发表机构
Ahsanullah University of Science and Technology（阿萨努拉科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
UCBound-Net利用MC Dropout不确定性，通过三个协同组件缓解临床超声分割中的灾难性遗忘，在BUSI和TN3K数据集上实现更优性能且无需任务边界监督。
AI 中文摘要
临床成像中的持续学习面临双重挑战：模型必须同化来自新解剖域的知识，同时保留从先前任务中学到的表征，这一问题被称为灾难性遗忘。现有缓解策略包括正则化和知识蒸馏，它们平等对待所有空间区域，却忽略了预测不确定性与遗忘倾向密切相关这一事实。我们提出UCBound-Net，这是一种利用蒙特卡洛（MC）Dropout不确定性作为遗忘风险空间代理的持续分割框架。该方法包含三个协同组件：（i）不确定性加权边界蒸馏，它放大了冻结教师模型高熵区域的知识迁移信号；（ii）不确定性校准正则化，它明确惩罚过度自信的错误预测；（iii）不确定性引导样本选择，这是一个优先存储边界区域表现出最高预测熵的样本的记忆缓冲区。在包含乳腺超声（BUSI，任务1）和后续甲状腺超声（TN3K，任务2）的序列域增量基准上评估，UCBound-Net相较于朴素微调减少了遗忘，实现了-0.098的反向迁移（BWT），而朴素微调的BWT为-0.173，同时在两个任务中获得了0.755的平均戴斯相似系数（DSC）。所提出的框架优于基线方法，且无需任务边界监督。消融研究进一步表明，每个组件独立对遗忘缓解有贡献，为临床图像分割的不确定性感知持续学习提供了实用途径。
英文摘要
Continual learning in clinical imaging faces a dual challenge: a model must assimilate knowledge from new anatomical domains while retaining representations learned from prior tasks, a problem known as catastrophic forgetting. Existing mitigation strategies, including regularization and knowledge distillation, treat all spatial regions equally, ignoring the fact that prediction uncertainty is strongly correlated with the propensity for forgetting. We introduce UCBound-Net, a continual segmentation framework that exploits Monte Carlo (MC) Dropout uncertainty as a spatial proxy for forgetting risk. Our method contributes three synergistic components: (i) uncertainty-weighted boundary distillation, which amplifies the knowledge transfer signal at high-entropy regions of the frozen teacher; (ii) uncertainty-calibration regularization, which explicitly penalizes overconfident erroneous predictions; and (iii) uncertainty-guided exemplar selection, a memory buffer that preferentially stores samples whose boundary regions exhibit the highest predictive entropy. Evaluated on a sequential domain-incremental benchmark comprising breast ultrasound (BUSI, Task 1) followed by thyroid ultrasound (TN3K, Task 2), UCBound-Net reduces forgetting relative to naive fine-tuning, achieving a backward transfer (BWT) of -0.098 compared with -0.173, while obtaining an average Dice Similarity Coefficient (DSC) of 0.755 across both tasks. The proposed framework outperforms baseline methods without requiring task-boundary supervision. An ablation study further demonstrates that each component contributes independently to forgetting mitigation, providing a practical pathway toward uncertainty-aware continual learning for clinical image segmentation.
CommentsAccepted at the MICCAI 2026 CLiMeM Workshop
