arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.22091cs.CVcs.LG
收藏

超越主导标签:用多实例学习恢复共存的病变证据

Beyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance Learning

USTC(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究所,合肥综合性国家科学中心)

Lubin Gan, Jing Zhang, Xinming Zhang, Chengpeng Xu, Siying Wu, Xiaoyan Sun

AI总结:

该研究针对全切片图像中弱监督仅提供最严重诊断的问题,提出DomSet-MIL框架,通过主导标签删失似然等技术恢复共存病变证据,实现了更优的主导标签预测与次要病变保留。

摘要:

全切片图像可能包含共存的病变,但弱监督通常仅提供最严重的诊断。我们将此场景表述为主导标签多实例学习,其中观测到的标签是潜在病变集中严重程度最高的元素。标准多类别多实例学习(MIL)将其视为完整的独热描述,因此当低严重度证据与主导病变共存时会将其抑制。我们提出DomSet-MIL,这是一种感知标签的框架,可对齐包级和实例级的标注机制。主导标签删失似然对报告的诊断进行建模,同时不将未报告的病变判定为不存在;严重度排序残差路由按从高到低的严重度分配图像块证据,保留对次要发现的残差支持;而top-q池化将局部路由分数与包预测关联。在自然和受控场景下的实验表明,DomSet-MIL在主导标签预测上达到了当前最优性能,同时能更有效地恢复潜在的共存病变证据。这些发现表明,对主导标签机制进行建模可在不牺牲临床有意义的次要发现的情况下提升诊断预测效果。

英文摘要:

Whole-slide images may contain coexisting lesions, yet weak supervision typically provides only the most severe diagnosis. We formulate this setting as dominant-label multiple instance learning, where the observed label is the maximum-severity element of a latent lesion set. Standard multiclass MIL treats it as a complete one-hot description and therefore suppresses lower-severity evidence whenever it co-occurs with a dominant lesion. We propose DomSet-MIL, a label-aware framework that aligns the annotation mechanism across bag and instance levels. Dominant-Label Censored Likelihood models the reported diagnosis without declaring unreported lesions absent. Severity-Ordered Residual Routing assigns patch evidence from high to low severity and preserves residual support for secondary findings, while top-$q$ pooling links local routing scores to bag prediction. Experiments across natural and controlled settings show that DomSet-MIL achieves state-of-the-art performance in dominant-label prediction while more effectively recovering latent coexisting-lesion evidence. These findings demonstrate that modeling the dominant-label mechanism can improve diagnostic prediction without sacrificing clinically meaningful secondary findings.

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。

↑