Curia: A Multi-Modal Foundation Model for Radiology

Radiology is at the center of many medical specialties, which rely on radiologists' interpretation of images from various modalities, including CT, MRI, ultrasound, and X-ray [1]. The analysis of these images is crucial for detecting and characterizing medical conditions, quantifying disease progression, and monitoring treatment efficacy across a broad spectrum of diseases. AI has the potential to enhance radiology workflows and improve radiologists' efficiency, particularly for labor-intensive tasks such as image segmentation, or specialized and/or complex tasks which are prone to inter-reader variability [2, 3]. To date, the dominant paradigm in radiological AI development has involved training specialized models for individual tasks such as segmentation, abnormality detection (e.g., tumor detection), or pathology classification. However, this "one-task, one-model" approach is exceptionally resource-intensive, as it necessitates the curation and manual annotation of large, task-specific datasets for each modality and clinical application [4, 5]. It is potentially one of the bottlenecks in moving AI radiology models into the clinical workflow. Foundation models (FM) represent a significant paradigm shift in the field of AI.