多实例学习框架与掩码困难实例挖掘用于全切片图像分类
Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification
AI总结：
提出MHIM-MIL框架，通过孪生结构挖掘困难实例，提升全切片图像分类性能，在多个数据集上优于现有方法。
摘要：
全切片图像（WSI）分类通常被表述为多实例学习（MIL）问题。由于阳性组织仅占十亿像素级WSI的一小部分，现有的MIL方法直观地通过注意力机制聚焦于识别显著实例。然而，这导致了对易分类实例的偏倚，而忽视了难分类实例。一些文献已揭示，困难样本有助于精确建模判别边界。通过在实例层面应用这一思想，我们精心设计了一种新颖的带有掩码困难实例挖掘的MIL框架（MHIM-MIL），该框架使用带有一致性约束的孪生结构（教师-学生）来探索潜在的困难实例。基于注意力分数的多种实例掩码策略，MHIM-MIL采用动量教师隐式挖掘困难实例以训练学生模型，该学生模型可以是任何基于注意力的MIL模型。这种反直觉的策略本质上使学生能够学习到更好的判别边界。此外，学生用于通过指数移动平均（EMA）更新教师，这反过来为后续训练迭代识别新的困难实例并稳定优化。在CAMELYON-16和TCGA肺癌数据集上的实验结果表明，MHIM-MIL在性能和训练成本方面优于其他最新方法。代码可在以下网址获取：https://github.com/DearCaat/MHIM-MIL。
英文摘要：
The whole slide image (WSI) classification is often formulated as a multiple instance learning (MIL) problem. Since the positive tissue is only a small fraction of the gigapixel WSI, existing MIL methods intuitively focus on identifying salient instances via attention mechanisms. However, this leads to a bias towards easy-to-classify instances while neglecting hard-to-classify instances. Some literature has revealed that hard examples are beneficial for modeling a discriminative boundary accurately. By applying such an idea at the instance level, we elaborate a novel MIL framework with masked hard instance mining (MHIM-MIL), which uses a Siamese structure (Teacher-Student) with a consistency constraint to explore the potential hard instances. With several instance masking strategies based on attention scores, MHIM-MIL employs a momentum teacher to implicitly mine hard instances for training the student model, which can be any attention-based MIL model. This counter-intuitive strategy essentially enables the student to learn a better discriminating boundary. Moreover, the student is used to update the teacher with an exponential moving average (EMA), which in turn identifies new hard instances for subsequent training iterations and stabilizes the optimization. Experimental results on the CAMELYON-16 and TCGA Lung Cancer datasets demonstrate that MHIM-MIL outperforms other latest methods in terms of performance and training cost. The code is available at: https://github.com/DearCaat/MHIM-MIL.
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。
