Complexity of leaf surface texture affects microbial colonization in temperate forest tree species
Schulze, Waltraud X.; Schulze, Ernst-Detlef ; Reiße, Susanne; Rischke, Roman; Bouriaud, Oliver; Büdel, Burkhard; Straub, Tatsiana; Pillai, Evelina; Tanunchai, Benjawan; Purahong, Witoon; Simm, Stefan; Noll, Matthias (2026)
Schulze, Waltraud X.; Schulze, Ernst-Detlef ; Reiße, Susanne; Rischke, Roman...
PLoS One 2026 (21), 5.
DOI: 10.1371/journal.pone.0349938
Open Access Peer Reviewed
Throughout their life cycle, tree leaves are subject to colonization and degradation by microorganisms, including fungi, bacteria, and algae. These relationships co-evolved with chemical properties, leaf shape, and surface structures. Here we developed (i) a novel quantitative trait describing leaf surface texture complexity based on variables extracted from scanning electron microscopic images, resulting in a quantitative score of surface texture complexity on a tree species level. This complexity score was then used (ii) to test functional hypotheses, quantifying the contribution of leaf surface texture complexity in context of growth habitat preferences and colonization patterns by fungi and bacteria. We show that (iii) leaf surface texture complexity correlated with anatomical features such as stomatal density and leaf orientation as well as with Ellenberg temperature habitat indicator. Increasing leaf surface texture complexity was negatively correlated with leaf-associated fungal and bacterial specialists. Moreover, leaves with higher leaf surface texture complexity values showed reduced richness of colonization with plant pathogens (broad-leaved species) or lichenization (conifers), suggesting protection effects. Our results highlight leaf surface texture complexity as a previously underappreciated trait that may be a key to understanding microbial diversity between tree species and interaction patterns with leaf-associated microbes. This opens promising avenues for future research on plant-microbe co-evolution, trait-based ecosystem modeling, and the potential use of surface traits in forest management and disease resistance strategies.
Range-Coder with fast Adaptation and Table-Based Decoding
Strutz, Tilo; Rischke, Roman (2026)
arXiv.
Open Access
Diversity of stomatal and cuticular structures affect microbial colonization and leaf functioning in temperate forest tree species.
SChulze, Waltraud, X.; Schulze, Ernst-Detlef ; Reiße,, Susanne; Rischke, Roman; Bouriaud, Oliver; Büdel, B; Pillai, E; Tanunchai, Benjawan; Purahong, Witoon; Simm, Stefan (2025)
SChulze, Waltraud, X.; Schulze, Ernst-Detlef ; Reiße,, Susanne; Rischke, Roman...
bioRxiv.
Open Access
Handreichung zur Lehre mit (mathematischen) Concept Maps
Pawlowsky, Raik; Rischke, Roman; Wick , Michael (2025)
Tagungsband MINT-Symposium 2025, 395-402.
Open Access Peer Reviewed
Federated vs local vs central deep learning of tooth segmentation on panoramic radiographs
Schneider, Lisa; Rischke, Roman; Krois, Joachim; Krasowski, Aleksander; Büttner, Martha; Mohammad-Rahimi, Hossein; Chaurasia, Akhilanand; Pereira, Nielsen S.; Lee, Jae-Hong; Uribe, Sergio E.; Shahab, Shahriar; Koca-Ünsal, Revan B.; Ünsal, Gürkan; Martinez-Beneyto, Yolanda; Brinz, Janet; Tryfonos, Olga; Schwendicke, Falk (2023)
Schneider, Lisa; Rischke, Roman; Krois, Joachim; Krasowski, Aleksander; Büttner, Martha...
Journal of Dental Research 2023/135, 104556.
DOI: 10.1016/j.jdent.2023.104556
Peer Reviewed
Objective
Federated Learning (FL) enables collaborative training of artificial intelligence (AI) models from multiple data sources without directly sharing data. Due to the large amount of sensitive data in dentistry, FL may be particularly relevant for oral and dental research and applications. This study, for the first time, employed FL for a dental task, automated tooth segmentation on panoramic radiographs.
Methods
We employed a dataset of 4,177 panoramic radiographs collected from nine different centers (n = 143 to n = 1881 per center) across the globe and used FL to train a machine learning model for tooth segmentation. FL performance was compared against Local Learning (LL), i.e., training models on isolated data from each center (assuming data sharing not to be an option). Further, the performance gap to Central Learning (CL), i.e., training on centrally pooled data (based on data sharing agreements) was quantified. Generalizability of models was evaluated on a pooled test dataset from all centers.
Results
For 8 out of 9 centers, FL outperformed LL with statistical significance (p<0.05); only the center providing the largest amount of data FL did not have such an advantage. For generalizability, FL outperformed LL across all centers. CL surpassed both FL and LL for performance and generalizability.
Conclusion
If data pooling (for CL) is not feasible, FL is shown to be a useful alternative to train performant and, more importantly, generalizable deep learning models in dentistry, where data protection barriers are high.
Clinical Significance
This study proves the validity and utility of FL in the field of dentistry, which encourages researchers to adopt this method to improve the generalizability of dental AI models and ease their transition to the clinical environment.
FedAUXfdp: Differentially private one-shot federated distillation
Hoech, Haley; Rischke, Roman; Müller, Karsten; Samek, Wojciech (2023)
Goebel, R., Yu, H., Faltings, B., Fan, L., Xiong, Z. (eds) Trustworthy Federated Learning. FL 2022. Lecture Notes in Computer Science. 13448, 100-114.
Peer Reviewed
CFD: Communication-efficient federated distillation via soft-label quantization and delta coding
Sattler, Felix; Marban, Arturo; Rischke, Roman; Samek, Wojciech (2022)
IEEE Transactions on Network Science and Engineering 9 (4), 2025-2038.
Open Access Peer Reviewed
Federated learning in dentistry: Chances and challenges
Rischke, Roman; Schneider, Lisa; Müller, Karsten; Samek, Wojciech; Schwendicke, Falk; Krois, Joachim (2022)
Rischke, Roman; Schneider, Lisa; Müller, Karsten; Samek, Wojciech; Schwendicke, Falk...
Journal of Dental Research 101 (11), 1269-1273.
Open Access Peer Reviewed
Auf dem Weg zu Energieeffizienter Künstlicher Intelligenz: Welche Energieeinsparpotentiale bieten KI-Anwendungen?
Babilon, Linda; Kratochwill, Lisa; Müller, Karsten; Rischke, Roman; Samek, Wojciech; Stabernack, Benno; Steinert, Fritjof (2022)
Babilon, Linda; Kratochwill, Lisa; Müller, Karsten; Rischke, Roman; Samek, Wojciech...
Deutsche-Energie-Agentur (Hrsg.).
Open Access
FedAUX: Leveraging unlabeled auxiliary data in federated learning
Sattler, Felix; Korjakow, Tim; Rischke, Roman; Samek, Wojciech (2021)
IEEE Transactions on Neural Networks and Learning Systems 34 (9), 5531-5543.
Open Access Peer Reviewed
Prof. Dr. Roman Rischke
Hochschule Coburg
Fakultät Angewandte Naturwissenschaften und Gesundheit (FNG)
Friedrich-Streib-Str. 2
96450 Coburg
T +49 9561 317 Roman.Rischke[at]hs-coburg.de
ORCID iD: 0000-0002-2657-2811