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

Lisa Schneider, Roman Rischke, Joachim Krois, Aleksander Krasowski, Martha Büttner, Hossein Mohammad-Rahimi, Akhilanand Chaurasia, Nielsen S Pereira, Jae-Hong Lee, Sergio E Uribe, Shahriar Shahab, Revan Birke Koca-Unsal, Gürkan Unsal, Yolanda Martinez-Beneyto, Janet Brinz, Olga Tryfonos, Falk Schwendicke (Coresponding Author)

Research output: Contribution to journalArticlepeer-review


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=1,881 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.

Original languageEnglish
Article number104556
Number of pages13
JournalJournal of Dentistry
Publication statusPublished - Aug 2023


  • Artificial Intelligence
  • Big Data
  • Computer Vision
  • Deep Learning
  • Informatics
  • Mathematical Models

Field of Science*

  • 2.6 Medical engineering
  • 1.2 Computer and information sciences
  • 3.3 Health sciences

Publication Type*

  • 1.1. Scientific article indexed in Web of Science and/or Scopus database


Dive into the research topics of 'Federated vs local vs central deep learning of tooth segmentation on panoramic radiographs'. Together they form a unique fingerprint.

Cite this