Explainable AI model reveals informative mutational signatures for cancer-type classification
Wagner, Jonas; Oldenburg, Jan; Nath, Neetika; Simm, Stefan (2025)
Cancers (Basel) 17 (11), 1731.
Open Access Peer Reviewed
Background/Objectives: The prediction of cancer types is primarily reliant on driver genes and their specific mutations. The advancement in novel omics technologies has led to the acquisition of additional genetic data. When integrated with artificial intelligence models, there is considerable potential for this to enhance the accuracy of cancer diagnosis. As mutational signatures can provide insights into repair mechanism malfunctions, they also have the potential for more accurate cancer diagnosis. Methods: First, we compared unsupervised and supervised machine learning approaches to predict cancer types. We employed deep and artificial neural network architectures with an explainable component like layerwise relevance propagation to extract the most relevant features for the cancer-type prediction. Ten-fold cross-validation and an extensive grid search were used to optimize the neural network architecture using driver gene mutations, mutational signatures and topological mutation information as input. The PCAWG dataset was used as input to discriminate between 17 primary sites and 24 cancer types. Results: Overall, our approach showed that the most relevant mutation information to discriminate between cancer types is increased by >10% using the whole genome or intergenic and intronic genome regions instead of exome information. Furthermore, the most relevant features for most cancer types, except for two, are in the mutational signatures and not the topological mutation information. Conclusions: Informative mutational signatures outperformed the prediction of cancer types in comparison to driver gene mutations and added a new layer of diagnostic information. As the degree of information within the mutational signatures is not solely based on the frequency of occurrence, it is even possible to separate cancer types from the same primary site by the different relevant mutations. Furthermore, the comparison of informative mutational signatures allowed the cancer-type assignment of specific impaired repair mechanisms.
Does future climate and agricultural farming system affect the fungal plastisphere of different biodegradable plastics at the early stage of field degradation?
Tanunchai, Benjawan; Schädler , M.; Noll, Matthias (2025)
Environmental Science Europe 2025 (37), 23.
DOI: 10.1186/s12302-025-01051-7
Peer Reviewed
Das aktive Mikrobiom als ökotoxikologischer Indikator in Umweltproben
Reiß, Fabienne; Noll, Matthias (2025)
Biospektrum 2025 (31), 1-3.
DOI: DOI: 10.1007/s12268-025-2384-1
Peer Reviewed
Postoperative use of fitness trackers for continuous monitoring of vital signs: a survey of hospitalized patients
Helmer, Philipp; Hottenrott, Sebastian; Wienböker, Kathrin; Brugger, Jürgen; Stoppe, Christian; Schmid, Benedikt; Kranke, Peter; Meybohm, Patrick; Sammeth, Michael (2025)
Helmer, Philipp; Hottenrott, Sebastian; Wienböker, Kathrin; Brugger, Jürgen...
Journal of Clinical Monitoring and Computing, doi: 10.1007/s10877-025-01273-3.
Open Access Peer Reviewed
Brain pericytes and perivascular fibroblasts are stromal progenitors with dual functions in cerebrovascular regeneration after stroke
Bernier, Louis-Philippe; Hefendehl, Jasmin; Scott, R; Tung, Lin; Lewis, Coral-Ann; Soliman, Hesham; Simm, Stefan; Dissing-Olesen, Lasse; Hofmann, Jan; Guo, David; DeMeglio, Murphy; Rossi, Fabio; Underhill, T; MacVicar, Brian (2025)
Bernier, Louis-Philippe; Hefendehl, Jasmin; Scott, R; Tung, Lin; Lewis, Coral-Ann...
Nature Neuroscience 28 (3), 517–535.
DOI: 10.1038/s41593-025-01872-y
Open Access Peer Reviewed
Functional revascularization is key to stroke recovery and requires remodeling and regeneration of blood vessels around which is located the brain’s only stromal compartment. Stromal progenitor cells (SPCs) are critical for tissue regeneration following injury in many organs, yet their identity in the brain remains elusive. Here we show that the perivascular niche of brain SPCs includes pericytes, venular smooth muscle cells and perivascular fibroblasts that together help cerebral microvasculature regenerate following experimental stroke. Ischemic injury triggers amplification of pericytes and perivascular fibroblasts in the infarct region where they associate with endothelial cells inside a reactive astrocyte border. Fate-tracking of Hic1+ SPCs uncovered a transient functional and transcriptional phenotype of stroke-activated pericytes and perivascular fibroblasts. Both populations of these cells remained segregated, displaying distinct angiogenic and fibrogenic profiles. Therefore, pericytes and perivascular fibroblasts are distinct subpopulations of SPCs in the adult brain that coordinate revascularization and scar formation after injury.
Multi-modal dataset creation for federated learning with DICOM-structured reports
Tölle, Malte; Burger, Lukas; Kelm, Halvar; André, Florian; Bannas, Peter; Diller, Gerhard; Frey, Norbert; Garthe, Philipp; Groß, Stefan; Hennemuth, Anja; Kaderali, Lars; Krüger, Nina; Leha, Andreas; Martin, Simon; Meyer, Alexander; Nagel, Eike; Orwat, Stefan; Scherer, Clemens; Seiffert, Moritz; Seliger, Jan; Simm, Stefan; Friede, Tim; Seidler, Tim; Engelhardt, Sandy (2025)
Tölle, Malte; Burger, Lukas; Kelm, Halvar; André, Florian; Bannas, Peter...
International Journal of Computer Assisted Radiology and Surgery 20 (3), 485–495.
DOI: 10.1007/s11548-025-03327-y
Open Access Peer Reviewed
Purpose Federated training is often challenging on heterogeneous datasets due to divergent data storage options, inconsistent naming schemes, varied annotation procedures, and disparities in label quality. This is particularly evident in the emerging multi-modal learning paradigms, where dataset harmonization including a uniform data representation and filtering options are of paramount importance.Methods DICOM-structured reports enable the standardized linkage of arbitrary information beyond the imaging domain and can be used within Python deep learning pipelines with highdicom. Building on this, we developed an open platform for data integration with interactive filtering capabilities, thereby simplifying the process of creation of patient cohorts over several sites with consistent multi-modal data.Results In this study, we extend our prior work by showing its applicability to more and divergent data types, as well as streamlining datasets for federated training within an established consortium of eight university hospitals in Germany. We prove its concurrent filtering ability by creating harmonized multi-modal datasets across all locations for predicting the outcome after minimally invasive heart valve replacement. The data include imaging and waveform data (i.e., computed tomography images, electrocardiography scans) as well as annotations (i.e., calcification segmentations, and pointsets), and metadata (i.e., prostheses and pacemaker dependency).Conclusion Structured reports bridge the traditional gap between imaging systems and information systems. Utilizing the inherent DICOM reference system arbitrary data types can be queried concurrently to create meaningful cohorts for multi-centric data analysis. The graphical interface as well as example structured report templates are available at https://github.com/Cardio-AI/fl-multi-modal-dataset-creation .
Akustische Mehrschichtsystemcharakterisierung zur quantitativen Zustandsüberwachung von Hüftprothesen
Lützelberger, Jan (2025)
Vortrag, 4. Technologietag Angewandte Sensorik (TAS) des Instituts für Sensor- und Aktortechnik der Hochschule Coburg, Coburg, 2025.
Interview: Wissenschaft zu Homeoffice, Karenztag und Produktivität
Kohls, Niko (2025)
Wie positiv bleiben?
Kohls, Niko (2025)
Real world federated learning with a knowledge distilled transformer for cardiac CT imaging
Tölle, Malte; Garthe, Philipp; Scherer, Clemens; Seliger, Jan; Leha, Andreas; Krüger, Nina; Simm, Stefan; Martin, Simon; Eble, Sebastian; Kelm, Halvar; Bednorz, Moritz; André, Florian; Bannas, Peter; Diller, Gerhard; Frey, Norbert; Groß, Stefan; Hennemuth, Anja; Kaderali, Lars; Meyer, Alexander; Nagel, Eike; Orwat, Stefan; Seiffert, Moritz; Friede, Tim; Seidler, Tim; Engelhardt, Sandy (2025)
Tölle, Malte; Garthe, Philipp; Scherer, Clemens; Seliger, Jan; Leha, Andreas...
NPJ digital medicine 8 (1), 88.
DOI: 10.1038/s41746-025-01434-3
Open Access Peer Reviewed
Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert annotations, leaving large portions of unlabeled data unused. Leveraging these could enhance transformer architectures’ ability in regimes with small and diversely annotated sets. We conduct the largest federated cardiac CT analysis to date (n = 8, 104) in a real-world setting across eight hospitals. Our two-step semi-supervised strategy distills knowledge from task-specific CNNs into a transformer. First, CNNs predict on unlabeled data per label type and then the transformer learns from these predictions with label-specific heads. This improves predictive accuracy and enables simultaneous learning of all partial labels across the federation, and outperforms UNet-based models in generalizability on downstream tasks. Code and model weights are made openly available for leveraging future cardiac CT analysis.
How do patient and practitioner characteristics influence empathy in healthcare? Protocol for a systematic review and meta-analysis
White, Cleo; Khunti , Kamlesh ; Gillies , Clare ; Meißner, Karin; Palipana , Dinesh ; Nockels , Keith ; Howick, J. (2025)
White, Cleo; Khunti , Kamlesh ; Gillies , Clare ; Meißner, Karin; Palipana , Dinesh ...
BMJ open 15 (2), e096269.
DOI: 10.1136/bmjopen-2024-096269
Open Access Peer Reviewed
Die Bedeutung der Koniferen für die Erhaltung der Pilz-Artenvielfalt
Schulze, Ernst-Detlef ; Bouriaud, Oliver; Guenther, A; Tanunchai, Benjawan; Noll, Matthias; SChulze, Waltraud, X. (2025)
Schulze, Ernst-Detlef ; Bouriaud, Oliver; Guenther, A; Tanunchai, Benjawan...
Allgemeine Forstzeitung 2025 (1), 44 | 41-44.
Gratitude and sleep disturbance in primary care patients: the mediating roles of health self-efficacy, health behaviors, and psychological distress
Altier, H.; Hirsch, J; Weber, A; Kohls, Niko; Schelling, J.; Toussaint, L; Sirois, F; Offenbächer, M. (2025)
Altier, H.; Hirsch, J; Weber, A; Kohls, Niko; Schelling, J.; Toussaint, L; Sirois, F...
Frontiers in Sleep 4, 1459854.
DOI: 10.3389/frsle.2025.1459854
Reliability of continuous vital sign monitoring in post-operative patients employing consumer-grade fitness trackers: A randomised pilot trial
Helmer, Philipp; Hottenrott, Sebastian; Wienböker, Kathrin; Pryss, Rüdiger; Drosos, Vasileios; Seitz, Anna Katharina; Röder, Daniel; Jovanoviç, Aleksandar; Kranke, Peter; Meybohm, Patrick; Winkler, Bernd E (2024)
Helmer, Philipp; Hottenrott, Sebastian; Wienböker, Kathrin; Pryss, Rüdiger...
eCollection 2024 Jan-Dec (10), 20552076241254026.
DOI: 10.1177/20552076241254026
Open Access Peer Reviewed
Psychotherapy with somatosensory stimulation as a complementary treatment for women with endometriosis-associated pain – a qualitative study
Limmer, A.; Weber, Annemarie; Olliges, Elisabeth; Kraft, Jana; Beissner, F.; Preibisch, C.; Meißner, Karin (2024)
Limmer, A.; Weber, Annemarie; Olliges, Elisabeth; Kraft, Jana; Beissner, F....
BMC Complementary Medicine and Therapies 24, 426 | 1-9.
DOI: 10.1186/s12906-024-04731-8
Open Access Peer Reviewed
Was ist dran am Placebo-Effekt?
Meißner, Karin (2024)
Interview in Ö1, Sendung Dimensionen, 23.12.2024.
Open Access
Satiety-enhancing placebo intervention decreases selective attention to food cues
Lanz, Marina; Hoffmann, Verena; Meißner, Karin (2024)
Frontiers in Psychiatry 15, 1472532 | 1-11.
DOI: 10.3389/fpsyt.2024.1472532
Open Access Peer Reviewed
Best-Practice-Beispiele der Evaluationsforschung in der kommunalen Gesundheitsförderung: das Projekt „Gesunde Südstadt"
John, Dennis; Kohls, Niko (2024)
(77), 8.
DOI: 10.17883/fet-schriften077
Open Access
Seit Inkrafttreten des Präventionsgesetzes (PrävG) im Jahr 2015 wurden bundesweit Projekte der gesetzlichen Krankenversicherungen (GKV) zur Gesundheitsförderung und Prävention (GfP) initiiert. Die Messung der Wirkung von GfP wurde im PrävG nicht explizit formuliert, mit der Folge, dass in den letzten 10 Jahren externe Evaluationsstudien nicht flächendeckend und systematisch in GKV-geförderten Projekten zur GfP eingesetzt wurden. Dennoch gibt es einige Beispiele von Evaluationsstudien, die Effekte von GKV-geförderten Projekten der GfP auf relevante Zielgruppen in verschiedenen Lebenswelten empirisch untersucht haben, vor allem in der kommunalen Gesundheitsförderung. Evaluation von Projekten der GfP in Kommunen wurden sowohl in Städten als auch im ländlichen Raum durchgeführt. Evaluationsforschung in GKV-geförderten Projekten der GfP ist auch 10 Jahre nach Inkrafttreten des Präventionsgesetzes kein wissenschaftlicher Selbstzweck. Evidenzbasierung und Wirkungsorientierung tragen - auch vor dem Hintergrund eines zunehmenden legitimatorischen (Kosten-)Drucks - zur Nachhaltigkeit von Projekten der GfP bei. Im folgenden Beitrag wird ein Best-Practice-Beispiel vorgestellt, mit dem Ziel aufzuzeigen, wie externe Begleitevaluationen in GKV-geförderten Projekten der kommunalen Gesundheits-förderung integriert werden können.
TAM receptors mediate the Fpr2-driven pain resolution and fibrinolysis after nerve injury
Hartmannsberger, Beate; Ben-Kraiem, Adel; Kramer, Sofia; Guidolin, Carolina; Kazerani, Ida; Doppler, Kathrin; Thomas, Dominique; Gurke, Robert; Sisignano, Marco; Kalelkar, Pranav; García, Andrés; Monje, Paula; Nusrat, Asma; Sammeth, Michael; Krug, Susanne; Sommer, Claudia; Rittner, Heike (2024)
Hartmannsberger, Beate; Ben-Kraiem, Adel; Kramer, Sofia; Guidolin, Carolina...
Acta Neuropathologica 149 (16), 1.
Open Access Peer Reviewed
Feels like home: A biobased and biodegradable plastic offers a novel habitat for diverse plant pathogenic fungi in temperate forest ecosystems
Nonthijun, Parada; Tanunchai, Benjawan; Schroeter , Simon Andreas; Wahdan, S. F. M.; Alves , G. E.; Hilke , Ines; Buscot, F.; Schulze, Ernst-Detlef ; Disayathanoowat, Terd; Purahong, W.; Noll, Matthias (2024)
Nonthijun, Parada; Tanunchai, Benjawan; Schroeter , Simon Andreas; Wahdan, S. F. M....
Microbial Ecology 2024 (87), 155.
DOI: 10.1007/s00248-024-02466-0.
Open Access Peer Reviewed
Fakultät Angewandte Naturwissenschaften und Gesundheit (FNG)
Hochschule Coburg
Friedrich-Streib-Str. 2
96450 Coburg
Dr. phil. Jakob Hanke
Forschungsreferent
T +49 9561 317 360
jakob.hanke[at]hs-coburg.de