Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
This addresses the need for more robust and versatile AI in radiology, though it appears incremental as an application of self-supervised learning to medical imaging.
The researchers tackled the problem of limited generalizability and unexplored biases in medical foundation models by developing RayDINO, a self-supervised visual encoder trained on 873k chest X-rays. They achieved state-of-the-art results across nine radiology tasks and improved generalization to unseen populations while mitigating bias.
AI Foundation models are gaining traction in various applications, including medical fields like radiology. However, medical foundation models are often tested on limited tasks, leaving their generalisability and biases unexplored. We present RayDINO, a large visual encoder trained by self-supervision on 873k chest X-rays. We compare RayDINO to previous state-of-the-art models across nine radiology tasks, from classification and dense segmentation to text generation, and provide an in depth analysis of population, age and sex biases of our model. Our findings suggest that self-supervision allows patient-centric AI proving useful in clinical workflows and interpreting X-rays holistically. With RayDINO and small task-specific adapters, we reach state-of-the-art results and improve generalization to unseen populations while mitigating bias, illustrating the true promise of foundation models: versatility and robustness.