面向通用医疗模型的类别增量持续学习
Class-Incremental Continual Learning for General Purpose Healthcare Models
AI总结：
本研究针对医疗场景中深度学习微调易出现的灾难性遗忘问题，在四类医学影像场景、十个多源分类数据集上测试多种持续学习方法，验证了单模型跨专科增量学习的可行性，为通用医学影像AI跨机构共享提供支撑。
摘要：
医疗诊所经常会遇到因患者群体差异、治疗政策调整、医疗设备更新以及新发疾病模式而产生的动态数据。在此类场景中对深度学习模型进行微调时，模型可能会遭遇灾难性遗忘问题，导致其在先前已学习任务上的表现不佳。持续学习能够让模型在学习新任务的同时，不会出现在旧任务上性能下降的情况。在本研究中，我们针对四种不同的医学影像场景，探究了持续学习模型的性能，这些场景涵盖了来自不同模态、临床专科和医院的十个分类数据集。我们实现了多种持续学习方法，并在这些场景中评估了它们的性能。研究结果表明，单个模型能够按顺序学习来自不同专科的新任务，并且能达到与朴素方法相当的性能。这些发现证明了在相同或不同的医学专科之间复用或共享模型的可行性，为可跨机构共享的通用医学影像AI的发展又推进了一步。
英文摘要：
Healthcare clinics regularly encounter dynamic data that changes due to variations in patient populations, treatment policies, medical devices, and emerging disease patterns. Deep learning models can suffer from catastrophic forgetting when fine-tuned in such scenarios, causing poor performance on previously learned tasks. Continual learning allows learning on new tasks without performance drop on previous tasks. In this work, we investigate the performance of continual learning models on four different medical imaging scenarios involving ten classification datasets from diverse modalities, clinical specialties, and hospitals. We implement various continual learning approaches and evaluate their performance in these scenarios. Our results demonstrate that a single model can sequentially learn new tasks from different specialties and achieve comparable performance to naive methods. These findings indicate the feasibility of recycling or sharing models across the same or different medical specialties, offering another step towards the development of general-purpose medical imaging AI that can be shared across institutions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
