arXiv 2303.157492023-08-23cs.CV

用于全切片图像分类的从实例到包分类器的迭代耦合多示例学习

Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classification

Zhejiang University（浙江大学）；The Hong Kong University of Science and Technology（香港科技大学）；Sir Run Run Shaw Hospital（邵逸夫医院）；Zhejiang Lab（之江实验室）；Ritsumeikan University（立命馆大学）

Hongyi Wang, Luyang Luo, Fang Wang, Ruofeng Tong, Yen-Wei Chen, Hongjie Hu, Lanfen Lin, Hao Chen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对全切片图像分类中多示例学习两模块训练脱节的问题，提出迭代耦合框架ICMIL，低成本实现嵌入器与分类器的信息交互，在多数据集和骨干网络上均取得性能提升。

摘要：

全切片图像（Whole Slide Image, WSI）分类因分辨率极高且缺乏细粒度标签，仍是一项挑战性任务。目前，在仅拥有切片级标签时，WSI分类通常被视为多示例学习（Multiple Instance Learning, MIL）问题。MIL方法包含补丁嵌入模块和包级分类模块，但以端到端方式训练二者的计算成本过高，难以实现。因此，现有方法通常将二者分开训练，或直接跳过嵌入器的训练。这类方案导致补丁嵌入器无法获取切片级语义标签，造成整个MIL流水线内部存在不一致性。为解决该问题，我们提出了名为Iteratively Coupled MIL（ICMIL，迭代耦合MIL）的新型框架，该框架打通了从包级分类器到补丁嵌入器的损失反向传播流程。在ICMIL中，我们利用包级分类器中的类别信息，指导补丁特征提取器的补丁级微调。经优化的嵌入器随后会生成更优的实例表示，以实现更精准的包级分类器。通过以较低成本耦合补丁嵌入器与包分类器，我们提出的框架实现了两个模块间的信息交互，使整个MIL分类模型受益。我们使用三种不同的骨干网络在两个数据集上测试了该框架，实验结果表明，其性能相较于当前最优的MIL方法有持续提升。代码可在以下链接获取：https://github.com/Dootmaan/ICMIL。

英文摘要：

Whole Slide Image (WSI) classification remains a challenge due to their extremely high resolution and the absence of fine-grained labels. Presently, WSI classification is usually regarded as a Multiple Instance Learning (MIL) problem when only slide-level labels are available. MIL methods involve a patch embedding module and a bag-level classification module, but they are prohibitively expensive to be trained in an end-to-end manner. Therefore, existing methods usually train them separately, or directly skip the training of the embedder. Such schemes hinder the patch embedder's access to slide-level semantic labels, resulting in inconsistency within the entire MIL pipeline. To overcome this issue, we propose a novel framework called Iteratively Coupled MIL (ICMIL), which bridges the loss back-propagation process from the bag-level classifier to the patch embedder. In ICMIL, we use category information in the bag-level classifier to guide the patch-level fine-tuning of the patch feature extractor. The refined embedder then generates better instance representations for achieving a more accurate bag-level classifier. By coupling the patch embedder and bag classifier at a low cost, our proposed framework enables information exchange between the two modules, benefiting the entire MIL classification model. We tested our framework on two datasets using three different backbones, and our experimental results demonstrate consistent performance improvements over state-of-the-art MIL methods. The code is available at: https://github.com/Dootmaan/ICMIL.

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。