Continual Learning in Medical Imaging: Methods, Foundation Models, Challenges, and Clinical Translation

Source abstract

Deep learning now supports many tasks in medical imaging, but most systems assume a fixed data source and a single training event. Clinical practice is not static: new scanners arrive, protocols change, patient populations shift, and new diagnostic questions appear. A model that trains once and stays frozen tends to lose accuracy over time, while a model that retrains on new data alone tends to forget what it already knew, a failure known as catastrophic forgetting. Continual learning studies how a model can learn from a stream of data and tasks while it keeps prior knowledge. This survey reviews continual learning in medical imaging with a focus on recent progress. We report a reproducible review methodology, formalize the three learning scenarios, and organize methods into five families: regularization, replay, dynamic architectures, foundation-model adaptation, and hybrids. We give particular attention to the shift toward frozen foundation models with lightweight adapters. We review applications across tasks and modalities, give a critical analysis of study quality that separates peer-reviewed work from preprints, and connect the methods to the current regulatory framework for model updates. We close with open problems, aiming to give researchers and clinical teams a clear and current reference for building systems that adapt safely over time.