Profiling of pollen in honey using multispectral imaging flow cytometry.
16 affiliations
- 1Department Physiological Diversity, Helmholtz Centre for Environmental Research UFZ, Leipzig, Germany.
- 2German Centre for integrative Biodiversity Research iDiv Halle-Jena-Leipzig, Leipzig, Germany.
- 3Data-intensive Systems and Visualization Group (dAI.SY), Technische Universität Ilmenau, Ilmenau, Germany.
- 4Lower Saxony State Office for Consumer Protection and Food Safety LAVES - Institute of Apiculture, Celle, Germany.
- 5Institute for Bee Protection, Federal Research Centre for Cultivated Plants, Julius Kühn Institute (JKI), Braunschweig, Germany.
- 6Zoological Institute, Technische Universität Braunschweig, Braunschweig, Germany.
- 7University of Hohenheim, State Institute of Bee Research, Stuttgart, Germany.
- 8Department Community Ecology, Helmholtz Centre for Environmental Research UFZ, Leipzig, Germany.
- 9Thuenen Institute of Biodiversity, Braunschweig, Germany.
- 10Martin Luther University Halle-Wittenberg, Halle, Germany.
- 11Faculty of Biological Sciences, Friedrich Schiller University Jena, Jena, Germany.
- 12CICYTTP (CONICET-Prov. ER-UADER), Laboratorio Interdisciplinario de Biología y Genética Molecular, Instituto de Botánica del Nordeste (CONICET-UNNE), Corrientes, Argentina.
- 13Department Physiological Diversity, Helmholtz Centre for Environmental Research UFZ, Leipzig, Germany. [email protected].
- 14German Centre for integrative Biodiversity Research iDiv Halle-Jena-Leipzig, Leipzig, Germany. [email protected].
- 15Department Physiological Diversity, Helmholtz Centre for Environmental Research UFZ, Leipzig, Germany. [email protected].
- 16German Centre for integrative Biodiversity Research iDiv Halle-Jena-Leipzig, Leipzig, Germany. [email protected].
Abstract
Pollen identification from honey (melissopalynology) is of great economic and consumer relevance. Traditional microscopy is time-consuming and dependent on expert knowledge, thus limiting high-throughput analyses. We tested whether pollen images generated with Multispectral Imaging Flow Cytometry (MIFC) classified by machine learning (ML) (convolution neural networks (CNNs) and random forest (RF)) can serve as a fast and reproducible method for identifying pollen in honey. We examined how the classification of honey pollen is affected by images from different matrices (anther and honey samples), how results compare with traditional microscopic analysis and used a set of human-interpretable image features to better explain ML results. The study focused on the six common target pollen in honey Brassica, Castanea, Centaurea, Helianthus, Phacelia and Tilia type. A classifier trained with a combination of anther and honey brightfield and fluorescence images provided the best predictions for 13 monofloral and 10 polyfloral honeys. Yielding pollen identification results comparable to microscopy, three times more pollen can be evaluated, and a measurement time of a maximum of 10 min, the method demonstrates its high potential as a powerful screening tool in melissopalynology.
Related
- Nest Structure and Pollen Analysis of Honey Bee Apis koschevnikovi and Apis cerana (Hymenoptera: Apidae) from Belitung
- Integrated Assessment of Pollen Substitute Diets in Honey Bees Based on Transcriptional Responses, Immune-Derived Predicted Biological Age, and Survival.
- Assessing Botanical Authenticity of Honey Through DNA-Metabarcoding-Based Pollen Analysis: A Preliminary Study.
- Application of spectroscopic and multispectral imaging technologies on the assessment of ready-to-eat pineapple quality: A performance evaluation study of machine learning models generated from two commercial data analytics tools
- AltraFlowSOM: A Semi-Supervised Framework for Imaging Mass Cytometry Phenotyping
BibTeX
@article{walther2026profiling,
title = {{Profiling of pollen in honey using multispectral imaging flow cytometry.}},
author = {Franziska Walther and Martin Hofmann and Martina Janke and Silvio Erler and Elsa Friedrich and Manuel Treder and Demetra Rakosy and W Stanley Harpole and Patrick Mäder and Alicia Berdún and Thomas Hornick and Susanne Dunker},
journal = {NPJ science of food},
year = {2026},
month = oct,
doi = {10.1038/s41538-026-01188-6},
url = {https://europepmc.org/article/MED/42963353},
note = {CC BY},
}
RIS
TY - JOUR
TI - Profiling of pollen in honey using multispectral imaging flow cytometry.
AU - Franziska Walther
AU - Martin Hofmann
AU - Martina Janke
AU - Silvio Erler
AU - Elsa Friedrich
AU - Manuel Treder
AU - Demetra Rakosy
AU - W Stanley Harpole
AU - Patrick Mäder
AU - Alicia Berdún
AU - Thomas Hornick
AU - Susanne Dunker
PY - 2026
DA - 2026/10/30
JO - NPJ science of food
DO - 10.1038/s41538-026-01188-6
UR - https://europepmc.org/article/MED/42963353
AB - Pollen identification from honey (melissopalynology) is of great economic and consumer relevance. Traditional microscopy is time-consuming and dependent on expert knowledge, thus limiting high-throughput analyses. We tested whether pollen images generated with Multispectral Imaging Flow Cytometry (MIFC) classified by machine learning (ML) (convolution neural networks (CNNs) and random forest (RF)) can serve as a fast and reproducible method for identifying pollen in honey. We examined how the classification of honey pollen is affected by images from different matrices (anther and honey samples), how results compare with traditional microscopic analysis and used a set of human-interpretable image features to better explain ML results. The study focused on the six common target pollen in honey Brassica, Castanea, Centaurea, Helianthus, Phacelia and Tilia type. A classifier trained with a combination of anther and honey brightfield and fluorescence images provided the best predictions for 13 monofloral and 10 polyfloral honeys. Yielding pollen identification results comparable to microscopy, three times more pollen can be evaluated, and a measurement time of a maximum of 10 min, the method demonstrates its high potential as a powerful screening tool in melissopalynology.
SN - 2396-8370
ER -