基于Shapley值的渐进式伪袋增强方法用于全切片图像分类
Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification
AI总结：
本文提出利用Shapley值改进全切片图像多实例学习中的实例重要性估计，并通过渐进式伪袋分配平衡注意力分布，在多个病理数据集上取得优于现有方法的分类性能。
摘要：
在计算病理学中，全切片图像（WSI）分类因其十亿像素级分辨率和有限的细粒度标注而面临巨大挑战。多实例学习（MIL）提供了一种弱监督解决方案，但从包级标签中细化实例级信息仍然困难。大多数传统MIL方法使用注意力分数来估计对切片标签预测有贡献的实例重要性分数（IIS），但这些方法往往导致注意力分布偏斜，并且在识别关键实例时存在不准确性。为了解决这些问题，我们提出了一种受合作博弈论启发的新方法：利用Shapley值评估每个实例的贡献，从而改进IIS估计。随后使用注意力机制加速Shapley值的计算，同时保留增强的实例识别与优先级排序能力。我们进一步引入了一个基于估计的IIS进行渐进式伪袋分配的框架，以鼓励MIL模型中的注意力分布更加均衡。我们在CAMELYON-16、BRACS、TCGA-LUNG和TCGA-BRCA数据集上的大量实验表明，我们的方法优于现有的最先进方法，提供了更强的可解释性和类别层面的洞察。源代码可在https://github.com/RenaoYan/PMIL获取。
英文摘要：
In computational pathology, whole-slide image (WSI) classification presents a formidable challenge due to its gigapixel resolution and limited fine-grained annotations. Multiple-instance learning (MIL) offers a weakly supervised solution, yet refining instance-level information from bag-level labels remains challenging. While most of the conventional MIL methods use attention scores to estimate instance importance scores (IIS) which contribute to the prediction of the slide labels, these often lead to skewed attention distributions and inaccuracies in identifying crucial instances. To address these issues, we propose a new approach inspired by cooperative game theory: employing Shapley values to assess each instance's contribution, thereby improving IIS estimation. The computation of the Shapley value is then accelerated using attention, meanwhile retaining the enhanced instance identification and prioritization. We further introduce a framework for the progressive assignment of pseudo bags based on estimated IIS, encouraging more balanced attention distributions in MIL models. Our extensive experiments on CAMELYON-16, BRACS, TCGA-LUNG, and TCGA-BRCA datasets show our method's superiority over existing state-of-the-art approaches, offering enhanced interpretability and class-wise insights. Our source code is available at https://github.com/RenaoYan/PMIL.
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。
