Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation

统一主动学习与半监督学习以实现医学图像分割

Abstract: In practical settings, medical image segmentation models are often developed with limited annotated data rather than fully labeled datasets. Training frequently begins in ultra-low labeled regimes where only a small number of volumes are annotated. In such scenarios, practitioners must simultaneously decide which cases to annotate and how to best use the remaining unlabeled data.

摘要： 在实际应用中，医学图像分割模型的开发往往依赖于有限的标注数据，而非全标注数据集。训练通常始于极低标注量的环境，即仅有少量数据卷被标注。在这种情况下，从业者必须同时决定哪些案例需要标注，以及如何最有效地利用剩余的未标注数据。

Although active learning (AL) and semi-supervised learning (SSL) both target annotation scarcity, they are typically designed and optimized independently, resulting in objective mismatch and unstable training during early-stage “cold start” conditions. We propose RegAL, a unified active semi-supervised framework governed by a shared topology-aware Pareto optimization that couples sample acquisition with unlabeled data utilization.

尽管主动学习（AL）和半监督学习（SSL）都旨在解决标注稀缺问题，但它们通常是独立设计和优化的，这导致了目标不匹配，并在早期的“冷启动”阶段导致训练不稳定。我们提出了 RegAL，这是一个统一的主动半监督框架，由共享的拓扑感知帕累托优化（topology-aware Pareto optimization）控制，将样本获取与未标注数据利用相结合。

RegAL evaluates images along three complementary axes, voxel-wise uncertainty, feature diversity, and a novel topological consistency metric, to select anatomically informative edge cases for annotation. On the other hand, the same criteria are used to identify geometrically stable atlas candidates for diffeomorphic registration-guided augmentation to train a self-supervised Mean Teacher segmentation network.

RegAL 通过三个互补维度——体素级不确定性、特征多样性以及一种新颖的拓扑一致性指标——来评估图像，从而筛选出具有解剖学信息价值的边缘案例进行标注。另一方面，同样的标准也被用于识别几何稳定的图谱候选者，以进行微分同胚配准引导的数据增强，从而训练一个自监督的 Mean Teacher 分割网络。

Across BraTS 2021, dHCP, and ProstateX, RegAL remains stable with few labeled volumes and consistently outperforms state-of-the-art AL, SSL, and active semi-supervised baselines across Dice and boundary-distance (ASD, HD95) metrics under extreme annotation scarcity.

在 BraTS 2021、dHCP 和 ProstateX 数据集上的实验表明，RegAL 在极少标注数据的情况下依然保持稳定，并且在极端标注稀缺的条件下，其 Dice 系数和边界距离指标（ASD, HD95）均持续优于当前最先进的 AL、SSL 及主动半监督基准模型。