超越持续学习中的遗忘：持续医学图像分割的全面基准研究
Beyond Forgetting in Continual Medical Image Segmentation: A Comprehensive Benchmark Study
AI总结：
本文针对持续医学图像分割中的三大挑战，提出全面的基准研究，评估了不同方法在泛化性、遗忘抑制、可塑性等方面的表现，发现基于重放的方法在稳定性和可塑性之间取得最佳平衡。
摘要：
持续学习（CL）对于在临床环境中部署医学图像分割模型至关重要，因为成像领域、解剖目标和诊断任务会随时间演变。然而，持续分割仍面临三大主要挑战：首先，该任务的场景仍不足以标准化以适应真实临床环境；其次，现有研究主要集中在减轻遗忘，忽略了其他关键属性如可塑性；第三，缺乏对现有方法的全面评估基准。为解决这些差距，我们提出了持续医学图像分割的基准研究。我们首先定义了三个临床驱动的场景，即域持续学习（Domain-CL）、类持续学习（Class-CL）和器官持续学习（Organ-CL），分别捕捉跨中心域偏移、增量解剖结构分割和跨器官分割。然后，我们引入了一个评估框架，不仅测量通用性能和遗忘，还测量可塑性、正向泛化能力、参数效率和重放负担。结果表明，开发一个同时满足所有要求的模型仍然具有挑战性。然而，这些研究也表明，基于重放的方法在稳定性和可塑性之间取得了最佳平衡，参数隔离方法应能有效减少遗忘，尽管会增加模型大小，而正向泛化能力仍然是该研究领域中显著被忽视的方面。最后，我们讨论了相关学习范式，并概述了持续医学图像分割的未来研究方向。
英文摘要：
Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical targets, and diagnostic tasks evolve over time. However, continual segmentation still faces three main challenges. First, the scenarios for this task remain insufficiently standardized for real-world clinical settings. Second, existing research has been primarily focused on mitigating forgetting, overlooking the other essential properties such as plasticity. Third, a benchmark work with comprehensive evaluation on existing methods is stll desirable. To address these gaps, we present such benchmark study of continual medical image segmentation. We first define three clinically motivated scenarios, namely Domain-CL, Class-CL, and Organ-CL, to respectively capture the cross-center domain shift, the incremental anatomical structure segmentation, and the cross-organ segmentation. We then introduce an evaluation framework that measures not only general performance and forgetting, but also plasticity, forward generalizability, parameter efficiency, and replay burden. The results, from extensive experiments with representative CL methods, showed that it was still challenging to develop a model that could satisfy all the requirements simultaneously. Nevertheless, these studies also suggested that the replay-based methods achieve the best overall balance between stability and plasticity, the parameter-isolation methods should be effective at reducing forgetting, though at the cost of increased model size, and the forward generalizability remain a significantly understudied aspect of this research field. Finally, we discuss related learning paradigms and outline future directions for continual medical image segmentation.
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。
