Researchers develop privacy-friendly, secure and sustainable AI techniques for medical imaging

AI Summary

Researchers at the Karlsruhe Institute of Technology demonstrated a federated-learning approach that lets hospitals train medical-imaging AI models without sharing sensitive patient data. The work explores radiation therapy applications and is presented as a secure, sustainable, and more accessible way to develop clinical AI.

Artificial intelligence can be helpful in analyzing medical images and support radiotherapy planning workflows. However, huge amounts of sensitive patient data are needed to train robust AI models. Researchers at the Karlsruhe Institute of Technology (KIT) have investigated how hospitals can jointly develop AI models for radiation therapy applications without exchanging such data. In their project, they use federated learning, a process in which a single model is trained at a decentralized location while the data remains in place. Their results demonstrate not only the technical feasibility of the approach but also its safe, more sustainable, and accessible use.