Responsive image





Handreichung zur Lehre mit (mathematischen) Concept Maps

Pawlowsky, Raik; Rischke, Roman; Wick , Michael (2025)

Tagungsband MINT-Symposium 2025, 395-402.


Open Access Peer Reviewed
more

Federated vs local vs central deep learning of tooth segmentation on panoramic radiographs

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.

more

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
more

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
more

Federated learning in dentistry: Chances and challenges

Rischke, Roman; Schneider, Lisa; Müller, Karsten; Samek, Wojciech; Schwendicke, Falk...

Journal of Dental Research 101 (11), 1269-1273.


Open Access Peer Reviewed
more

Auf dem Weg zu Energieeffizienter Künstlicher Intelligenz: Welche Energieeinsparpotentiale bieten KI-Anwendungen?

Babilon, Linda; Kratochwill, Lisa; Müller, Karsten; Rischke, Roman; Samek, Wojciech...

Deutsche-Energie-Agentur (Hrsg.).


Open Access
more

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
more

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