenotyping pipeline which is capable of accurately and consistently measuring stress responses, typically in an automated high-throughput context using image processing. In this work, we present Latent Space Phenotyping (LSP), a novel phenotyping method which is able to automatically detect and quantify response to treatment directly from images. Using two synthetically generated image datasets, we first show that LSP is able to successfully recover the simulated QTL in both simple and complex synthetic imagery. We then demonstrate an example application of an interspecific cross of the model C4 grass Setaria. We propose LSP as an alternative to traditional image analysis methods for phenotyping, enabling association mapping studies without the need for engineering complex image processing pipelines.

plant biology↗