RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture
Researchers have developed RadJEPA, a novel self-supervised learning framework for medical image analysis, specifically for chest X-rays. Unlike previous methods that rely on paired image-text data, RadJEPA learns from approximately 840,000 unlabeled X-ray images by predicting masked regions from a visible context. This approach aims to overcome limitations of clinical narrative bias and data availability. Evaluations show RadJEPA matches or surpasses existing image-only and vision-language baselines in radiology report generation, disease classification, and semantic segmentation tasks. AI
IMPACT This research could enable more robust medical image analysis by reducing reliance on labeled data, potentially improving diagnostic tools.