Federated Learning for Breast Density Classification: A Real-World Implementation
This addresses the problem of data privacy and diversity in medical imaging for healthcare institutions, though it is incremental as it applies an existing federated learning method to a new medical domain.
The study tackled the challenge of training robust deep learning models for breast density classification without centralizing data by implementing federated learning across seven clinical institutions, resulting in models that performed 6.3% better on average than locally trained ones and showed a 45.8% relative improvement in generalizability.
Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting. Seven clinical institutions from across the world joined this FL effort to train a model for breast density classification based on Breast Imaging, Reporting & Data System (BI-RADS). We show that despite substantial differences among the datasets from all sites (mammography system, class distribution, and data set size) and without centralizing data, we can successfully train AI models in federation. The results show that models trained using FL perform 6.3% on average better than their counterparts trained on an institute's local data alone. Furthermore, we show a 45.8% relative improvement in the models' generalizability when evaluated on the other participating sites' testing data.