Publications by authors named "Markus Bujotzek"
Real-world federated learning in radiology: hurdles to overcome and benefits to gain.
J Am Med Inform Assoc
January 2025
Objective: Federated Learning (FL) enables collaborative model training while keeping data locally. Currently, most FL studies in radiology are conducted in simulated environments due to numerous hurdles impeding its translation into practice. The few existing real-world FL initiatives rarely communicate specific measures taken to overcome these hurdles.
View Article and Find Full Text PDFArticle Synopsis
- Medical Object Detection (MOD) enhances image processing by identifying key structures in radiological images using bounding boxes, but it struggles with data privacy issues that limit dataset availability.
- Federated Learning (FL) addresses these privacy concerns by allowing model training without transferring patient data, yet its application to MOD has been under-explored.
- This study introduces an open-source, self-configuring Federated MOD framework that combines FL with existing MOD techniques, demonstrating effective training strategies through simulated scenarios and analyzing how dataset characteristics influence model performance.
The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research.
View Article and Find Full Text PDF