Federated Data Model
This addresses data privacy and sharing problems for medical AI applications, offering a promising incremental improvement for cross-site model training.
The paper tackled the challenge of training robust deep learning models across different locations without sharing actual data due to privacy and regulatory issues, by developing the Federated Data Model (FDM) that uses diffusion models to create synthetic data; results showed that models trained with this method performed well on both original and external medical image data.
In artificial intelligence (AI), especially deep learning, data diversity and volume play a pivotal role in model development. However, training a robust deep learning model often faces challenges due to data privacy, regulations, and the difficulty of sharing data between different locations, especially for medical applications. To address this, we developed a method called the Federated Data Model (FDM). This method uses diffusion models to learn the characteristics of data at one site and then creates synthetic data that can be used at another site without sharing the actual data. We tested this approach with a medical image segmentation task, focusing on cardiac magnetic resonance images from different hospitals. Our results show that models trained with this method perform well both on the data they were originally trained on and on data from other sites. This approach offers a promising way to train accurate and privacy-respecting AI models across different locations.