重新审视框监督：无偏的弱监督医学图像分割
Rethinking Box Supervision: Bias-Free Weakly Supervised Medical Segmentation
把边界框监督中的框形偏置显式建模为「掩码→框」对齐变换，并配合多尺度一致性自监督，这套训练期即插即用模块可直接迁移到任何只有框标注的密集预测任务（如病灶分割、伪装目标分割），且推理零开销。
原文依据 a Mask-to-Box transformation that aligns predicted masks with box annotations to reduce label mismatch and box-induced bias
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论医学图像分割的像素级标注成本高昂且耗费人力，通常需要专家知识。边界框标签提供了一种更具可扩展性的替代方案，但会引入强烈的框形偏置，从而损害分割质量。我们提出 WeakMed，一个通用的弱监督分割框架，它消除了对像素级掩码的依赖，同时克服了框监督的结构性局限。WeakMed 引入两个轻量、即插即用的训练组件：（1）掩码到框变换（Mask-to-Box），将预测掩码与框标注对齐，以减少标签不匹配和框诱导的偏置；（2）尺度一致性损失，施加多尺度自监督，以缓解弱标签的歧义性与不稳定性。两个模块仅在训练时使用，不带来任何推理开销。在 9 个分割任务、9 个数据集和 6 种成像模态上，WeakMed 一致地超越现有弱监督方法，并达到与全监督基线相当的性能。这些结果证明了其作为低成本、高质量医学图像分割方案的实用性。
英文原文摘要 1168 字符
Pixel-level annotations for medical image segmentation are costly and labor-intensive, often requiring expert knowledge. Bounding box labels provide a more scalable alternative but introduce strong box-shaped bias that hampers segmentation quality. We propose WeakMed, a general-purpose weakly supervised segmentation framework that removes the dependence on pixel-level masks while overcoming the structural limitations of box supervision. WeakMed introduces two lightweight, plug-and-play training components: (1) a Mask-to-Box transformation that aligns predicted masks with box annotations to reduce label mismatch and box-induced bias, and (2) a Scale Consistency loss that enforces multi-scale self-supervision to address the ambiguity and instability of weak labels. Both modules are used only during training and impose no inference overhead. Across 9 segmentation tasks, 9 datasets, and 6 imaging modalities, WeakMed consistently surpasses existing weakly supervised methods and achieves performance competitive with fully supervised baselines. These results demonstrate its practicality as a low-cost yet high-quality solution for medical image segmentation.