Continual learning (CL) methods designed for natural image classification often fail to reach basic quality standards for medical image segmentation. Atlas-based segmentation, a well-established approach in medical imaging, incorporates domain knowledge on the region of interest, leading to semantically coherent predictions. This is especially promising for CL, as it allows us to leverage structural information and strike an optimal balance between model rigidity and plasticity over time. When combined with privacy-preserving prototypes, this process offers the advantages of rehearsal-based CL without compromising patient privacy. We propose Atlas Replay, an atlas-based segmentation approach that uses prototypes to generate high-quality segmentation masks through image registration that maintain consistency even as the training distribution changes. We explore how our proposed method performs compared to state-of-the-art CL methods in terms of knowledge transferability across seven publicly available prostate segmentation datasets. Prostate segmentation plays a vital role in diagnosing prostate cancer, however, it poses challenges due to substantial anatomical variations, benign structural differences in older age groups, and fluctuating acquisition parameters. Our results show that Atlas Replay is both robust and generalizes well to yet-unseen domains while being able to maintain knowledge, unlike end-to-end segmentation methods. Our code base is available under https://github.com/MECLabTUDA/Atlas-Replay.

翻译：持续学习（CL）方法最初针对自然图像分类设计，却常难以达到医学图像分割的基本质量标准。基于图谱的分割作为医学影像领域成熟的技术，融合了感兴趣区域的领域知识，从而生成语义一致的预测。这一特性对持续学习尤为有利，因为它能利用结构信息，在模型刚性与可塑性之间实现动态最优平衡。当与隐私保护原型结合时，该流程既具备基于重演的持续学习优势，又不损害患者隐私。我们提出Atlas Replay方法，这是一种基于图谱的分割方法，通过图像配准利用原型生成高质量分割掩膜，即便训练分布发生变化仍能保持一致性。我们探究了所提方法与现有最先进持续学习方法在七个公开前列腺分割数据集上的知识迁移能力差异。前列腺分割在前列腺癌诊断中至关重要，但由于解剖结构显著变异、老年群体良性结构差异以及采集参数波动等因素，该任务颇具挑战。实验结果表明，与端到端分割方法不同，Atlas Replay既具备鲁棒性，能良好泛化至未见领域，又能维持已有知识。我们的代码库已开源至 https://github.com/MECLabTUDA/Atlas-Replay。