Biology subjects

Scharr, H.

Publications and source records attributed to Scharr, H..

5 recordsLinked to original sources

bioRxiv2025

Virtual World Coupling with Photosynthesis Evaluation for Synthetic Data Production

In this work, we couple the functional-structural plant model CPlantBox to the Unreal Engine by exploiting the implemented raytracing pipeline to evaluate light influx on the plant surface. There are many approaches for photosynthesis computation and light evaluation, though they typically are limited by versatility, compute speed, or operate on much coarser resolutions. This work specifically addresses the concern that data generation pipelines tend to be unresponsive and do not include model-based knowledge as part of the generation pipeline. Using established photosynthesis solvers, we model the interaction between the Unreal Engine and the FSPM to measure physical properties in the virtual world. This is successful if we are able to reproduce experimental results using an in silico model. As part of the pipeline, we generate a surface geometry and utilize material shaders that are designed to establish a baseline surface model for light interception and transmission, based on simple parameter sets that can be calibrated. Using a Selhausen field experiment as baseline, we reproduce the photosynthesis effectiveness of the plants in the 2016 winter wheat experiments. Our pipeline is deeply intertwined with data generation and has been proven to perform well at scale. In this work, we build on our previous work by showcasing both a simulation study of a light evaluation as well as quantifying how well our system performs on high-performance computing systems.

bioinformatics↗

bioRxiv2024

VRoot: An XR-Based Application for Manual Root System Architecture Reconstruction

This article describes an immersive extended reality reconstruction tool for root system architectures from 3D volumetric scans of soil columns. We have conducted a laboratory user study to assess the performance of new users with our software in comparison to classical and established desktop software. We utilize a functional-structural plant model to derive a synthetic root architecture that serves as objective quantification for the root system architecture reconstruction. Additionally, we have collected quantitative feedback on our software in the form of standardized questionnaires. This work provides an overview of the extended reality software and the advantage of using immersive techniques for 3D data extraction in plant science. Through our formal study, we further provide a quantification of manual root system reconstruction accuracy. We observe an increase in root system architecture reconstruction accuracy (F1) compared to state-of-the-art desktop software and a more robust extraction quality.

bioinformatics↗

bioRxiv2022

ObiWan-Microbi: OMERO-based integrated workflow for annotating microbes in the cloud

SummaryReliable deep learning segmentation for microfluidic live-cell imaging requires comprehensive ground truth data. ObiWan-Microbi is a microservice platform combining the strength of state-of-the-art technologies into a unique integrated workflow for data management and efficient ground truth generation for instance segmentation, empowering collaborative semi-automated image annotation in the cloud. Availability and ImplementationObiWan-Microbi is open-source and available under the MIT license at https://github.com/hip-satomi/ObiWan-Microbi, along documentation and usage examples. Contactk.noeh@fz-juelich.de Supplementary informationSupplementary data are available online.

bioinformatics↗

bioRxiv2022

microbeSEG: Accurate Cell Segmentation with OMERO Data Management

In biotechnology, cell growth is one of the most important properties for the characterization and optimization of microbial cultures. Novel live-cell imaging methods are leading to an ever better understanding of cell cultures and their development. The key to analyzing acquired data is accurate and automated cell segmentation at the single-cell level. Therefore, we present microbeSEG, a user-friendly Python-based cell segmentation tool with a graphical user interface and OMERO data management. microbeSEG utilizes a state-of-the-art deep learning-based segmentation method and can be used for instance segmentation of a wide range of cell morphologies and imaging techniques, e.g., phase contrast or fluorescence microscopy. The main focus of microbeSEG is a comprehensible, easy, efficient, and complete workflow from the creation of training data to the final application of the trained segmentation model. We demonstrate that accurate cell segmentation results can be obtained within 45 minutes of user time. Utilizing public segmentation datasets or pre-labeling further accelerates the microbeSEG workflow. This opens the door for accurate and efficient data analysis of microbial cultures.

bioinformatics↗

bioRxiv2017

ARIGAN: Synthetic Arabidopsis Plants using Generative Adversarial Network

In recent years, there has been an increasing interest in image-based plant phenotyping, applying state-of-the-art machine learning approaches to tackle challenging problems, such as leaf segmentation (a multi-instance problem) and counting. Most of these algorithms need labelled data to learn a model for the task at hand. Despite the recent release of a few plant phenotyping datasets, large annotated plant image datasets for the purpose of training deep learning algorithms are lacking. One common approach to alleviate the lack of training data is dataset augmentation. Herein, we propose an alternative solution to dataset augmentation for plant phenotyping, creating artificial images of plants using generative neural networks. We propose the Arabidopsis Rosette Image Generator (through) Adversarial Network: a deep convolutional network that is able to generate synthetic rosette-shaped plants, inspired by DC-GAN (a recent adversarial network model using convolutional layers). Specifically, we trained the network using A1, A2, and A4 of the CVPPP 2017 LCC dataset, containing Arabidopsis Thaliana plants. We show that our model is able to generate realistic 128 x 128 colour images of plants. We train our network conditioning on leaf count, such that it is possible to generate plants with a given number of leaves suitable, among others, for training regression based models. We propose a new Ax dataset of artificial plants images, obtained by our ARIGAN. We evaluate this new dataset using a state-of-the-art leaf counting algorithm, showing that the testing error is reduced when Ax is used as part of the training data.

plant biology↗