METHODS: We propose a universal framework for weakly supervised WSI analysis based on Multiple Instance Learning (MIL). To achieve effective aggregation of instance features, we design a feature aggregation module from multiple dimensions by considering feature distribution, instances correlation and instance-level evaluation. First, we implement instance-level standardization layer and deep projection unit to improve the separation of instances in the feature space. Then, a self-attention mechanism is employed to explore dependencies between instances. Additionally, an instance-level pseudo-label evaluation method is introduced to enhance the available information during the weak supervision process. Finally, a bag-level classifier is used to obtain preliminary WSI classification results. To achieve even more accurate WSI label predictions, we have designed a key instance selection module that strengthens the learning of local features for instances. Combining the results from both modules leads to an improvement in WSI prediction accuracy.
RESULTS: Experiments conducted on Camelyon16, TCGA-NSCLC, SICAPv2, PANDA and classical MIL benchmark datasets demonstrate that our proposed method achieves a competitive performance compared to some recent methods, with maximum improvement of 14.6 % in terms of classification accuracy.
CONCLUSIONS: Our method can improve the classification accuracy of whole slide images in a weakly supervised way, and more accurately detect lesion areas.
方法:我们提出了一种基于多实例学习(MIL)的弱监督WSI分析的通用框架。为了实现实例功能的有效聚合,我们通过考虑特征分布,从多个维度设计了一个特征聚合模块,实例相关性和实例级评估。首先,我们实现了实例级标准化层和深度投影单元,以改善特征空间中实例的分离。然后,采用自我注意机制来探索实例之间的依赖关系。此外,引入了一种实例级伪标签评估方法,以增强弱监督过程中的可用信息。最后,使用袋级分类器来获得初步的WSI分类结果。为了实现更准确的WSI标签预测,我们设计了一个关键实例选择模块,加强了实例本地特征的学习。组合来自两个模块的结果导致WSI预测准确性的提高。
结果:对Camelyon16,TCGA-NSCLC,SICAPv2,PANDA和经典的MIL基准测试数据集表明,与一些最近的方法相比,我们提出的方法具有竞争力。在分类精度方面最大提高14.6%。
结论:我们的方法可以以弱监督的方式提高整个幻灯片图像的分类精度,更准确地检测病变区域。