Biology subjects

Wuehrl, L.

Publications and source records attributed to Wuehrl, L..

4 recordsLinked to original sources

bioRxiv2026

Entomoscope 2.0 and ENIMAS 2.0: An Open-Source, AI-Integrated Platform for Rapid and Affordable Insect Digitization

The rapid decline of global biodiversity necessitates scalable and accessible tools for monitoring insect populations, yet the high cost and slow pace of specimen digitization remain significant bottlenecks. To address this challenge, we present the Entomoscope 2.0, an open-source platform that integrates a low-cost photomicroscope with an AI-integrated software suite, ENIMAS 2.0. The system combines optimized hardware with an end-to-end software module for digital specimen curation. This module comprises automated specimen cropping, background standardization, morphometric analysis using an Oriented Bounding Box (OBB) with a human-in-the-loop (HITL) supervision, and a flexible interface for rapid taxonomic screening using custom AI identification models. With a material cost of only 400 {euro}, the system offers a cost-effective alternative to expensive commercial solutions. We compare results from the Entomoscope 2.0 with a high-end commercial system (Keyence) using 54 insect specimens and demonstrate the efficiency of the proposed AI workflow. Entomoscope 2.0 completed the whole digitization process in an average of 54.6 seconds per specimen, representing a 2.28-fold increase in speed over the Keyence systems multi-step workflow (124.3 seconds). Crucially, all hardware specifications and construction manuals are freely available to support widespread adoption. By lowering financial barriers and accelerating research workflows, the Entomoscope 2.0 platform offers a practical solution to enable high-throughput digitization for researchers, educators, and citizen scientists.

bioengineering↗

bioRxiv2025

Automated Specimen Triage for Dark Taxa: Deep Learning Enables Orientation, Sex Identification, and Anatomical Segmentation from Robotic Imaging

Robotic specimen processing is transforming biodiversity discovery by replacing labor-intensive handling with scalable systems that can simultaneously generate high-quality specimen images. We demonstrate that these images can be leveraged by deep learning to efficiently extract key biological information and guide targeted specimen processing. Using a model dark taxon, the Phoridae (Diptera), the workflow performs three core tasks: sex identification, specimen orientation classification, and anatomical segmentation. Sex identification allows selective retention of diagnostically informative specimens, avoiding wasted effort on non-diagnostic individuals. Orientation classification enables specimens in the desired orientation to proceed immediately, while suboptimally oriented specimens can be repositioned for informative processing. Anatomical segmentation allows targeted processing of specimens displaying diagnostic characters or targeted analysis of specific anatomical regions in subsequent workflow steps. Comparative analysis of model architectures shows task-specific selection is crucial: a Convolutional Neural Network achieved an accuracy of 0.94 for orientation, a Vision Transformer achieved 0.88 for sex, and a U-Net precisely segmented nine anatomical regions with a mean IoU of 0.78. These results demonstrate that robotic imaging combined with deep learning provides a validated foundation for high-throughput, targeted specimen processing, maximising efficiency and utility for taxonomic and trait-based analyses, and supporting scalable, sustainable biodiversity workflows.

bioinformatics↗

bioRxiv2025

Deep Learning-Based Methods for Automated Estimation of Insect Length, Volume, and Biomass

We present InsectMorphoAI, an open-source, user-friendly software package that automates the measurement of insects from 2D images. The software addresses the need for high-throughput, non-invasive alternatives to laborious and often destructive manual measurement methods. InsectMorphoAI provides two analysis modes: a rapid, general-purpose method using oriented bounding boxes for linear length estimation across diverse taxa, and a high-precision, taxon-specific instance segmentation method for detailed curvilinear length, volume, and biomass estimation. We demonstrate the softwares accuracy, showing that the volume estimates from the segmentation module are strongly correlated with dry weight (R = 0.907), and the general length module achieves a mean absolute error corresponding to ~2.3% of the average specimen length. InsectMorphoAI is distributed with a graphical user interface and is freely available, with straightforward installation via a Docker container or a native Python environment. By streamlining data acquisition, InsectMorphoAI facilitates the integration of detailed trait data into large-scale ecological research, from biodiversity monitoring to functional trait analysis.

bioinformatics↗

bioRxiv2021

DiversityScanner: Robotic discovery of small invertebrates with machine learning methods

Invertebrate biodiversity remains poorly explored although it comprises much of the terrestrial animal biomass, more than 90% of the species-level diversity and supplies many ecosystem services. The main obstacle is specimen- and species-rich samples. Traditional sorting techniques require manual handling and are slow while molecular techniques based on metabarcoding struggle with obtaining reliable abundance information. Here we present a fully automated sorting robot, which detects each specimen, images and measures it before moving it from a mixed invertebrate sample to the well of a 96-well microplate in preparation for DNA barcoding. The images are then used by a newly trained convolutional neural network (CNN) to assign the specimens to 14 particularly common, usually family-level "classes" of insects in Malaise trap samples and an "other-class" (N=15). The average assignment precision for the classes is 91.4% (75-100%). In order to obtain biomass information, the specimen images are also used to measure specimen length and estimate body volume. We outline how the DiversityScanner robot can be a key component for tackling and monitoring invertebrate diversity. The robot generates large numbers of images that become training sets for CNNs once the images are labelled with identifications based on DNA barcodes. In addition, the robot allows for taxon-specific subsampling of large invertebrate samples by only removing the specimens that belong to one of the 14 classes. We conclude that a combination of automation, machine learning, and DNA barcoding has the potential to tackle invertebrate diversity at an unprecedented scale.

zoology↗