面向隐私感知数字病理学的持续域增量学习
Continual Domain Incremental Learning for Privacy-aware Digital Pathology
AI总结：
针对数字病理模型在染色、器官等分布偏移下易遗忘且回放存储数据存在隐私风险的问题，提出GLRCL，用高斯混合模型生成潜在特征回放，性能接近大型缓冲区方法。
摘要：
近年来，借助先进深度学习算法对复杂组织模式进行建模，数字病理学领域取得了显著进展。然而，在存在数据偏移（例如不同染色、器官、中心等）的情况下，这些模型的鲁棒性往往会严重下降。持续学习（CL）技术则旨在学习具有分布偏移条件的新数据时，减少对过去数据的遗忘。具体而言，基于回放的CL技术会将部分过去数据存储在缓冲区中，随后将其与新数据一起回放，这类方法已被证明在医学图像分析任务中有效。但由于这些方法会存储过去数据，因此引发隐私担忧，这促使我们开发了新型基于生成式潜在回放的CL（GLRCL）方法。GLRCL通过高斯混合模型捕获先前分布，而不是存储过去样本；随后利用这些模型生成特征，并与新数据执行潜在回放。我们在组织病理学数据的不同偏移条件下系统评估了所提出框架，包括染色偏移和器官偏移。我们的方法显著优于流行的无缓冲区CL方法，并且表现与基于回放的CL方法相近，而后者需要大型缓冲区并会造成严重隐私侵犯。
英文摘要：
In recent years, there has been remarkable progress in the field of digital pathology, driven by the ability to model complex tissue patterns using advanced deep-learning algorithms. However, the robustness of these models is often severely compromised in the presence of data shifts (e.g., different stains, organs, centers, etc.). Alternatively, continual learning (CL) techniques aim to reduce the forgetting of past data when learning new data with distributional shift conditions. Specifically, rehearsal-based CL techniques, which store some past data in a buffer and then replay it with new data, have proven effective in medical image analysis tasks. However, privacy concerns arise as these approaches store past data, prompting the development of our novel Generative Latent Replay-based CL (GLRCL) approach. GLRCL captures the previous distribution through Gaussian Mixture Models instead of storing past samples, which are then utilized to generate features and perform latent replay with new data. We systematically evaluate our proposed framework under different shift conditions in histopathology data, including stain and organ shift. Our approach significantly outperforms popular buffer-free CL approaches and performs similarly to rehearsal-based CL approaches that require large buffers causing serious privacy violations.
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。
