arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.07939cs.CV
收藏

动态策略驱动的自适应多实例学习用于全切片图像分类

Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification

Harbin Institute of Technology(哈尔滨工业大学)

Tingting Zheng, Kui Jiang, Hongxun Yao

AI总结:

提出动态策略驱动的自适应多实例学习方法,通过动态采样和强化学习改进实例选择与特征聚合,在WSI分类中超越现有方法。

摘要:

多实例学习(MIL)在组织病理学全切片图像(WSI)分析中,使用包或伪包已展现出显著性能。它涉及实例采样、特征表示和决策制定。然而,现有的基于MIL的技术至少存在以下一个或多个问题:1)需要高存储和密集预处理来处理大量实例(采样);2)在知识有限的情况下预测包标签可能导致过拟合(特征表示);3)伪包数量和先验偏差影响模型的鲁棒性和泛化能力(决策制定)。受临床诊断的启发,利用过去的采样实例可以促进最终的WSI分析,但在先前技术中很少被探索。为了突破这些限制,我们将动态实例采样和强化学习集成到一个统一框架中,以改进实例选择和特征聚合,形成一种新颖的动态策略实例选择(DPIS)方案,以实现更好、更可信的决策。具体而言,采用特征距离度量和奖励函数来促进连续实例采样。为了缓解过拟合,我们探索实例间的潜在全局关系,以获得更鲁棒和判别性的特征表示,同时建立奖励和惩罚机制,利用对比学习纠正伪包中的偏差。这些策略构成了最终用于WSI任务的动态策略驱动的自适应多实例学习(PAMIL)方法。大量实验表明,我们的PAMIL方法在CAMELYON16数据集上比最先进方法提高了3.8%,在TCGA肺癌数据集上提高了4.4%。

英文摘要:

Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing MIL-based technologies at least suffer from one or more of the following problems: 1) requiring high storage and intensive pre-processing for numerous instances (sampling); 2) potential over-fitting with limited knowledge to predict bag labels (feature representation); 3) pseudo-bag counts and prior biases affect model robustness and generalizability (decision-making). Inspired by clinical diagnostics, using the past sampling instances can facilitate the final WSI analysis, but it is barely explored in prior technologies. To break free these limitations, we integrate the dynamic instance sampling and reinforcement learning into a unified framework to improve the instance selection and feature aggregation, forming a novel Dynamic Policy Instance Selection (DPIS) scheme for better and more credible decision-making. Specifically, the measurement of feature distance and reward function are employed to boost continuous instance sampling. To alleviate the over-fitting, we explore the latent global relations among instances for more robust and discriminative feature representation while establishing reward and punishment mechanisms to correct biases in pseudo-bags using contrastive learning. These strategies form the final Dynamic Policy-Driven Adaptive Multi-Instance Learning (PAMIL) method for WSI tasks. Extensive experiments reveal that our PAMIL method outperforms the state-of-the-art by 3.8\% on CAMELYON16 and 4.4\% on TCGA lung cancer datasets.

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。

↑